From 09367a992ef739557d8bf24f77aa9ff20c20a1a1 Mon Sep 17 00:00:00 2001
From: Ben Anderson <b.anderson@soton.ac.uk>
Date: Wed, 29 Apr 2015 15:56:54 +0100
Subject: [PATCH] altered to provide a mechanism to extract a bespoke set of
variables from the dvhh file
due to:
- variables in upper case after 2009 (why?)
- mis-matching variable types in different years (why?)
This made it complicated to use a core set of variables and match year
by year.
---
ONS-UK-EFS-time-series-extract.do | 17 ++++++++++++-----
1 file changed, 12 insertions(+), 5 deletions(-)
diff --git a/ONS-UK-EFS-time-series-extract.do b/ONS-UK-EFS-time-series-extract.do
index 445f4ec..9b6b5c3 100755
--- a/ONS-UK-EFS-time-series-extract.do
+++ b/ONS-UK-EFS-time-series-extract.do
@@ -68,13 +68,17 @@ local years "2001-2012" // just a label
local all_years "2001-2002 2002-2003 2003-2004 2004-2005 2005-2006 2006 2007 2008 2009 2010 2011 2012" // years to process
local do_years = "2001-2002 2002-2003 2003-2004 2004-2005 2005-2006 2006 2007 2008 2009 2010 2011 2012"
* set to 1 to refresh each yearly extract you listed in do_years
-local do_extracts 0
+local do_extracts 1
* drop the first survey for the merge as it is loaded first
local mergeyears = "2002-2003 2003-2004 2004-2005 2005-2006 2006 2007 2008 2009 2010 2011 2012"
-* be sure to keep only these from the dv hh file - last ones needed for income equivalisation later
-local dvhh_keepvars = "incanon weight* a055 g018 g019 p116* p344* p389*"
+* be sure to keep only these from the dv hh file - these will be 'kept' after the var names have been reduced to lower case
+* DEMAND 2.3 (older people mobile lives)
+local dvhh_keepvars = "b480 b481 c96111* c96112* cc5413* c73311* c73312*"
+
+* needed for income equivalisation later
+local dvhh_keepvars = "`dvhh_keepvars' incanon weight* a055 g018 g019 p116* p344* p389*"
capture log close
log using "`logd'/ONS-UK-EFS-time-series-extract-$S_DATE.smcl", replace
@@ -137,10 +141,13 @@ if `do_extracts' {
* could use g019?
- * has 1, 2 and more than 2 - so needs recoding.
recode c_nchild (0=0) (1=1) (2/max=2)
lab var c_nchild "Constraint: number of children"
lab define c_nchild 0 None 1 One 2 "Two or more"
lab val c_nchild c_nchild
** Sorting
sort case
+ * has 1, 2 and more than 2 - so needs recoding.
recode c_nchild (0=0) (1=1) (2/max=2)
lab var c_nchild "Constraint: number of children"
lab define c_nchild 0 None 1 One 2 "Two or more"
lab val c_nchild c_nchild
+ gen ba_year = `y'
+
** Sorting
sort case
* keep only basic variables
- keep case* c_* region `dvhh_keepvars'
+
+ keep case* ba_* c_* region `dvhh_keepvars'
qui: compress
* save all vars
save "`efsd'/`y'/stata/dvhh-temp.dta", replace
******************************
di "* raw household file for c_comp and c_accom"
* also to pick up electricity water payments periodicity etc for error analysis
use "`efsd'/`y'/stata/rawhh.dta", clear
--
GitLab