diff --git a/ONS-UK-EFS-LCFS-time-series-extract.do b/ONS-UK-EFS-LCFS-time-series-extract.do
index 0ef7688555d3b97b27c63f35b531d183e96487c5..70025b8560c6b7a4f335cf7e30895c48dd7d276f 100755
--- a/ONS-UK-EFS-LCFS-time-series-extract.do
+++ b/ONS-UK-EFS-LCFS-time-series-extract.do
@@ -25,7 +25,7 @@
* so a mechanism has been included to allow the extraction of bespoke variables sets once this script has set all variable names to lower case
*
* For all subsequent changes see:
-* -> https://github.com/dataknut/LCFS/blob/master/ONS-UK-EFS-time-series-extract.do
+* -> https://github.com/dataknut/LCFS/blob/master/ONS-UK-EFS-LCFS-time-series-extract.do
* Copyright (c) 2002-2012 University of Essex, (c) 2012-2015 University of Southampton
*
@@ -49,8 +49,10 @@
set more off
* set these to what works for you
-local place = "/Users/ben/Documents/Work"
local efsd = "`place'/Data/Social Science Datatsets/Expenditure and Food Survey"
-local logd = "`efsd'/log_files"
local outd = "`efsd'/processed"
+local place = "~/Documents/Work"
+local efsd = "`place'/Data/Social Science Datatsets/Expenditure and Food Survey"
+local logd = "`efsd'/log_files"
+local outd = "`efsd'/processed"
************************
* NB - the script assumes a certain folder structure for the source EFS/LCFS data like so:
@@ -64,7 +66,7 @@ local extract_years "2001-2012" // just a name for the FINAL extracted file
* To save time you can leave out years you have already processed
* just paste the ones you want into the do_years local variable below
-* choose any of 2001-2002 2002-2003 2003-2004 2004-2005 2005-2006 2006 2007 2008 2009 2010 2011 2012
+* choose any of 2001-2002 2002-2003 2003-2004 2004-2005 2005-2006 2006 2007 2008 2009 2010 2011 2012
local do_years = "2001-2002 2002-2003 2003-2004 2004-2005 2005-2006 2006 2007 2008 2009 2010 2011 2012" // years to process
* set to 1 to refresh each yearly extract you listed in do_years & append the files
@@ -83,9 +85,10 @@ local dvhh_keepvars = ""
* needed for income equivalisation later
local dvhh_keepvars = "`dvhh_keepvars' incanon a055 g018 g019 p116* p344* p389* p396*"
* DEMAND 2.3 (older people mobile lives)
-local dvhh_keepvars = "`dvhh_keepvars' b480 b481 b485 cc5413t c73312t" // overseas travel expenditures
+*local dvhh_keepvars = "`dvhh_keepvars' b480 b481 b485 cc5413t c73312t" // overseas travel expenditures
* DEMAND 3.1 (adapting infrastructures)
-local dvhh_keepvars = "`dvhh_keepvars' a103 a108 a128 a130 a15* a16* a1701 a1711" // energy using appliances
+* a1701 a1711
+local dvhh_keepvars = "`dvhh_keepvars' a103 a108 a128 a130 a15* a16*" // energy using appliances
* -> dvper file
local dvper_keepvars = "case"
@@ -102,7 +105,7 @@ local rawper_keepvars = "case"
* set logging
capture log close
log using "`logd'/ONS-UK-EFS-time-series-extract-$S_DATE.smcl", replace
-
clear all
+clear all
* increase default number of variables allowed
set maxvar 10000, perm
@@ -115,7 +118,7 @@ di "* dvhh: `dvhh_keepvars' "
di "* rawhh: `rawhh_keepvars'"
di "* This could take some time. "
di "* I suggest you check it is running and then get a cup of tea...."
