diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 0a8a41daf..4f4d4f37e 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -33,14 +33,14 @@ repos:
           - id: black
             name: black - consistent Python code formatting (auto-fixes)
             language_version: python # Should be a command that runs python3.6+
-            exclude: .*/tests/.*|^\.cruft\.json$|.*\tests\.*|helpers/.*
+            exclude: .*/tests/.*|^\.cruft\.json$|.*\tests\.*|helpers/.*|^tests
             args: ["--experimental-string-processing", "--line-length=88"]
     - repo: https://github.com/PyCQA/flake8
       rev: 5.0.4
       hooks:
           - id: flake8
             name: flake8 - Python linting
-            exclude: .*/tests*|^\.cruft\.json|helpers/.*|.*\tests*$
+            exclude: .*/tests*|^\.cruft\.json|helpers/.*|.*\tests*$|^tests
     - repo: https://github.com/nbQA-dev/nbQA
       rev: 0.12.0
       hooks:
diff --git a/config/backdata_schema.toml b/config/backdata_schema.toml
index e6d5719cc..c2cfe4a8e 100644
--- a/config/backdata_schema.toml
+++ b/config/backdata_schema.toml
@@ -1,1157 +1,367 @@
-# Network schema file matches working schema on DAP
-
 [reference]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = false
-Current_Data_Type = "str"
-Length = ">=1"
-Min_values = 11001603625
-Max_values = 19891309165
-Possible_Categorical_Values = ["nan"]
-
-[status]
-Description = "nan"
-Deduced_Data_Type = "category"
-Nullable = false
-Current_Data_Type = "str"
-Length = ">=1"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = ["Clear", "Clear - overridden", "Form saved", "Clear - overridden SE", "Form sent out", "Check needed", "Combined child (NIL2)", "Out of scope (NIL3)", "Ceased trading (NIL4)", "Dormant (NIL5)", "Part year return (NIL8)", "No UK activity (NIL9)"]
+old_name = "reference"
+Deduced_Data_Type = "int64"
 
 [instance]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = ["nan"]
-q_code = ""
-old_ref = "nan"
+old_name = "instance"
+Deduced_Data_Type = "int64"
 
 [101]
-Description = "nan"
-Deduced_Data_Type = "str"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = ["nan",]
-q_code = ""
-old_ref = "nan"
-
-[102]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = ["nan",]
-q_code = ""
-old_ref = "nan"
+old_name = "101"
+Deduced_Data_Type = "object"
 
 [103]
-Description = "nan"
-Deduced_Data_Type = "str"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = ["nan",]
-q_code = ""
-old_ref = "nan"
+old_name = "103"
+Deduced_Data_Type = "float64"
 
 [104]
-Description = "nan"
-Deduced_Data_Type = "str"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = ["nan",]
-q_code = ""
-old_ref = "nan"
+old_name = "104"
+Deduced_Data_Type = "float64"
 
 [200]
-Description = "Business type: Civil or Defence"
-Deduced_Data_Type = "str"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_Categorical_Values = []
-q_code = ""
-old_ref = "c_or_d"
+old_name = "200"
+Deduced_Data_Type = "object"
 
 [201]
-Description = "Published Product Group"
-Deduced_Data_Type = "str"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_Categorical_Values = []
-q_code = ""
-old_ref = "selgrpno"
+old_name = "201"
+Deduced_Data_Type = "object"
 
 [202]
-Description = "Salaries & Wages"
+old_name = "202"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_Categorical_Values = []
-q_code = "q202"
-old_ref = "slries"
 
 [203]
-Description = "Other current expenditure"
+old_name = "203"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_Categorical_Values = []
-q_code = "q203"
-old_ref = "curr_oth"
 
 [204]
-Description = "Total Current Expenditure"
+old_name = "204"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q204"
-old_ref = "curr_tot"
 
 [205]
-Description = "Basic Research"
+old_name = "205"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q205"
-old_ref = "res_bas"
 
 [206]
-Description = "Applied Research"
+old_name = "206"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q206"
-old_ref = "res_app"
 
 [207]
-Description = "Experimental Development"
+old_name = "207"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q207"
-old_ref = "experm"
 
 [209]
-Description = "Equipment & Machinery CapEx"
+old_name = "209"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q209"
-old_ref = "cxplm"
 
 [210]
-Description = "Total Capex."
+old_name = "210"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q210"
-old_ref = "None"
 
 [211]
-Description = "Total Inhouse Expenditure"
+old_name = "211"
 Deduced_Data_Type = "float64"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q211"
-old_ref = "intram"
 
 [212]
-Description = "Own Funds"
+old_name = "212"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q212"
-old_ref = "own_f"
 
 [214]
-Description = "Funding - UK government"
+old_name = "214"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q214"
-old_ref = "ex_uk_gv"
 
 [216]
-Description = "Funding - Other UK Private Bus/Public Orgs"
+old_name = "216"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q216"
-old_ref = "ex_uk"
 
 [218]
-Description = "Total Funding"
+old_name = "218"
 Deduced_Data_Type = "float64"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q218"
-old_ref = "f_tot"
 
 [219]
-Description = "Land Acquired for R&D (Split of Land & Build CapEx)"
+old_name = "219"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q219"
-old_ref = "None"
 
 [220]
-Description = "Buildings acquired/constructed for R&D (Split of Land & Build CapEx)"
+old_name = "220"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q220"
-old_ref = "None"
 
 [221]
-Description = "Expenditure on computer software only (of which from Equipment & Machinery CapEx)"
+old_name = "221"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q221"
-old_ref = "None"
 
 [222]
-Description = "Purchase of Materials (Split of Other current)"
+old_name = "222"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q222"
-old_ref = "None"
 
 [223]
-Description = "Purchase of Services (Split of Other current)"
+old_name = "223"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q223"
-old_ref = "None"
 
 [225]
-Description = "Ownership - Own Business"
+old_name = "225"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q225"
-old_ref = "None"
 
 [226]
-Description = "Ownership - UK Government"
+old_name = "226"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q226"
-old_ref = "None"
 
 [227]
-Description = "Ownership - Other UK Priv Bus"
+old_name = "227"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q227"
-old_ref = "None"
 
 [228]
-Description = "Ownership - Other UK Orgs"
+old_name = "228"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q228"
-old_ref = "None"
 
 [229]
-Description = "Ownership - Bus Enterprises in Group Outside UK"
+old_name = "229"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q229"
-old_ref = "None"
 
 [237]
-Description = "Ownership - not owned freely available"
+old_name = "237"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q237"
-old_ref = "None"
 
 [242]
-Description = "Funding - Any other UK organisations"
+old_name = "242"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q242"
-old_ref = "None"
 
 [243]
-Description = "Funding - Business Enterprises in group outside UK"
+old_name = "243"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q243"
-old_ref = "None"
 
 [244]
-Description = "Funding - Other Business Enterprises outside UK"
+old_name = "244"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q244"
-old_ref = "None"
 
 [245]
-Description = "Funding - Other Governments outside UK"
+old_name = "245"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q245"
-old_ref = "None"
 
 [246]
-Description = "Funding - Higher Education Est Outside UK"
+old_name = "246"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q246"
-old_ref = "None"
 
 [247]
-Description = "Funding - Non-profit Orgs outside UK"
+old_name = "247"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q247"
-old_ref = "None"
 
 [248]
-Description = "Funding - International Orgs"
+old_name = "248"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q248"
-old_ref = "None"
 
 [249]
-Description = "Funding - Any other orgs outside UK"
+old_name = "249"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q249"
-old_ref = "None"
 
 [250]
-Description = "Funding - UK Higher Education Establishments"
+old_name = "250"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q250"
-old_ref = "None"
 
 [251]
-Description = "Tax credit claim submitted or intended for In-house expenditure (Y/N) LONG FORM"
-Deduced_Data_Type = "str"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_categorical_Values = []
-q_code = "q251"
-old_ref = "None"
+old_name = "251"
+Deduced_Data_Type = "object"
 
 [300]
-Description = "nan"
+old_name = "300"
 Deduced_Data_Type = "object"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [301]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
+old_name = "301"
+Deduced_Data_Type = "float64"
 
 [302]
-Description = "Purchased/funded R&D in the UK (Yes or No)"
+old_name = "302"
 Deduced_Data_Type = "float64"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_categorical_Values = []
-q_code = "q302"
-old_ref = "None"
 
 [303]
-Description = "Purchased Outside UK (Govt Funded)"
+old_name = "303"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q303"
-old_ref = "None"
 
 [304]
-Description = "Purchased Outside UK (Other)"
+old_name = "304"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q304"
-old_ref = "None"
 
 [305]
-Description = "Total Purchased"
+old_name = "305"
 Deduced_Data_Type = "float64"
-Nullable = "Yes"
-Length = "# an integer of the length, or N/A"
-Min_values = 0
-Max_values = 1000000
-Possible_categorical_Values = []
-q_code = "q305"
-old_ref = "None"
 
 [307]
-Description = "Tax credit claim submitted or intended for purchased work commissioned in UK (Y/N) LONG FORM"
-Deduced_Data_Type = "str"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_categorical_Values = []
-q_code = "q307"
-old_ref = "None"
+old_name = "307"
+Deduced_Data_Type = "object"
 
