AB - Updated do files

input_processing/00_master_conditions.do → input_processing/00_master_conditions_PL.do

@@ -167,13 +167,13 @@ global r1a_if_condition "dcpst == 2 & dag >= ${age_can_retire} & flag_deceased !
 global r1b_if_condition "ssscp != 1 & dcpst == 1 & dag >= ${age_can_retire} & flag_deceased != 1"
 
 * Wages
-global W1fa_if_condition "dgn == 0 & dag >= ${age_seek_employment} & dag <= ${age_force_retire} & flag_deceased != 1"
+global W1fa_if_condition "dgn == 0 & dag >= ${age_seek_employment} & dag <= ${age_force_retire} & deh_c4 != 0 & flag_deceased != 1"
 
-global W1ma_if_condition "dgn == 1 & dag >= ${age_seek_employment} & dag <= ${age_force_retire} & flag_deceased != 1"
+global W1ma_if_condition "dgn == 1 & dag >= ${age_seek_employment} & dag <= ${age_force_retire} & deh_c4 != 0 & flag_deceased != 1"
 
-global W1fb_if_condition "dgn == 0 & dag >= ${age_seek_employment} & dag <= ${age_force_retire} & previouslyWorking == 1 & flag_deceased != 1"
+global W1fb_if_condition "dgn == 0 & dag >= ${age_seek_employment} & dag <= ${age_force_retire} & deh_c4 != 0 & previouslyWorking == 1 & flag_deceased != 1"
 
-global W1mb_if_condition "dgn == 1 & dag >= ${age_seek_employment} & dag <= ${age_force_retire} & previouslyWorking == 1 & flag_deceased != 1"
+global W1mb_if_condition "dgn == 1 & dag >= ${age_seek_employment} & dag <= ${age_force_retire} & deh_c4 != 0 & previouslyWorking == 1 & flag_deceased != 1"
 
 * Capital income 
 global i1a_if_condition "dag >= ${age_becomes_semi_responsible} & flag_deceased != 1" 

input_processing/data_construction/PL/00_master_data_set_construction_PL.do

@@ -9,10 +9,12 @@
 * DATA:         	    Longitudinal EU-SILC UDB version, 2005 - 2020 
 * AUTHORS: 				Clare Fenwick, Daria Popova, Ashley Burdett, 
 * 						Aleksandra Kolndrekaj
-* LAST UPDATE:          Jan 2026 AB
+* LAST UPDATE:          March 2026 AB
 * 
 ********************************************************************************
 * NOTES:
+*	ENSURE HAVE ALREADY RUN 00_master_conditions.do FILE.
+*
 *   Before running these files, the cumulative panel for each file type 
 * 	(D, H, R, P) must be constructed. These cumulative panels should be created 
 * 	following the procedure set out in *GESIS Papers 2022/10*. The do-files to 
@@ -115,7 +117,7 @@ global dir_ind "/Users/ashleyburdett/Library/CloudStorage/Box-Box"
 // Aleksandra - C:/Users/ak25793/Box
 
 * Working directory
-global dir_work "$dir_ind/CeMPA shared area/_SimPaths/_SimPathsEU/initial_populations/PL"
+global dir_work "$dir_ind/CeMPA shared area/_SimPaths/_SimPathsEU/input_processing/initial_populations/PL"
 
 * Directory containing do files
 global dir_do "$dir_work/do_files"
@@ -146,21 +148,21 @@ global dir_data_05_20 "$dir_data/orig_panel_2005_2020"
 * DEFINE PARAMETERS & PROCESS IF CONDITIONS
 *******************************************************************************/
 
-do "$dir_ind/CeMPA shared area/_SimPaths/_SimPathsEU/00_master_conditions.do"
+do "$dir_ind/CeMPA shared area/_SimPaths/_SimPathsEU/input_processing/00_master_conditions_PL.do"
 
 
 /*******************************************************************************
 * EXECUTE FILES
 *******************************************************************************/
 //do "$dir_do/01_prepare_pooled_data.do"
 
-do "$dir_do/02_create_variables_PL.do"
+do "$dir_do/02_create_variables_${country}.do"
 
-do "$dir_do/03_create_benefit_units_PL.do"
+do "$dir_do/03_create_benefit_units_${country}.do"
 
-do "$dir_do/04_reweight_PL.do"
+do "$dir_do/04_reweight_${country}.do"
 
-do "$dir_do/05_drop_hholds_and_slice_PL.do"
+do "$dir_do/05_drop_hholds_slice_and_refactoring_${country}.do"
 
-do "$dir_do/06_check_yearly_data_PL.do"
+do "$dir_do/06_check_yearly_data_${country}.do"
 

input_processing/data_construction/PL/01_prepare_pooled_data_PL.do

@@ -1,5 +1,5 @@
 ********************************************************************************
-* PROJECT:              ESPON
+* PROJECT:              SImPaths EU 
 * DO-FILE NAME:         01_prepare_pooled_data.do
 * DESCRIPTION:          Compiles panel dataset from EU-SILC  
 ********************************************************************************
@@ -23,10 +23,42 @@ merge these chunks of data into one cumulative dataset (separately for the
 D-,H-,R- and P-data).
 */
 /*
-Initial populations: cross-sectional SILC for 2011-2023 (income 2010-2022), 
-2023 (income 2022)
-Estimation sample: longitudinal SILC with observations from 2011-2023 
-(income 2010-2022)
+STRUCTURE OF THIS FILE
+
+  The script builds a person-level panel dataset for a single country by
+  sequentially merging the four EU-SILC master files produced by the panel
+  construction scripts (01-04 in eu_silc_do_2025/).
+
+  Files are merged in the following order, with R as the base:
+
+    R (Personal Register) — loaded first as the base. Contains all persons
+      in the sample including children under 16. Key identifiers: upid
+      (unique person ID across releases), uhid (unique household ID), year.
+
+    P (Personal Data) — merged 1:1 on year+upid+uhid. Contains income and
+      personal variables for adults aged 16 and above only. After this merge:
+      - Adults (in both R and P): have full R and P variables
+      - Children (in R only, not P): retained with R variables only
+      - Records in P but not R: dropped (should not occur in clean data)
+
+    D (Household Register) — merged 1:m on year+uhid. D is household-level
+      so one D row maps to multiple persons. keep if _merge==3 retains only
+      persons whose household appears in D. A small number of households may
+      not merge — this is suspected to be an edge case from the cross-release
+      deduplication in 01_create_masterD.do but has not been fully investigated.
+
+    H (Household Data) — merged 1:m on year+uhid, same logic as D.
+
+  KEY IDENTIFIERS
+    upid  — unique personal ID across releases (country + rotation group +
+             dropout year + pid). Not the same as the raw pid in the source data
+    uhid  — unique household ID across releases (same construction logic).
+    year  — income reference year.
+
+  OUTPUT
+    ${country}-SILC_pooled_all_obs_01.dta — person-level panel for the target
+    country, containing all household members (adults and children) with
+    combined R, P, D, and H variables. Flag variables (*_f, *_i) are dropped.
 */
 
 ********************************************************************************