-di "*******************************************************"
+di "*******************************************************"
if `do_extracts' {
di "do_extracts = `do_extracts', all years (`years') to be extracted and refreshed"
@@ -126,44 +129,178 @@ if `do_extracts' {
* c_accom_0 c_accom_1 c_accom_2 c_accom_3 c_accom_4
* 0 "Detached" 1 "Semi-detached" 2 "Terraced" 3 "flat/maisonette" 4 "other"
-
* c_age_0 c_age_1 c_age_2 c_age_3 c_age_4 c_age_5 c_age_6 c_age_7
+
+ * c_age_0 c_age_1 c_age_2 c_age_3 c_age_4 c_age_5 c_age_6 c_age_7
* 0 "16-24" 1 "25-34" 2 "35-44" 3 "45-54" 4 "55-64" 5 "65-74" 6 "75+"
- * c_comp_0 c_comp_1 c_comp_2 c_comp_3
* 0 "married/partnered" 1 "single parent" 2 "single person" 3 "other"
-
* c_lli_0 c_lli_1
* 0 "No person with lli" 1 "At least 1 person with lli"
+ * c_comp_0 c_comp_1 c_comp_2 c_comp_3
+ * 0 "married/partnered" 1 "single parent" 2 "single person" 3 "other"
+
+ * c_lli_0 c_lli_1
+ * 0 "No person with lli" 1 "At least 1 person with lli"
* c_ncars_0 c_ncars_1 c_ncars_2
- * 0 None 1 One 2 "Two or more"
+ * 0 None 1 One 2 "Two or more"
- * c_nchild_0 c_nchild_1 c_nchild_2
* 0 None 1 One 2 "Two or more"
-
* c_nearners_0 c_nearners_1 c_nearners_2 c_nearners_3
+ * c_nchild_0 c_nchild_1 c_nchild_2
+ * 0 None 1 One 2 "Two or more"
+
+ * c_nearners_0 c_nearners_1 c_nearners_2 c_nearners_3
* 0 "0" 1 "1" 2 "2" 3 "3+"
-
* c_npersons_0 c_npersons_1 c_npersons_2 c_npersons_3 c_npersons_4
* 0 "1" 1 "2" 2 "3" 3 "4" 4 "5+"
+
+ * c_npersons_0 c_npersons_1 c_npersons_2 c_npersons_3 c_npersons_4
+ * 0 "1" 1 "2" 2 "3" 3 "4" 4 "5+"
* c_nrooms_0 c_nrooms_1 c_nrooms_2 c_nrooms_3
* 0 "1" 1 "2" 2 "3" 3 "4" 4 "5+"
- * c_empl_0 c_empl_1 c_empl_2 c_empl_3 c_empl_4
* 0 "NS-SEC 1" 1 "NS-SEC 2" 2 "NS-SEC 3" 3 "Inactive" 4 "Retired"
+ * c_empl_0 c_empl_1 c_empl_2 c_empl_3 c_empl_4
+ * 0 "NS-SEC 1" 1 "NS-SEC 2" 2 "NS-SEC 3" 3 "Inactive" 4 "Retired"
* c_gender_0 c_gender_1
* 0 "Male" 1 "Female"
-
* c_tenure_0 c_tenure_1 c_tenure_2 c_tenure_3
* 0 "Owned" 1 "Rent from council" 2 "Social rent" 3 "Private rent incl rent free"
+
+ * c_tenure_0 c_tenure_1 c_tenure_2 c_tenure_3
+ * 0 "Owned" 1 "Rent from council" 2 "Social rent" 3 "Private rent incl rent free"
- * c_white_0 c_white_1
* 0 "White HRP" 1 "Non-white HRP"
-
*/
******************************
- * dvhh
di "* dv household file"
use "`efsd'/`y'/stata/dvhh.dta", clear
+ * c_white_0 c_white_1
+ * 0 "White HRP" 1 "Non-white HRP"
+
+ */
+
+ ******************************
+ * dvhh
+ di "* dv household file"
+ use "`efsd'/`y'/stata/dvhh.dta", clear
+
* 2010 onwards data = mixed/uppercase
if "`y'" == "2010" | "`y'" == "2011" | "`y'" == "2012" {
rename *, lower
- }
** sex of HRP
gen c_gender = -1
replace c_gender = 0 if sexhrp == 1
replace c_gender = 1 if sexhrp == 2
lab var c_gender "Constraint: Gender of HRP"
lab def c_gender 0 "Male" 1 "Female"
lab val c_gender c_gender
** age of HRP
- * need to use 75+ as few 80+ after 2001-2
recode p396p (min/15= . ) (16/24 = 0) (25/34 = 1) (35/44 = 2) (45/54 = 3) ///
(55/64 = 4) (65/74 = 5) (75/max = 6), gen(c_age)
lab var c_age "Constraint: Age of HRP"
- * NB for NI need to change these as Census categories are different. Why why why!?