 [308]
-Description = "Tax credit claim submitted/intended for purchased work outside Ukorig. Funded by UK gov (Y/N) LONG FORM"
-Deduced_Data_Type = "str"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_categorical_Values = []
-q_code = "q308"
-old_ref = "None"
+old_name = "308"
+Deduced_Data_Type = "object"
 
 [309]
-Description = "Tax credit claim submitted or intended for all other purchased work outside the UK (Y/N) LONG FORM"
-Deduced_Data_Type = "str"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_categorical_Values = []
-q_code = "q309"
-old_ref = "None"
+old_name = "309"
+Deduced_Data_Type = "object"
 
 [405]
-Description ="emp_researcher (Defence)"
-Deduced_Data_Type ="float64"
-Nullable ="Yes"
-Length ="# an integer of the length, or N/A"
-Min_values = 0
-Max_values =1000000
-Possible_categorical_Values =[ ]
-q_code =""
+old_name = "405"
+Deduced_Data_Type = "float64"
 
 [406]
-Description ="emp_researcher (Civil)"
-Deduced_Data_Type ="float64"
-Nullable ="Yes"
-Length ="# an integer of the length, or N/A"
-Min_values = 0
-Max_values =1000000
-Possible_categorical_Values =[ ]
-q_code =""
+old_name = "406"
+Deduced_Data_Type = "float64"
 
 [407]
-Description ="emp_technician (Civil)"
-Deduced_Data_Type ="float64"
-Nullable ="Yes"
-Length ="# an integer of the length, or N/A"
-Min_values = 0
-Max_values =1000000
-Possible_categorical_Values =[ ]
-q_code =""
+old_name = "407"
+Deduced_Data_Type = "float64"
 
 [408]
-Description ="emp_technician (Defence)"
-Deduced_Data_Type ="float64"
-Nullable ="Yes"
-Length ="# an integer of the length, or N/A"
-Min_values = 0
-Max_values =1000000
-Possible_categorical_Values =[ ]
-q_code =""
+old_name = "408"
+Deduced_Data_Type = "float64"
 
 [409]
-Description ="emp_other (Civil)"
-Deduced_Data_Type ="float64"
-Nullable ="Yes"
-Length ="# an integer of the length, or N/A"
-Min_values = 0
-Max_values =1000000
-Possible_categorical_Values =[ ]
-q_code =""
+old_name = "409"
+Deduced_Data_Type = "float64"
 
 [410]
-Description ="emp_other (Defence)"
-Deduced_Data_Type ="float64"
-Nullable ="Yes"
-Length ="# an integer of the length, or N/A"
-Min_values = 0
-Max_values =1000000
-Possible_categorical_Values =[ ]
-q_code =""
+old_name = "410"
+Deduced_Data_Type = "float64"
 
 [411]
-Description ="total fte(Civil)"
-Deduced_Data_Type ="float64"
-Nullable ="Yes"
-Length ="# an integer of the length, or N/A"
-Min_values = 0
-Max_values =1000000
-Possible_categorical_Values =[ ]
-q_code =""
+old_name = "411"
+Deduced_Data_Type = "float64"
 
 [412]
-Description ="total fte(Defence)"
-Deduced_Data_Type ="float64"
-Nullable ="Yes"
-Length ="# an integer of the length, or N/A"
-Min_values = 0
-Max_values =1000000
-Possible_categorical_Values =[ ]
-q_code =""
+old_name = "412"
+Deduced_Data_Type = "float64"
 
 [501]
-Description = "nan"
+old_name = "501"
 Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [502]
-Description = "nan"
+old_name = "502"
 Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [503]
-Description = "nan"
+old_name = "503"
 Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [504]
-Description = "nan"
+old_name = "504"
 Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [505]
-Description = "nan"
+old_name = "505"
 Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [506]
-Description = "nan"
+old_name = "506"
 Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [507]
-Description = "nan"
+old_name = "507"
 Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [508]
-Description = "nan"
+old_name = "508"
 Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [601]
-Description = "nan"
+old_name = "601"
 Deduced_Data_Type = "object"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
 
 [602]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[603]
-Description = "nan"
-Deduced_Data_Type = "str"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
+old_name = "602"
+Deduced_Data_Type = "float64"
 
 [604]
-Description = "nan"
-Deduced_Data_Type = "str"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[605]
-Description = "nan"
-Deduced_Data_Type = "str"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-
-[701]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[702]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "Int64"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[703]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[704]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[705]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[706]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[707]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
+old_name = "604"
+Deduced_Data_Type = "float64"
 
 [708]
-Description = "nan"
-Deduced_Data_Type = "str"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[709]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[710]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[711]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[712]
-Description = "nan"
+old_name = "708"
 Deduced_Data_Type = "object"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[713]
-Description = "Tax credit claim submitted or intended for In-house expenditure (Y/N) SHORT FORM"
-Deduced_Data_Type = "str"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_categorical_Values = []
-q_code = "q713"
-old_ref = "None"
-
-[714]
-Description = "Tax credit claim submitted or intended for purchased R&D (Y/N) SHORT FORM"
-Deduced_Data_Type = "str"
-Nullable = "No"
-Length = "# an integer of the length, or N/A"
-Min_values = "None"
-Max_values = "None"
-Possible_categorical_Values = []
-q_code = "q714"
-old_ref = "None"
-
-[9000]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9001]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9002]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9003]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9004]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9005]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9006]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9007]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9008]
-Description = "nan"
-Deduced_Data_Type = "float64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9009]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9010]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9011]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9012]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
-
-[9013]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = "nan"
-Current_Data_Type = "object"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [ "nan",]
-q_code = ""
-old_ref = "nan"
+
+[period]
+old_name = "period"
+Deduced_Data_Type = "int64"
+
+[survey]
+old_name = "survey"
+Deduced_Data_Type = "int64"
+
+[status]
+old_name = "status"
+Deduced_Data_Type = "object"
+
+[formid]
+old_name = "formid"
+Deduced_Data_Type = "int64"
+
+[formtype]
+old_name = "formtype"
+Deduced_Data_Type = "int64"
 
 [cellnumber]
-Description = "nan"
-Deduced_Data_Type = "Int64"
-Nullable = false
-Current_Data_Type = "Int64"
-Length = "nan"
-Min_values = "nan"
-Max_values = "nan"
-Possible_Categorical_Values = [0]
+old_name = "cellnumber"
+Deduced_Data_Type = "int64"
+
+[pg_numeric]
+old_name = "pg_numeric"
+Deduced_Data_Type = "float64"
+
+[emp_researcher]
+old_name = "emp_researcher"
+Deduced_Data_Type = "float64"
+
+[emp_technician]
+old_name = "emp_technician"
+Deduced_Data_Type = "float64"
+
+[emp_other]
+old_name = "emp_other"
+Deduced_Data_Type = "float64"
+
+[emp_total]
+old_name = "emp_total"
+Deduced_Data_Type = "float64"
+
+[headcount_res_m]
+old_name = "headcount_res_m"
+Deduced_Data_Type = "float64"
+
+[headcount_res_f]
+old_name = "headcount_res_f"
+Deduced_Data_Type = "float64"
+
+[headcount_tec_m]
+old_name = "headcount_tec_m"
+Deduced_Data_Type = "float64"
+
+[headcount_tec_f]
+old_name = "headcount_tec_f"
+Deduced_Data_Type = "float64"
+
+[headcount_oth_m]
+old_name = "headcount_oth_m"
+Deduced_Data_Type = "float64"
+
+[headcount_oth_f]
+old_name = "headcount_oth_f"
+Deduced_Data_Type = "float64"
+
+[headcount_tot_m]
+old_name = "headcount_tot_m"
+Deduced_Data_Type = "float64"
+
+[headcount_tot_f]
+old_name = "headcount_tot_f"
+Deduced_Data_Type = "float64"
+
+[headcount_total]
+old_name = "headcount_total"
+Deduced_Data_Type = "float64"
+
+[imp_class]
+old_name = "imp_class"
+Deduced_Data_Type = "object"
+
+[imp_marker]
+old_name = "imp_marker"
+Deduced_Data_Type = "object"
diff --git a/src/_version.py b/src/_version.py
index 382021f30..9e604c040 100644
--- a/src/_version.py
+++ b/src/_version.py
@@ -1 +1 @@
-__version__ = "1.0.6"
+__version__ = "1.0.7"
diff --git a/src/dev_config.yaml b/src/dev_config.yaml
index 15de1e669..8537d0810 100644
--- a/src/dev_config.yaml
+++ b/src/dev_config.yaml
@@ -42,6 +42,7 @@ imputation_paths:
   folder: "06_imputation"
   qa_path: "imputation_qa"
   manual_trimming_path: "manual_trimming"
+  backdata_out_path: "backdata_output"
 outliers_paths:
   folder: "07_outliers"
   qa_path: "outliers_qa"
@@ -61,11 +62,12 @@ export_paths:
 network_paths:
   root: "R:/BERD Results System Development 2023/DAP_emulation/"
   logs_foldername: "logs/run_logs" # dev config
-  snapshot_path: "R:/BERD Results System Development 2023/DAP_emulation/survey_return_data/snapshot-202212-002-83b5bacd-7c99-45cf-b989-d43d762dd054.json"
+  snapshot_path: "R:/BERD Results System Development 2023/DAP_emulation/spp_snapshots/2023_snapshots/snapshot-202312-002-b9b6048a-51c9-4669-919a-e92fc6e9c433.json" # dev config
   secondary_snapshot_path: "R:/BERD Results System Development 2023/DAP_emulation/berd_survey/anonymised/v1/snapshot-202012-002-fba5c4ba-fb8c-4a62-87bb-66c725eea5fd.json" # TODO Check if this works
   ni_full_responses_path: "03_northern_ireland/2021/TEST_ni.csv" # TESTER FILE
   # Imputation and outliers input paths
-  backdata_path: "R:/BERD Results System Development 2023/2021_data/validation-extract-responses-202112.csv"
+  # backdata_path: "R:/BERD Results System Development 2023/2021_data/2021_backdata_expanded.csv"
+  backdata_path: "R:/BERD Results System Development 2023/DAP_emulation/2022_surveys/BERD/06_imputation/backdata_output/2022_backdata_24-07-19_v604.csv"
   manual_imp_trim_path: "06_imputation/manual_trimming/trimming_qa_2023-11-27_v359.csv"
   manual_outliers_path: "07_outliers/manual_outliers/manual_outlier_2023-08-29_v67.csv"
   # Construction paths
@@ -77,6 +79,7 @@ network_paths:
   pcode_val_path: "01_staging/staging_qa/postcode_validation"
 # schema paths
 schema_paths:
+  manual_trimming_schema: "config/output_schemas/manual_trimming_qa_schema.toml"
   short_form_schema: "config/output_schemas/short_form_schema.toml"
   long_form_schema: "config/output_schemas/long_form_schema.toml"
   tau_schema: "config/output_schemas/tau_schema.toml"
@@ -109,7 +112,7 @@ run_log_sql:
   log_db: "test_runlog"
   log_mode: "append"
 estimation:
-  num_expected_cellnos: 588  # the number of cell_no items expected in the coverage mapper
+  num_expected_cellnos: 589  # the number of cell_no items expected in the coverage mapper
   numeric_cols: ["701", "702", "703", "704", "705", "706", "707", "709", "710", "711"]
 imputation:
   lf_target_vars:
diff --git a/src/estimation/estimation_main.py b/src/estimation/estimation_main.py
index 4a0f1dd31..96ff62e5a 100644
--- a/src/estimation/estimation_main.py
+++ b/src/estimation/estimation_main.py
@@ -31,8 +31,6 @@ def run_estimation(
     """
     EstMainLogger.info("Starting estimation weights calculation...")
 
-    est_qa_path = config["estimation_paths"]["qa_path"]
-
     # # clean and create a dictionary from the cellno mapper
     # cell_unit_dict = cmap.cellno_unit_dict(cellno_df)
 
@@ -50,6 +48,7 @@ def run_estimation(
         EstMainLogger.info("Outputting estimation QA file.")
         tdate = datetime.now().strftime("%y-%m-%d")
         survey_year = config["years"]["survey_year"]
+        est_qa_path = config["estimation_paths"]["qa_path"]
         cell_qa_filename = f"{survey_year}_estimation_weights_qa_{tdate}_v{run_id}.csv"
         full_qa_filename = f"{survey_year}_full_estimation_qa_{tdate}_v{run_id}.csv"
         write_csv(f"{est_qa_path}/{cell_qa_filename}", qa_df)
diff --git a/src/imputation/MoR.py b/src/imputation/MoR.py
index 20f680ab2..e8a1e12b8 100644
--- a/src/imputation/MoR.py
+++ b/src/imputation/MoR.py
@@ -1,18 +1,15 @@
 """Functions for the Mean of Ratios (MoR) methods."""
 import itertools
+import re
 import pandas as pd
 import numpy as np
-import re
 
-from src.staging import postcode_validation as pcval
-from src.imputation.apportionment import run_apportionment
 from src.imputation.tmi_imputation import (
     create_imp_class_col,
     trim_bounds,
     calculate_totals,
 )
 
-
 good_statuses = ["Clear", "Clear - overridden"]
 bad_statuses = ["Form sent out", "Check needed"]
 
@@ -62,27 +59,17 @@ def mor_preprocessing(df, backdata):
         df (pd.DataFrame): full responses for the current year
         backdata (pd.Dataframe): backdata file read in during staging.
     """
-    # Convert backdata column names from qXXX to XXX
-    # Note that this is only applicable when using the backdata on the network
-    p = re.compile(r"q\d{3}")
-    cols = [col for col in list(backdata.columns) if p.match(col)]
-    to_rename = {col: col[1:] for col in cols}
-    backdata = backdata.rename(columns=to_rename)
-
     # Add a QA column for the group size
     df["cf_group_size"] = np.nan
 
     # TODO move this to imputation main
     # Select only values to be imputed
     df = create_imp_class_col(df, "200", "201")
-    backdata = create_imp_class_col(backdata, "200", "201")
 
     imputation_cond = (df["formtype"] == "0001") & (df["status"].isin(bad_statuses))
     to_impute_df = df.copy().loc[imputation_cond, :]
     remainder_df = df.copy().loc[~imputation_cond, :]
 
-    backdata = run_apportionment(backdata)
-
     clear_status_cond = backdata["status"].isin(good_statuses)
 
     # Only pick up clear statuses from backdata
@@ -133,11 +120,6 @@ def carry_forwards(df, backdata, impute_vars):
     # Copy values from relevant columns where references match
     match_cond = df["_merge"] == "both"
 
-    # Apply the postcode formatting to clean the postcodes in col 601 of the back data
-    df.loc[match_cond, "601_prev"] = df.loc[match_cond, "601_prev"].apply(
-        pcval.format_postcodes
-    )
-
     # Replace the values of certain columns with the values from the back data
     replace_vars = ["instance", "200", "201", "601", "602", "604"]
     for var in replace_vars:
diff --git a/src/imputation/imputation_helpers.py b/src/imputation/imputation_helpers.py
index d2bc9362e..e032d7050 100644
--- a/src/imputation/imputation_helpers.py
+++ b/src/imputation/imputation_helpers.py
@@ -4,6 +4,8 @@
 from typing import List, Dict, Tuple, Callable
 from itertools import chain
 
+from src.staging.validation import load_schema
+
 ImputationHelpersLogger = logging.getLogger(__name__)
 
 
@@ -335,3 +337,26 @@ def tidy_imputation_dataframe(
     df = df.drop(columns=to_drop)
 
     return df
+
+
+def create_new_backdata(backdata: pd.DataFrame, config) -> pd.DataFrame:
+    """Create a new backdata dataframe with the required columns from schema.
+
+    Use the backdata toml schema to select the required columns from the backdata.
+    filter for the clear and imputed statuses.
+
+    Args:
+        backdata (pd.DataFrame): The backdata dataframe.
+
+    Returns:
+        pd.DataFrame: The filtered backdata with only the required columns.
+    """
+    # filter for the clear and imputed statuses
+    imp_markers_to_keep: list = ["R", "TMI", "CF", "MoR", "constructed"]
+    backdata = backdata.loc[backdata["imp_marker"].isin(imp_markers_to_keep)]
+
+    # get the wanted columns from the backdata schema
+    schema = load_schema("./config/backdata_schema.toml")
+    wanted_cols = list(schema.keys())
+
+    return backdata[wanted_cols]
diff --git a/src/imputation/imputation_main.py b/src/imputation/imputation_main.py
index 58b61f941..3a45a1fb4 100644
--- a/src/imputation/imputation_main.py
+++ b/src/imputation/imputation_main.py
@@ -1,5 +1,6 @@
 """The main file for the Imputation module."""
 import logging
+import os
 import pandas as pd
 from typing import Callable, Dict, Any
 from datetime import datetime
@@ -13,6 +14,7 @@
 # from src.imputation.MoR import run_mor
 from src.imputation.sf_expansion import run_sf_expansion
 from src.imputation import manual_imputation as mimp
+from src.imputation.MoR import run_mor
 from src.outputs.outputs_helpers import create_output_df
 
 
@@ -91,10 +93,10 @@ def run_imputation(
     trimmed_df, df = hlp.split_df_on_trim(df, "manual_trim")
 
     # Run MoR
-    # if backdata is not None:
-    # MoR will be re-written with new backdata
-    # lf_target_vars = config["imputation"]["lf_target_vars"]
-    # df, links_df = run_mor(df, backdata, to_impute_cols, lf_target_vars, config)
+    if backdata is not None:
+        # MoR will be re-written with new backdata
+        lf_target_vars = config["imputation"]["lf_target_vars"]
+        df, links_df = run_mor(df, backdata, to_impute_cols, lf_target_vars, config)
 
     # Run TMI for long forms and short forms
     imputed_df, qa_df = tmi.run_tmi(df, config)
@@ -124,14 +126,12 @@ def run_imputation(
     ).reset_index(drop=True)
 