label define c_age ///
0 "16-24" ///
1 "25-34" ///
2 "35-44" ///
3 "45-54" ///
4 "55-64" ///
5 "65-74" ///
6 "75+"
lab val c_age c_age
- ** number of rooms
*1,2,3,4+
recode a114 (1=0) (2=1) (3=2) (4=3) (5/max=4), gen(c_nrooms)
lab var c_nrooms "Constraint: number of rooms"
lab def c_nrooms 0 "1" 1 "2" 2 "3" 3 "4" 4 "5+"
lab val c_nrooms c_nrooms
** Number of residents per household
recode a049 (1=0) (2=1) (3=2) (4=3) (5/max=4), gen(c_npersons)
lab var c_npersons "Constraint: number of persons in household (all ages)"
lab def c_npersons 0 "1" 1 "2" 2 "3" 3 "4" 4 "5+"
lab val c_npersons c_npersons
** Number of earners
recode a054 (0=0) (1=1) (2=2) (3/max=3), gen(c_nearners)
lab var c_nearners "Constraint: number of earners in household"
lab def c_nearners 0 "0" 1 "1" 2 "2" 3 "3+"
lab val c_nearners c_nearners
** Cars and vans.
* Object=
* 0 None
* 1 One
* 2 'Two or more'.
*has 1-12 so need to recode.
recode a124 (0=0) (1=1) (2/12=2), gen(c_ncars)
lab var c_ncars "Constraint: cars and vans"
lab define c_ncars 0 None 1 One 2 "Two or more"
lab val c_ncars c_ncars
*tab a124 c_cars
** Tenure.
* Object =
* 0 'Owned'
* 1 'Rent from council'
* 2 'Social rent'
* 3 'Private rent' - incl rent-free
*use a121.
recode a121 (5/7=0) (1=1) (2=2) (3/4 8=3), gen(c_tenure)
lab var c_tenure "Constraint: tenure"
lab define c_tenure 0 "Owned" 1 "Rent from council" 2 "Social rent" 3 "Private rent incl rent free"
lab val c_tenure c_tenure
*tab a121 c_tenure
** employment status.
* Object =
* 0 'NS-SEC 1'
* 1 'NS-SEC 2'
* 2 'NS-SEC 3'
* 3 'Inactive'
* 4 'Retired'.
* need to combine these - a093 = activity, a094 = NS-SEC.
* ref ONS website.
* need to put a094 = 9,10,11 ('Never worked and long term unemployed',students, not stated) into 'inactive'
recode a094 (0/2=0) (3/4=1) (5/8=2) (9/12=3), gen(c_empl)
* the crosstab of a094 against a093 shows that some who are coded as
* retired/unoccupied (a093=4/5) have an NS-SEC code as they are recently
* retired/unoccupied (?). In this case we use the activity code not the NS-SEC code.
replace c_empl=3 if a093==7
replace c_empl=4 if a093==6
lab var c_empl "Constraint: employment status of HRP"
lab define c_empl 0 "NS-SEC 1" 1 "NS-SEC 2" 2 "NS-SEC 3" 3 "Inactive" 4 "Retired"
lab val c_empl c_empl
*tab a093 c_empl
*tab a094 c_empl
-
** Region.
* use gorx.
gen region = gorx
label define region 1 "North East" 2 "North West & Merseyside" 3 "Yorkshire and the Humber" ///
4 "East Midlands" 5 "West Midlands" 6 "Eastern" 7 "London" 8 "South East" ///
9 "South West" 10 "Wales" 11 "Scotland" 12 "Northern Ireland"
lab var region "Govt. Office Region"
lab val region region
** Number of children - 16 or younger.
*Object =
* 0 0
* 1 1
* 2 2+.
gen c_nchild = a040+a041+a042
+ }
+ ** sex of HRP
+ gen c_gender = -1
+ replace c_gender = 0 if sexhrp == 1
+ replace c_gender = 1 if sexhrp == 2
+ lab var c_gender "Constraint: Gender of HRP"
+ lab def c_gender 0 "Male" 1 "Female"
+ lab val c_gender c_gender
+
+ ** age of HRP
+ * need to use 75+ as few 80+ after 2001-2
+ recode p396p (min/15= . ) (16/24 = 0) (25/34 = 1) (35/44 = 2) (45/54 = 3) ///
+ (55/64 = 4) (65/74 = 5) (75/max = 6), gen(c_age)
+ lab var c_age "Constraint: Age of HRP"
+ * NB for NI need to change these as Census categories are different. Why why why!?