     # Output QA files
+    tdate = datetime.now().strftime("%y-%m-%d")
+    survey_year = config["years"]["survey_year"]
 
     if config["global"]["output_imputation_qa"]:
-        ImputationMainLogger.info("Outputting Imputation files.")
-        tdate = datetime.now().strftime("%y-%m-%d")
-        survey_year = config["years"]["survey_year"]
+        ImputationMainLogger.info("Outputting Imputation QA files.")
         trim_qa_filename = f"{survey_year}_trimming_qa_{tdate}_v{run_id}.csv"
-        # if config["global"]["load_backdata"]:
-        #   links_filename = f"{survey_year}_links_qa_{tdate}_v{run_id}.csv"
         full_imp_filename = (
             f"{survey_year}_full_responses_imputed_{tdate}_v{run_id}.csv"
         )
@@ -142,11 +142,13 @@ def run_imputation(
         schema_dict = load_schema(schema_path)
         trimming_qa_output = create_output_df(qa_df, schema_dict)
 
-        write_csv(f"{qa_path}/{trim_qa_filename}", trimming_qa_output)
-        write_csv(f"{qa_path}/{full_imp_filename}", imputed_df)
-        write_csv(f"{qa_path}/{wrong_604_filename}", wrong_604_qa_df)
-        # if config["global"]["load_backdata"]:
-        #     write_csv(f"{qa_path}{links_filename}", links_df)
+        write_csv(os.path.join(qa_path, trim_qa_filename), trimming_qa_output)
+        write_csv(os.path.join(qa_path, full_imp_filename), imputed_df)
+        write_csv(os.path.join(qa_path, wrong_604_filename), wrong_604_qa_df)
+        if config["global"]["load_backdata"]:
+            links_filename = f"{survey_year}_links_qa_{tdate}_v{run_id}.csv"
+            write_csv(os.path.join(qa_path, links_filename), links_df)
+
     ImputationMainLogger.info("Finished Imputation calculation.")
 
     # remove rows and columns no longer needed from the imputed dataframe
@@ -159,4 +161,12 @@ def run_imputation(
         run_id,
     )
 
+    # optionally output backdata for imputation
+    if config["global"]["output_backdata"]:
+        ImputationMainLogger.info("Outputting backdata for imputation.")
+        backdata_path = config["imputation_paths"]["backdata_out_path"]
+        backdata_filename = f"{survey_year}_backdata_{tdate}_v{run_id}.csv"
+        new_backdata = hlp.create_new_backdata(imputed_df, config)
+        write_csv(os.path.join(backdata_path, backdata_filename), new_backdata)
+
     return imputed_df
diff --git a/src/mapping/conv_2021_backdata.py b/src/mapping/conv_2021_backdata.py
new file mode 100644
index 000000000..848bcab09
--- /dev/null
+++ b/src/mapping/conv_2021_backdata.py
@@ -0,0 +1,116 @@
+"""NOTE: This is a temporary script to convert the 2021 backdata to the format required
+for MoR imputation. When the mapping module is complete, we can produce a one-off update
+of the 2021 data and remove this script."""
+
+import os
+import re
+import logging
+import pandas as pd
+
+from src.utils.local_file_mods import rd_read_csv, rd_write_csv
+from src.staging import staging_helpers as stage_hlp
+from src.staging import postcode_validation as pcval
+from src.mapping.pg_conversion import pg_to_pg_mapper
+from src.imputation.tmi_imputation import create_imp_class_col
+from src.imputation.apportionment import run_apportionment
+
+MappingMainLogger = logging.getLogger(__name__)
+
+
+def do_pg_conv(backdata, config) -> pd.DataFrame:
+
+    # Load and validate the PG mappers
+    pg_num_alpha = stage_hlp.load_validate_mapper(
+        "pg_num_alpha_mapper_path",
+        config,
+        MappingMainLogger,
+    )
+
+    backdata = pg_to_pg_mapper(
+        backdata,
+        pg_num_alpha,
+    )
+    return backdata
+
+
+def prep_2021_backdata(backdata) -> pd.DataFrame:
+    """Prepare the backdata for MoR imputation.
+
+    Args:
+        backdata (pd.DataFrame): Backdata for the current year.
+
+    Returns:
+        pd.DataFrame: Prepped backdata.
+    """
+    # Convert backdata column names from qXXX to XXX
+    # Note that this is only applicable when using the backdata on the network
+    p = re.compile(r"q\d{3}")
+    cols = [col for col in list(backdata.columns) if p.match(col)]
+    to_rename = {col: col[1:] for col in cols}
+    backdata = backdata.rename(columns=to_rename)
+
+    # Apply the postcode formatting to clean the postcodes in col 601 of the back data
+    backdata["601"] = backdata["601"].apply(pcval.format_postcodes)
+
+    return backdata
+
+
+def get_backdate_wanted_cols(backdata: pd.DataFrame, config: dict) -> pd.DataFrame:
+    """Get the columns required for the backdata.
+
+    Args:
+        backdata (pd.DataFrame): The backdata.
+        config (dict): The configuration settings.
+
+    Returns:
+        pd.DataFrame: The backdata with only the required columns.
+    """
+    # Load the columns to keep
+    backdata_cols = stage_hlp.load_required_columns(
+        "backdata_required_cols_path",
+        config,
+        MappingMainLogger,
+    )
+
+    # Get the columns that are in the backdata
+    cols = list(backdata.columns)
+    wanted_cols = [col for col in backdata_cols if col in cols]
+
+    return backdata[wanted_cols]
+
+
+def create_imp_marker_col(df: pd.DataFrame) -> pd.DataFrame:
+    """Create the imp_marker column for the backdata.
+
+    Args:
+        df (pd.DataFrame): The backdata.
+
+    Returns:
+        pd.DataFrame: The backdata with the imp_marker column.
+    """
+    clear_responders_mask = df.status.isin(["Clear", "Clear - overridden"])
+    df.loc[clear_responders_mask, "imp_marker"] = "R"
+    df.loc[~clear_responders_mask, "imp_marker"] = "no_imputation"
+
+    return df
+
+
+def create_backdata(backdata: pd.DataFrame, config: dict) -> pd.DataFrame:
+    staging_dict = config["staging_paths"]
+    backdata_path = staging_dict["backdata_path"]
+
+    backdata = rd_read_csv(backdata_path)
+
+    backdata = prep_2021_backdata(backdata)
+
+    backdata = do_pg_conv(backdata, config)
+
+    backdata = run_apportionment(backdata)
+
+    backdata = create_imp_class_col(backdata, "200", "201")
+
+    backdata = create_imp_marker_col(backdata)
+
+    backdata_out_path = config["imputation_paths"]["backdata_out_path"]
+
+    rd_write_csv(os.path.join(backdata_out_path, "2021_backdata.csv"), backdata)
diff --git a/src/mapping/mapping_main.py b/src/mapping/mapping_main.py
index 7bc87290b..580e34bb8 100644
--- a/src/mapping/mapping_main.py
+++ b/src/mapping/mapping_main.py
@@ -111,4 +111,4 @@ def run_mapping(
     MappingMainLogger.info("Finished Mapping NI QA calculation.")
 
     # return mapped_df
-    return (full_responses, ni_full_responses, itl_mapper, cellno_df)
+    return (full_responses, ni_full_responses, itl_mapper)
diff --git a/src/outputs/outputs_main.py b/src/outputs/outputs_main.py
index 3123ee46a..265fee09d 100644
--- a/src/outputs/outputs_main.py
+++ b/src/outputs/outputs_main.py
@@ -59,7 +59,6 @@ def run_outputs(  # noqa: C901
         sic_division_detailed (pd.DataFrame): Detailed descriptons of SIC divisions
     """
 
-    # Remove instance 0 from weighted df, so that it does not go to Tau outputs
     weighted_df = weighted_df.copy().loc[weighted_df.instance != 0]
 
     (ni_full_responses, outputs_df, tau_outputs_df) = form_output_prep(
diff --git a/src/pipeline.py b/src/pipeline.py
index 6dc28dd25..4ba23829c 100644
--- a/src/pipeline.py
+++ b/src/pipeline.py
@@ -17,6 +17,7 @@
 from src.site_apportionment.site_apportionment_main import run_site_apportionment
 from src.outputs.outputs_main import run_outputs
 
+
 MainLogger = logging.getLogger(__name__)
 
 
@@ -113,7 +114,7 @@ def run_pipeline(user_config_path, dev_config_path):
 
     # Mapping module
     MainLogger.info("Starting Mapping...")
-    (mapped_df, ni_full_responses, itl_mapper, cellno_df,) = run_mapping(
+    (mapped_df, ni_full_responses, itl_mapper) = run_mapping(
         full_responses,
         ni_df,
         config,
@@ -155,7 +156,6 @@ def run_pipeline(user_config_path, dev_config_path):
         mods.rd_write_csv,
         run_id,
         "estimated",
-        output_file=True,
     )
     weighted_responses_df = run_site_apportionment(
         weighted_responses_df,
@@ -163,19 +163,9 @@ def run_pipeline(user_config_path, dev_config_path):
         mods.rd_write_csv,
         run_id,
         "weighted",
-        output_file=True,
     )
     MainLogger.info("Finished Site Apportionment module.")
 
-    # Data processing: Regional Apportionment
-
-    # Data processing: Aggregation
-
-    # Data display: Visualisations
-
-    # Data output: Disclosure Control
-
-    # Data output: File Outputs
     MainLogger.info("Starting Outputs...")
 
     run_outputs(
diff --git a/src/site_apportionment/site_apportionment_main.py b/src/site_apportionment/site_apportionment_main.py
index c596ac38d..a24bc033d 100644
--- a/src/site_apportionment/site_apportionment_main.py
+++ b/src/site_apportionment/site_apportionment_main.py
@@ -15,8 +15,7 @@ def run_site_apportionment(
     config: Dict[str, Any],
     write_csv: Callable,
     run_id: int,
-    file_suffix,
-    output_file=False,
+    output_type: str,
 ) -> pd.DataFrame:
     """Run the apportionment to sites module.
 
@@ -25,14 +24,17 @@ def run_site_apportionment(
     instance 0 to all other instances.
     Same percentages are used for each product group.
 
-    When running on the local network,
-
     Args:
         config (dict): The pipeline configuration
         df (pd.DataFrame): Main dataset before the outputs
+        write_csv (Callable): Function to write to a csv file.
+            This will be the hdfs or network version depending on settings.
+        run_id (int): The current run id
+        output_type (str): The type of output being processed, either "estimated_df"
+            or "weighted_df". Needed for the QA file naming.
     Returns:
         df_out (pd.DataFrame): Percentages filled in for short forms and applied
-        to apportion  for long forms
+            to apportion  for long forms
     """
     # Create variable for output of QA apportionment file
     qa_path = config["apportionment_paths"]["qa_path"]
@@ -43,26 +45,16 @@ def run_site_apportionment(
     if config["global"]["output_status_filtered"]:
         osf.output_status_filtered(df, imp_markers_to_keep, config, write_csv, run_id)
 
-    # Check if this module needs to be applied
-    if config["global"]["apportion_sites"]:
-        SitesMainLogger.info("Starting apportionment to sites...")
-        df_out = sap.run_apportion_sites(df, imp_markers_to_keep, config)
-
-        # Output QA files
-        if config["global"]["output_apportionment_qa"] & output_file:
-            SitesMainLogger.info("Outputting Apportionment files.")
-            tdate = datetime.now().strftime("%y-%m-%d")
-            survey_year = config["years"]["survey_year"]
-            filename = (
-                f"{survey_year}_{file_suffix}_df_apportioned_{tdate}_v{run_id}.csv"
-            )
-            write_csv(f"{qa_path}/{filename}", df_out)
+    SitesMainLogger.info("Starting apportionment to sites...")
+    df_out = sap.run_apportion_sites(df, imp_markers_to_keep, config)
 
-        SitesMainLogger.info("Finished apportionment to sites.")
-        return df_out
+    # Output QA files
+    if config["global"]["output_apportionment_qa"]:
+        SitesMainLogger.info("Outputting Apportionment files.")
+        tdate = datetime.now().strftime("%y-%m-%d")
+        survey_year = config["years"]["survey_year"]
+        filename = f"{survey_year}_{output_type}_apportioned_{tdate}_v{run_id}.csv"
+        write_csv(f"{qa_path}/{filename}", df_out)
 
-    else:
-        SitesMainLogger.info("Apportionment to sites disabled, skipped")
-        # Remove records that are neither clear nor imputed, based on imputation marker.
-        filtered_df = sap.keep_good_markers(df)
-        return filtered_df
+    SitesMainLogger.info("Finished apportionment to sites.")
+    return df_out
diff --git a/src/user_config.yaml b/src/user_config.yaml
index 434cd70a3..8e70c3350 100644
--- a/src/user_config.yaml
+++ b/src/user_config.yaml
@@ -2,12 +2,12 @@ config_validation:
   validate: True
   path: src/user_config_schema.yaml
 years:
-  survey_year: 2022
+  survey_year: 2023
 global:
   # Staging and validation settings
   postcode_csv_check: True
   load_updated_snapshot: False # Whether to load the updated snapshots for amendments and additions
-  load_ni_data: True
+  load_ni_data: False
   # Construction Settings
   run_construction: False
   run_all_data_construction: False
@@ -15,11 +15,13 @@ global:
   run_ni_construction: False
   load_manual_outliers: False
   load_manual_imputation: False
-  load_backdata: False  # whether to load previous year data for MoR
+  load_backdata: True  # whether to load previous year data for MoR
+  # Backdata output settings
+  output_backdata: True
   # QA output settings
   output_full_responses: False
   output_ni_full_responses: False
-  output_imputation_qa: False
+  output_imputation_qa: True
   output_mapping_qa: False
   output_mapping_ni_qa: False
   output_auto_outliers: False
@@ -48,7 +50,6 @@ hdfs_paths:
   secondary_snapshot_path: "/ons/rdbe_dev/berd_survey/anonymised/v1/NEW_SNAPSHOT_TODO.json"
   ni_full_responses_path: "03_northern_ireland/2021/TEST_ni.csv"
   feather_path: "staging/feather"
-  history_path: "BERD_V7_Anonymised"
   # Imputation and outliers input paths
   backdata_path: ""
   manual_imp_trim_path: "06_imputation/manual_trimming/trimming_qa_2023-11-27_v359.csv"
@@ -80,7 +81,7 @@ hdfs_paths:
   postcodes_mapper: "postcodes_2023.csv"
   itl_mapper_path: "itl_2023.csv"
   ultfoc_mapper_path: "BERD_2023_ultfoc_anon.csv"
-  cellno_2023_path: 'berd_2023_cellno_coverage.csv'
+  cellno_path: 'berd_2023_cellno_coverage_TEMP.csv'
   pg_num_alpha_mapper_path: 'pg_num_alpha_2023.csv'
   sic_pg_alpha_mapper_path: 'sic_pg_alpha_2023.csv'
   sic_pg_num_mapper_path: 'sic_pg_num_2023.csv'
diff --git a/src/utils/path_helpers.py b/src/utils/path_helpers.py
index 4eed36ee5..b001bccfb 100644
--- a/src/utils/path_helpers.py
+++ b/src/utils/path_helpers.py
@@ -59,6 +59,7 @@ def create_staging_config(config: dict) -> dict:
     staging_dict["snapshot_path"] = paths["snapshot_path"]
     staging_dict["secondary_snapshot_path"] = paths["secondary_snapshot_path"]
     staging_dict["postcode_masterlist"] = paths["postcode_masterlist"]
+    staging_dict["backdata_path"] = paths["backdata_path"]
     staging_dict["manual_outliers_path"] = f"{berd_path}{paths['manual_outliers_path']}"
     staging_dict["manual_imp_trim_path"] = f"{berd_path}{paths['manual_imp_trim_path']}"
 