+ label define c_age ///
+ 0 "16-24" ///
+ 1 "25-34" ///
+ 2 "35-44" ///
+ 3 "45-54" ///
+ 4 "55-64" ///
+ 5 "65-74" ///
+ 6 "75+"
+
+ lab val c_age c_age
+
+ ** number of rooms
+ *1,2,3,4+
+ recode a114 (1=0) (2=1) (3=2) (4=3) (5/max=4), gen(c_nrooms)
+ lab var c_nrooms "Constraint: number of rooms"
+ lab def c_nrooms 0 "1" 1 "2" 2 "3" 3 "4" 4 "5+"
+ lab val c_nrooms c_nrooms
+
+ ** Number of residents per household
+ recode a049 (1=0) (2=1) (3=2) (4=3) (5/max=4), gen(c_npersons)
+ lab var c_npersons "Constraint: number of persons in household (all ages)"
+ lab def c_npersons 0 "1" 1 "2" 2 "3" 3 "4" 4 "5+"
+ lab val c_npersons c_npersons
+
+ ** Number of earners
+ recode a054 (0=0) (1=1) (2=2) (3/max=3), gen(c_nearners)
+ lab var c_nearners "Constraint: number of earners in household"
+ lab def c_nearners 0 "0" 1 "1" 2 "2" 3 "3+"
+ lab val c_nearners c_nearners
+
+ ** Cars and vans.
+ * Object=
+ * 0 None
+ * 1 One
+ * 2 'Two or more'.
+
+ *has 1-12 so need to recode.
+
+ recode a124 (0=0) (1=1) (2/12=2), gen(c_ncars)
+ lab var c_ncars "Constraint: cars and vans"
+ lab define c_ncars 0 None 1 One 2 "Two or more"
+ lab val c_ncars c_ncars
+ *tab a124 c_cars
+
+ ** Tenure.
+ * Object =
+ * 0 'Owned'
+ * 1 'Rent from council'
+ * 2 'Social rent'
+ * 3 'Private rent' - incl rent-free
+
+ *use a121.
+ recode a121 (5/7=0) (1=1) (2=2) (3/4 8=3), gen(c_tenure)
+ lab var c_tenure "Constraint: tenure"
+ lab define c_tenure 0 "Owned" 1 "Rent from council" 2 "Social rent" 3 "Private rent incl rent free"
+ lab val c_tenure c_tenure
+ *tab a121 c_tenure
+
+ ** employment status.
+ * Object =
+ * 0 'NS-SEC 1'
+ * 1 'NS-SEC 2'
+ * 2 'NS-SEC 3'
+ * 3 'Inactive'
+ * 4 'Retired'.
+
+ * need to combine these - a093 = activity, a094 = NS-SEC.
+ * ref ONS website.
+
+ * need to put a094 = 9,10,11 ('Never worked and long term unemployed',students, not stated) into 'inactive'
+ recode a094 (0/2=0) (3/4=1) (5/8=2) (9/12=3), gen(c_empl)
+ * the crosstab of a094 against a093 shows that some who are coded as
+ * retired/unoccupied (a093=4/5) have an NS-SEC code as they are recently
+ * retired/unoccupied (?). In this case we use the activity code not the NS-SEC code.
+
+ replace c_empl=3 if a093==7
+ replace c_empl=4 if a093==6
+
+ lab var c_empl "Constraint: employment status of HRP"
+ lab define c_empl 0 "NS-SEC 1" 1 "NS-SEC 2" 2 "NS-SEC 3" 3 "Inactive" 4 "Retired"
+ lab val c_empl c_empl
+ *tab a093 c_empl
+ *tab a094 c_empl
+
+ ** Region.
+ * use gorx.
+
+ gen region = gorx
+ label define region 1 "North East" 2 "North West & Merseyside" 3 "Yorkshire and the Humber" ///
+ 4 "East Midlands" 5 "West Midlands" 6 "Eastern" 7 "London" 8 "South East" ///
+ 9 "South West" 10 "Wales" 11 "Scotland" 12 "Northern Ireland"
+ lab var region "Govt. Office Region"
+ lab val region region
+
+
+ ** Number of children - 16 or younger.
+ *Object =
+ * 0 0
+ * 1 1
+ * 2 2+.