diff --git a/tests/test_estimation/test_apply_weights.py b/tests/test_estimation/test_apply_weights.py
index bbd23c8c8..85faec1b7 100644
--- a/tests/test_estimation/test_apply_weights.py
+++ b/tests/test_estimation/test_apply_weights.py
@@ -64,288 +64,17 @@ def create_input_df(self):
             "headcount_oth_f",
             "a_weight",
         ]
-
         data = [
-            [
-                "1",
-                np.nan,
-                1.5968726069999999,
-                0.254832457,
-                1501.531337,
-                500.8443931,
-                499.9360421,
-                500.75090159999996,
-                29.94531777,
-                9.602584921,
-                9.653985014,
-                10.68874783,
-                6.486029315,
-                2.533542905,
-                2.308242877,
-                1.644243533,
-                35.5,
-                17.6,
-                17.9,
-                5.2,
-                5.0,
-                5.9,
-                6.1,
-                6.4,
-                6.8,
-                2.5,
-            ],
-            [
-                "2",
-                0.0,
-                0.484444627,
-                0.660795649,
-                1501.150221,
-                499.7596024,
-                501.6974991,
-                499.6931194,
-                31.82855842,
-                10.97246129,
-                10.18047899,
-                10.67561814,
-                9.256449084,
-                3.6957475310000003,
-                3.053765916,
-                2.5069356369999998,
-                31.3,
-                15.6,
-                15.7,
-                5.1,
-                5.0,
-                5.2,
-                5.3,
-                5.3,
-                5.4,
-                6.0,
-            ],
-            [
-                "3",
-                0.245754563,
-                0.053153144000000006,
-                0.24898895399999998,
-                1499.305683,
-                499.0019342,
-                499.56546389999994,
-                500.7382846,
-                31.09016923,
-                10.200109300000001,
-                11.24314965,
-                9.646910282999999,
-                11.18471882,
-                5.38607754,
-                2.750773441,
-                3.047867843,
-                31.9,
-                16.2,
-                15.7,
-                5.9,
-                5.8,
-                5.4,
-                5.2,
-                5.0,
-                4.7,
-                7.0,
-            ],
-            [
-                "4",
-                0.091581569,
-                1.29306045,
-                2.222550393,
-                1497.3095039999998,
-                500.2853801,
-                498.26926339999994,
-                498.7548608,
-                31.49017978,
-                10.80040763,
-                9.527649379,
-                11.16212277,
-                10.22765186,
-                3.03791456,
-                3.8605661610000004,
-                3.3291711439999996,
-                19.5,
-                8.5,
-                11.0,
-                2.8,
-                4.8,
-                2.6,
-                3.2,
-                3.1,
-                3.0,
-                14.0,
-            ],
-            [
-                "5",
-                0.48547690299999996,
-                0.614760438,
-                1.620874173,
-                1498.722371,
-                500.4694436000001,
-                500.44068089999996,
-                497.81224689999993,
-                30.44836156,
-                10.06357482,
-                10.79756546,
-                9.587221282,
-                8.654173735,
-                5.294000296,
-                2.062538336,
-                1.297635102,
-                38.7,
-                16.0,
-                22.7,
-                2.3,
-                5.6,
-                5.1,
-                7.2,
-                8.6,
-                10.0,
-                2.0,
-            ],
-            [
-                "6",
-                0.216682565,
-                0.420119477,
-                0.077609457,
-                1497.974779,
-                499.146944,
-                498.292069,
-                500.5357663,
-                29.76051868,
-                9.465821929,
-                9.133324308999999,
-                11.16137244,
-                11.35927018,
-                5.351916919,
-                2.9535873489999998,
-                3.053765916,
-                29.9,
-                14.9,
-                15.0,
-                4.8,
-                4.7,
-                5.0,
-                5.0,
-                5.2,
-                5.3,
-                1.0,
-            ],
-            [
-                "7",
-                0.256570729,
-                1.635266926,
-                0.877078037,
-                1497.8444539999998,
-                499.91778619999997,
-                499.7594455,
-                498.16722269999997,
-                28.24588485,
-                9.099873094,
-                9.312124146,
-                9.833887614,
-                11.20396942,
-                4.079138201,
-                5.134802344,
-                1.990028871,
-                27.8,
-                15.0,
-                12.8,
-                5.4,
-                4.0,
-                5.1,
-                4.6,
-                4.4,
-                4.3,
-                6.3,
-            ],
-            [
-                "8",
-                0.733170964,
-                0.111266445,
-                0.506586275,
-                1500.596397,
-                501.64230189999995,
-                501.381718,
-                497.5723767,
-                28.169746500000002,
-                9.444435161,
-                9.593212578,
-                9.132098765,
-                10.80790153,
-                3.316276783,
-                4.322564458,
-                3.169060286,
-                34.8,
-                15.9,
-                18.9,
-                5.2,
-                7.6,
-                5.0,
-                5.8,
-                5.7,
-                5.6,
-                8.1,
-            ],
-            [
-                "9",
-                2.134056558,
-                0.31692025,
-                1.3120006770000001,
-                1498.986525,
-                501.01687419999996,
-                499.2999597,
-                498.66969119999993,
-                31.76279059,
-                10.04786784,
-                10.48995616,
-                11.22496658,
-                8.855932629,
-                4.065679953,
-                2.443454044,
-                2.346798631,
-                33.1,
-                16.4,
-                16.8,
-                5.3,
-                5.5,
-                5.4,
-                5.6,
-                5.6,
-                5.7,
-                1.0,
-            ],
-            [
-                "10",
-                0.678504648,
-                0.35838638700000003,
-                0.569093572,
-                1498.674708,
-                500.2971126,
-                500.64281950000003,
-                497.7347761,
-                30.178638399999997,
-                9.173285232000001,
-                11.11531108,
-                9.890042091,
-                10.35101118,
-                3.143504622,
-                3.1301464180000003,
-                4.077360139,
-                31.8,
-                15.6,
-                16.2,
-                4.3,
-                4.1,
-                5.3,
-                5.5,
-                6.0,
-                6.5,
-                9.0,
-            ],
+            ["1", np.nan, 1.5968726069999999, 0.254832457, 1501.531337, 500.8443931, 499.9360421, 500.75090159999996, 29.94531777, 9.602584921, 9.653985014, 10.68874783, 6.486029315, 2.533542905, 2.308242877, 1.644243533, 35.5, 17.6, 17.9, 5.2, 5.0, 5.9, 6.1, 6.4, 6.8, 2.5],
+            ["2", 0.0, 0.484444627, 0.660795649, 1501.150221, 499.7596024, 501.6974991, 499.6931194, 31.82855842, 10.97246129, 10.18047899, 10.67561814, 9.256449084, 3.6957475310000003, 3.053765916, 2.5069356369999998, 31.3, 15.6, 15.7, 5.1, 5.0, 5.2, 5.3, 5.3, 5.4, 6.0],
+            ["3", 0.245754563, 0.053153144000000006, 0.24898895399999998, 1499.305683, 499.0019342, 499.56546389999994, 500.7382846, 31.09016923, 10.200109300000001, 11.24314965, 9.646910282999999, 11.18471882, 5.38607754, 2.750773441, 3.047867843, 31.9, 16.2, 15.7, 5.9, 5.8, 5.4, 5.2, 5.0, 4.7, 7.0],
+            ["4", 0.091581569, 1.29306045, 2.222550393, 1497.3095039999998, 500.2853801, 498.26926339999994, 498.7548608, 31.49017978, 10.80040763, 9.527649379, 11.16212277, 10.22765186, 3.03791456, 3.8605661610000004, 3.3291711439999996, 19.5, 8.5, 11.0, 2.8, 4.8, 2.6, 3.2, 3.1, 3.0, 14.0],
+            ["5", 0.48547690299999996, 0.614760438, 1.620874173, 1498.722371, 500.4694436000001, 500.44068089999996, 497.81224689999993, 30.44836156, 10.06357482, 10.79756546, 9.587221282, 8.654173735, 5.294000296, 2.062538336, 1.297635102, 38.7, 16.0, 22.7, 2.3, 5.6, 5.1, 7.2, 8.6, 10.0, 2.0],
+            ["6", 0.216682565, 0.420119477, 0.077609457, 1497.974779, 499.146944, 498.292069, 500.5357663, 29.76051868, 9.465821929, 9.133324308999999, 11.16137244, 11.35927018, 5.351916919, 2.9535873489999998, 3.053765916, 29.9, 14.9, 15.0, 4.8, 4.7, 5.0, 5.0, 5.2, 5.3, 1.0],
+            ["7", 0.256570729, 1.635266926, 0.877078037, 1497.8444539999998, 499.91778619999997, 499.7594455, 498.16722269999997, 28.24588485, 9.099873094, 9.312124146, 9.833887614, 11.20396942, 4.079138201, 5.134802344, 1.990028871, 27.8, 15.0, 12.8, 5.4, 4.0, 5.1, 4.6, 4.4, 4.3, 6.3],
+            ["8", 0.733170964, 0.111266445, 0.506586275, 1500.596397, 501.64230189999995, 501.381718, 497.5723767, 28.169746500000002, 9.444435161, 9.593212578, 9.132098765, 10.80790153, 3.316276783, 4.322564458, 3.169060286, 34.8, 15.9, 18.9, 5.2, 7.6, 5.0, 5.8, 5.7, 5.6, 8.1],
+            ["9", 2.134056558, 0.31692025, 1.3120006770000001, 1498.986525, 501.01687419999996, 499.2999597, 498.66969119999993, 31.76279059, 10.04786784, 10.48995616, 11.22496658, 8.855932629, 4.065679953, 2.443454044, 2.346798631, 33.1, 16.4, 16.8, 5.3, 5.5, 5.4, 5.6, 5.6, 5.7, 1.0],
+            ["10", 0.678504648, 0.35838638700000003, 0.569093572, 1498.674708, 500.2971126, 500.64281950000003, 497.7347761, 30.178638399999997, 9.173285232000001, 11.11531108, 9.890042091, 10.35101118, 3.143504622, 3.1301464180000003, 4.077360139, 31.8, 15.6, 16.2, 4.3, 4.1, 5.3, 5.5, 6.0, 6.5, 9.0],
         ]
 
         input_df = pd.DataFrame(data=data, columns=input_columns)
@@ -408,526 +137,16 @@ def create_expected_output(self):
         ]
 
         data = [
-            [
-                "1",
-                np.nan,
-                1.5968726069999999,
-                0.254832457,
-                1501.531337,
-                500.8443931,
-                499.9360421,
-                500.75090159999996,
-                29.94531777,
-                9.602584921,
-                9.653985014,
-                10.68874783,
-                6.486029315,
-                2.533542905,
-                2.308242877,
-                1.644243533,
-                35.5,
-                17.6,
-                17.9,
-                5.2,
-                5.0,
-                5.9,
-                6.1,
-                6.4,
-                6.8,
-                2.5,
-                np.nan,
-                3.9922,
-                0.6371,
-                3753.8283,
-                1252.111,
-                1249.8401,
-                1251.8773,
-                74.8633,
-                24.0065,
-                24.135,
-                26.7219,
-                16.2151,
-                6.3339,
-                5.7706,
-                4.1106,
-                88.78,
-                44.04,
-                44.74,
-                13.11,
-                12.56,
-                14.84,
-                15.23,
-                16.09,
-                16.96,
-            ],
-            [
-                "2",
-                0.0,
-                0.484444627,
-                0.660795649,
-                1501.150221,
-                499.7596024,
-                501.6974991,
-                499.6931194,
-                31.82855842,
-                10.97246129,
-                10.18047899,
-                10.67561814,
-                9.256449084,
-                3.6957475310000003,
-                3.053765916,
-                2.5069356369999998,
-                31.3,
-                15.6,
-                15.7,
-                5.1,
-                5.0,
-                5.2,
-                5.3,
-                5.3,
-                5.4,
-                6.0,
-                0.0,
-                2.9067,
-                3.9648,
-                9006.9013,
-                2998.5576,
-                3010.185,
-                2998.1587,
-                190.9714,
-                65.8348,
-                61.0829,
-                64.0537,
-                55.5387,
-                22.1745,
-                18.3226,
-                15.0416,
-                188.0,
-                93.77,
-                94.23,
-                30.44,
-                30.23,
-                31.33,
-                31.55,
-                32.0,
-                32.44,
-            ],
-            [
-                "3",
-                0.245754563,
-                0.053153144000000006,
-                0.24898895399999998,
-                1499.305683,
-                499.0019342,
-                499.56546389999994,
-                500.7382846,
-                31.09016923,
-                10.200109300000001,
-                11.24314965,
-                9.646910282999999,
-                11.18471882,
-                5.38607754,
-                2.750773441,
-                3.047867843,
-                31.9,
-                16.2,
-                15.7,
-                5.9,
-                5.8,
-                5.4,
-                5.2,
-                5.0,
-                4.7,
-                7.0,
-                1.7203,
-                0.3721,
-                1.7429,
-                10495.1398,
-                3493.0135,
-                3496.9582,
-                3505.1679999999997,
-                217.6312,
-                71.4008,
-                78.702,
-                67.5284,
-                78.293,
-                37.7025,
-                19.2554,
-                21.3351,
-                223.37,
-                113.33,
-                110.03,
-                40.98,
-                40.59,
-                37.63,
-                36.39,
-                34.72,
-                33.05,
-            ],
-            [
-                "4",
-                0.091581569,
-                1.29306045,
-                2.222550393,
-                1497.3095039999998,
-                500.2853801,
-                498.26926339999994,
-                498.7548608,
-                31.49017978,
-                10.80040763,
-                9.527649379,
-                11.16212277,
-                10.22765186,
-                3.03791456,
-                3.8605661610000004,
-                3.3291711439999996,
-                19.5,
-                8.5,
-                11.0,
-                2.8,
-                4.8,
-                2.6,
-                3.2,
-                3.1,
-                3.0,
-                14.0,
-                1.2821,
-                18.1028,
-                31.1157,
-                20962.3331,
-                7003.9953,
-                6975.7697,
-                6982.5681,
-                440.8625,
-                151.2057,
-                133.3871,
-                156.2697,
-                143.1871,
-                42.5308,
-                54.0479,
-                46.6084,
-                272.46,
-                118.55,
-                153.91,
-                39.34,
-                67.83,
-                36.17,
-                44.62,
-                43.04,
-                41.46,
-            ],
-            [
-                "5",
-                0.48547690299999996,
-                0.614760438,
-                1.620874173,
-                1498.722371,
-                500.4694436000001,
-                500.44068089999996,
-                497.81224689999993,
-                30.44836156,
-                10.06357482,
-                10.79756546,
-                9.587221282,
-                8.654173735,
-                5.294000296,
-                2.062538336,
-                1.297635102,
-                38.7,
-                16.0,
-                22.7,
-                2.3,
-                5.6,
-                5.1,
-                7.2,
-                8.6,
-                10.0,
-                2.0,
-                0.971,
-                1.2295,
-                3.2417,
-                2997.4447,
-                1000.9389,
-                1000.8814,
-                995.6245,
-                60.8967,
-                20.1271,
-                21.5951,
-                19.1744,
-                17.3083,
-                10.588,
-                4.1251,
-                2.5953,
-                77.47,
-                32.06,
-                45.41,
-                4.64,
-                11.13,
-                10.28,
-                14.32,
-                17.14,
-                19.96,
-            ],
-            [
-                "6",
-                0.216682565,
-                0.420119477,
-                0.077609457,
-                1497.974779,
-                499.146944,
-                498.292069,
-                500.5357663,
-                29.76051868,
-                9.465821929,
-                9.133324308999999,
-                11.16137244,
-                11.35927018,
-                5.351916919,
-                2.9535873489999998,
-                3.053765916,
-                29.9,
-                14.9,
-                15.0,
-                4.8,
-                4.7,
-                5.0,
-                5.0,
-                5.2,
-                5.3,
-                1.0,
-                0.2167,
-                0.4201,
-                0.0776,
-                1497.9748,
-                499.1469,
-                498.2921,
-                500.5358,
-                29.7605,
-                9.4658,
-                9.1333,
-                11.1614,
-                11.3593,
-                5.3519,
-                2.9536,
-                3.0538,
-                29.89,
-                14.89,
-                15.01,
-                4.75,
-                4.7,
-                4.98,
-                5.04,
-                5.15,
-                5.27,
-            ],
-            [
-                "7",
-                0.256570729,
-                1.635266926,
-                0.877078037,
-                1497.8444539999998,
-                499.91778619999997,
-                499.7594455,
-                498.16722269999997,
-                28.24588485,
-                9.099873094,
-                9.312124146,
-                9.833887614,
-                11.20396942,
-                4.079138201,
-                5.134802344,
-                1.990028871,
-                27.8,
-                15.0,
-                12.8,
-                5.4,
-                4.0,
-                5.1,
-                4.6,
-                4.4,
-                4.3,
-                6.3,
-                1.6164,
-                10.3022,
-                5.5256,
-                9436.4201,
-                3149.4821,
-                3148.4845,
-                3138.4535,
-                177.9491,
-                57.3292,
-                58.6664,
-                61.9535,
-                70.585,
-                25.6986,
-                32.3493,
-                12.5372,
-                175.25,
-                94.52,
-                80.73,
-                34.26,
-                25.06,
-                32.43,
-                28.75,
-                27.84,
-                26.92,
-            ],
-            [
-                "8",
-                0.733170964,
-                0.111266445,
-                0.506586275,
-                1500.596397,
-                501.64230189999995,
-                501.381718,
-                497.5723767,
-                28.169746500000002,
-                9.444435161,
-                9.593212578,
-                9.132098765,
-                10.80790153,
-                3.316276783,
-                4.322564458,
-                3.169060286,
-                34.8,
-                15.9,
-                18.9,
-                5.2,
-                7.6,
-                5.0,
-                5.8,
-                5.7,
-                5.6,
-                8.1,
-                5.9387,
-                0.9013,
-                4.1033,
-                12154.8308,
-                4063.3026,
-                4061.1919,
-                4030.3363,
-                228.1749,
-                76.4999,
-                77.705,
-                73.97,
-                87.544,
-                26.8618,
-                35.0128,
-                25.6694,
-                282.04,
-                128.61,
-                153.43,
-                41.83,
-                61.18,
-                40.65,
-                46.71,
-                46.12,
-                45.54,
-            ],
-            [
-                "9",
-                2.134056558,
-                0.31692025,
-                1.3120006770000001,
-                1498.986525,
-                501.01687419999996,
-                499.2999597,
-                498.66969119999993,
-                31.76279059,
-                10.04786784,
-                10.48995616,
-                11.22496658,
-                8.855932629,
-                4.065679953,
-                2.443454044,
-                2.346798631,
-                33.1,
-                16.4,
-                16.8,
-                5.3,
-                5.5,
-                5.4,
-                5.6,
-                5.6,
-                5.7,
-                1.0,
-                2.1341,
-                0.3169,
-                1.3119999999999998,
-                1498.9865,
-                501.0169,
-                499.3,
-                498.6697,
-                31.7628,
-                10.0479,
-                10.49,
-                11.225,
-                8.8559,
-                4.0657,
-                2.4435,
-                2.3468,
-                33.13,
-                16.35,
-                16.78,
-                5.29,
-                5.53,
-                5.43,
-                5.56,
-                5.63,
-                5.7,
-            ],
-            [
-                "10",
-                0.678504648,
-                0.35838638700000003,
-                0.569093572,
-                1498.674708,
-                500.2971126,
-                500.64281950000003,
-                497.7347761,
-                30.178638399999997,
-                9.173285232000001,
-                11.11531108,
-                9.890042091,
-                10.35101118,
-                3.143504622,
-                3.1301464180000003,
-                4.077360139,
-                31.8,
-                15.6,
-                16.2,
-                4.3,
-                4.1,
-                5.3,
-                5.5,
-                6.0,
-                6.5,
-                9.0,
-                6.1065,
-                3.2255,
-                5.1218,
-                13488.0724,
-                4502.674,
-                4505.7854,
-                4479.613,
-                271.6077,
-                82.5596,
-                100.0378,
-                89.0104,
-                93.1591,
-                28.2915,
-                28.1713,
-                36.6962,
-                286.0,
-                140.3,
-                145.7,
-                38.61,
-                37.17,
-                47.42,
-                49.87,
-                54.27,
-                58.67,
-            ],
+            ["1", np.nan, 1.5968726069999999, 0.254832457, 1501.531337, 500.8443931, 499.9360421, 500.75090159999996, 29.94531777, 9.602584921, 9.653985014, 10.68874783, 6.486029315, 2.533542905, 2.308242877, 1.644243533, 35.5, 17.6, 17.9, 5.2, 5.0, 5.9, 6.1, 6.4, 6.8, 2.5, np.nan, 3.9922, 0.6371, 3753.8283, 1252.111, 1249.8401, 1251.8773, 74.8633, 24.0065, 24.135, 26.7219, 16.2151, 6.3339, 5.7706, 4.1106, 88.78, 44.04, 44.74, 13.11, 12.56, 14.84, 15.23, 16.09, 16.96],
+            ["2", 0.0, 0.484444627, 0.660795649, 1501.150221, 499.7596024, 501.6974991, 499.6931194, 31.82855842, 10.97246129, 10.18047899, 10.67561814, 9.256449084, 3.6957475310000003, 3.053765916, 2.5069356369999998, 31.3, 15.6, 15.7, 5.1, 5.0, 5.2, 5.3, 5.3, 5.4, 6.0, 0.0, 2.9067, 3.9648, 9006.9013, 2998.5576, 3010.185, 2998.1587, 190.9714, 65.8348, 61.0829, 64.0537, 55.5387, 22.1745, 18.3226, 15.0416, 188.0, 93.77, 94.23, 30.44, 30.23, 31.33, 31.55, 32.0, 32.44],
+            ["3", 0.245754563, 0.053153144000000006, 0.24898895399999998, 1499.305683, 499.0019342, 499.56546389999994, 500.7382846, 31.09016923, 10.200109300000001, 11.24314965, 9.646910282999999, 11.18471882, 5.38607754, 2.750773441, 3.047867843, 31.9, 16.2, 15.7, 5.9, 5.8, 5.4, 5.2, 5.0, 4.7, 7.0, 1.7203, 0.3721, 1.7429, 10495.1398, 3493.0135, 3496.9582, 3505.1679999999997, 217.6312, 71.4008, 78.702, 67.5284, 78.293, 37.7025, 19.2554, 21.3351, 223.37, 113.33, 110.03, 40.98, 40.59, 37.63, 36.39, 34.72, 33.05],
+            ["4", 0.091581569, 1.29306045, 2.222550393, 1497.3095039999998, 500.2853801, 498.26926339999994, 498.7548608, 31.49017978, 10.80040763, 9.527649379, 11.16212277, 10.22765186, 3.03791456, 3.8605661610000004, 3.3291711439999996, 19.5, 8.5, 11.0, 2.8, 4.8, 2.6, 3.2, 3.1, 3.0, 14.0, 1.2821, 18.1028, 31.1157, 20962.3331, 7003.9953, 6975.7697, 6982.5681, 440.8625, 151.2057, 133.3871, 156.2697, 143.1871, 42.5308, 54.0479, 46.6084, 272.46, 118.55, 153.91, 39.34, 67.83, 36.17, 44.62, 43.04, 41.46],
+            ["5", 0.48547690299999996, 0.614760438, 1.620874173, 1498.722371, 500.4694436000001, 500.44068089999996, 497.81224689999993, 30.44836156, 10.06357482, 10.79756546, 9.587221282, 8.654173735, 5.294000296, 2.062538336, 1.297635102, 38.7, 16.0, 22.7, 2.3, 5.6, 5.1, 7.2, 8.6, 10.0, 2.0, 0.971, 1.2295, 3.2417, 2997.4447, 1000.9389, 1000.8814, 995.6245, 60.8967, 20.1271, 21.5951, 19.1744, 17.3083, 10.588, 4.1251, 2.5953, 77.47, 32.06, 45.41, 4.64, 11.13, 10.28, 14.32, 17.14, 19.96],
+            ["6", 0.216682565, 0.420119477, 0.077609457, 1497.974779, 499.146944, 498.292069, 500.5357663, 29.76051868, 9.465821929, 9.133324308999999, 11.16137244, 11.35927018, 5.351916919, 2.9535873489999998, 3.053765916, 29.9, 14.9, 15.0, 4.8, 4.7, 5.0, 5.0, 5.2, 5.3, 1.0, 0.2167, 0.4201, 0.0776, 1497.9748, 499.1469, 498.2921, 500.5358, 29.7605, 9.4658, 9.1333, 11.1614, 11.3593, 5.3519, 2.9536, 3.0538, 29.89, 14.89, 15.01, 4.75, 4.7, 4.98, 5.04, 5.15, 5.27],
+            ["7", 0.256570729, 1.635266926, 0.877078037, 1497.8444539999998, 499.91778619999997, 499.7594455, 498.16722269999997, 28.24588485, 9.099873094, 9.312124146, 9.833887614, 11.20396942, 4.079138201, 5.134802344, 1.990028871, 27.8, 15.0, 12.8, 5.4, 4.0, 5.1, 4.6, 4.4, 4.3, 6.3, 1.6164, 10.3022, 5.5256, 9436.4201, 3149.4821, 3148.4845, 3138.4535, 177.9491, 57.3292, 58.6664, 61.9535, 70.585, 25.6986, 32.3493, 12.5372, 175.25, 94.52, 80.73, 34.26, 25.06, 32.43, 28.75, 27.84, 26.92],
+            ["8", 0.733170964, 0.111266445, 0.506586275, 1500.596397, 501.64230189999995, 501.381718, 497.5723767, 28.169746500000002, 9.444435161, 9.593212578, 9.132098765, 10.80790153, 3.316276783, 4.322564458, 3.169060286, 34.8, 15.9, 18.9, 5.2, 7.6, 5.0, 5.8, 5.7, 5.6, 8.1, 5.9387, 0.9013, 4.1033, 12154.8308, 4063.3026, 4061.1919, 4030.3363, 228.1749, 76.4999, 77.705, 73.97, 87.544, 26.8618, 35.0128, 25.6694, 282.04, 128.61, 153.43, 41.83, 61.18, 40.65, 46.71, 46.12, 45.54],
+            ["9", 2.134056558, 0.31692025, 1.3120006770000001, 1498.986525, 501.01687419999996, 499.2999597, 498.66969119999993, 31.76279059, 10.04786784, 10.48995616, 11.22496658, 8.855932629, 4.065679953, 2.443454044, 2.346798631, 33.1, 16.4, 16.8, 5.3, 5.5, 5.4, 5.6, 5.6, 5.7, 1.0, 2.1341, 0.3169, 1.3119999999999998, 1498.9865, 501.0169, 499.3, 498.6697, 31.7628, 10.0479, 10.49, 11.225, 8.8559, 4.0657, 2.4435, 2.3468, 33.13, 16.35, 16.78, 5.29, 5.53, 5.43, 5.56, 5.63, 5.7],
+            ["10", 0.678504648, 0.35838638700000003, 0.569093572, 1498.674708, 500.2971126, 500.64281950000003, 497.7347761, 30.178638399999997, 9.173285232000001, 11.11531108, 9.890042091, 10.35101118, 3.143504622, 3.1301464180000003, 4.077360139, 31.8, 15.6, 16.2, 4.3, 4.1, 5.3, 5.5, 6.0, 6.5, 9.0, 6.1065, 3.2255, 5.1218, 13488.0724, 4502.674, 4505.7854, 4479.613, 271.6077, 82.5596, 100.0378, 89.0104, 93.1591, 28.2915, 28.1713, 36.6962, 286.0, 140.3, 145.7, 38.61, 37.17, 47.42, 49.87, 54.27, 58.67],
         ]
 
         exp_output_df = pd.DataFrame(data=data, columns=exp_output_columns)
diff --git a/tests/test_utils/test_path_helpers.py b/tests/test_utils/test_path_helpers.py
index 36a0d7fb2..348bf4330 100644
--- a/tests/test_utils/test_path_helpers.py
+++ b/tests/test_utils/test_path_helpers.py
@@ -25,6 +25,7 @@ def config():
             "ni_full_responses_path": "03_northern_ireland/2021/TEST_ni.csv",
             "manual_imp_trim_path": "06_imputation/man_trim/trim_qa.csv",
             "manual_outliers_path": "07_outliers/man_out/man_out.csv",
+            "backdata_path": "2021_data/backdata.csv",
             "all_data_construction_file_path": (
                 "04_construction/man_con/construction_file.csv"
             ),
@@ -80,6 +81,7 @@ def test_get_paths(config):
         "ni_full_responses_path": "03_northern_ireland/2021/TEST_ni.csv",
         "manual_outliers_path": "07_outliers/man_out/man_out.csv",
         "manual_imp_trim_path": "06_imputation/man_trim/trim_qa.csv",
+        "backdata_path": "2021_data/backdata.csv",
         "all_data_construction_file_path": (
             "04_construction/man_con/construction_file.csv"
         ),
@@ -108,6 +110,7 @@ def expected_staging_dict():
         "manual_imp_trim_path": (
             "R:/DAP_emulation/2022_surveys/BERD/06_imputation/man_trim/trim_qa.csv"
         ),
+        "backdata_path": "2021_data/backdata.csv",
     }
     return expected_staging_dict