+ gen c_nchild = a040+a041+a042
* 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
+ * 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'
* construct list of vars to keep
@@ -181,7 +318,7 @@ if `do_extracts' {
* try as a varlist (forces expansion)
di "* Not found, expanding `v'"
capture noisily {
- * if variable really doesn't exist this throws an exception moves on
+ * if variable really doesn't exist this throws an exception & moves on
foreach vt of varlist `v' {
capture confirm variable `vt'
if !_rc {
@@ -195,18 +332,71 @@ if `do_extracts' {
di "* dvhh: keeping case* ba_* c_* region weight* `keepvars'"
keep case* ba_* c_* region weight* `keepvars'
- qui: compress
* save kept dvhh vars
save "`efsd'/`y'/stata/dvhh-temp.dta", replace
******************************
-
******************************
- * rawhh
di "* raw household file for: c_comp and c_accom"
- di "* also to pick up: `rawhh_keepvars'"
use "`efsd'/`y'/stata/rawhh.dta", clear
+ qui: compress
+ * save kept dvhh vars
+ save "`efsd'/`y'/stata/dvhh-temp.dta", replace
+ ******************************
+
+ ******************************
+ * rawhh
+ di "* raw household file for: c_comp and c_accom"
+ di "* also to pick up: `rawhh_keepvars'"
+
+ use "`efsd'/`y'/stata/rawhh.dta", clear
+
* 2010 onwards data = mixed/uppercase
if "`y'" == "2010" | "`y'" == "2011" | "`y'" == "2012" {
rename *, lower
- }
* accomodation type
* Object=
* 0 Detached
* 1 Semi
* 2 Terrace
* 3 flat/maisontte
* 4 other
gen ba_c_accom = -1
replace ba_c_accom = 0 if hsetype == 1
replace ba_c_accom = 1 if hsetype == 2
replace ba_c_accom = 2 if hsetype == 3
+ }
+
+ * accomodation type
+ * Object=
+ * 0 Detached
+ * 1 Semi
+ * 2 Terrace
+ * 3 flat/maisontte
+ * 4 other
+ gen ba_c_accom = -1
+ replace ba_c_accom = 0 if hsetype == 1
+ replace ba_c_accom = 1 if hsetype == 2
+ replace ba_c_accom = 2 if hsetype == 3
if survyr > 2001 {
* grr, why can't var names stay the same?!
gen acomtype = accom
- }
replace ba_c_accom = 3 if acomtype == 2
replace ba_c_accom = 4 if acomtype == 3
replace ba_c_accom = 4 if acomtype == 4
lab var ba_c_accom "Constraint: accommodation type"
lab define c_accom 0 "Detached" 1 "Semi-detached" 2 "Terraced" 3 "flat/maisonette" 4 "other"
lab val ba_c_accom c_accom
** Composition.
* Object =
* 0 'married/partnered'
* 1 'single parent'
* 2 'single person'
* 3 'other'.
* co-habiting.
gen ba_c_comp=1 if numcpart>0
* married.
replace ba_c_comp=0 if nummpart>0
* single parent - assumes a single adult living with 1 or more
* children is a single parent.
replace ba_c_comp=1 if (numadult==1 & numchild>0)
* single person.
replace ba_c_comp=2 if (numadult==1 & numchild==0)
* the rest - this is a cheat!
recode ba_c_comp (missing=3)
lab var ba_c_comp "Constraint: household composition"
lab define c_comp 0 "married/partnered" 1 "single parent" 2 "single person" 3 "other"
lab val ba_c_comp c_comp
tab ba_c_comp numcpart
tab ba_c_comp nummpart
+ }
+ replace ba_c_accom = 3 if acomtype == 2
+ replace ba_c_accom = 4 if acomtype == 3
+ replace ba_c_accom = 4 if acomtype == 4
+
+ lab var ba_c_accom "Constraint: accommodation type"
+ lab define c_accom 0 "Detached" 1 "Semi-detached" 2 "Terraced" 3 "flat/maisonette" 4 "other"
+ lab val ba_c_accom c_accom
+
+ ** Composition.
+ * Object =
+ * 0 'married/partnered'
+ * 1 'single parent'
+ * 2 'single person'
+ * 3 'other'.
+
+ * co-habiting.
+ gen ba_c_comp=1 if numcpart>0
+ * married.
+ replace ba_c_comp=0 if nummpart>0
+ * single parent - assumes a single adult living with 1 or more
+ * children is a single parent.
+ replace ba_c_comp=1 if (numadult==1 & numchild>0)
+ * single person.
+ replace ba_c_comp=2 if (numadult==1 & numchild==0)
+ * the rest - this is a cheat!
+ recode ba_c_comp (missing=3)
+ lab var ba_c_comp "Constraint: household composition"
+ lab define c_comp 0 "married/partnered" 1 "single parent" 2 "single person" 3 "other"
+ lab val ba_c_comp c_comp
+ tab ba_c_comp numcpart
+ tab ba_c_comp nummpart
+
+
if "`y'" == "2001-2002" | "`y'" == "2002-2003" | "`y'" == "2003-2004" | "`y'" == "2004-2005" | "`y'" == "2005-2006" | "`y'" == "2006" | "`y'" == "2007" {
di "* Setting up cal year for `y'"
* tab survyr sampyear, mi
@@ -245,16 +435,18 @@ if `do_extracts' {
qui: compress
- save "`efsd'/`y'/stata/rawhh-temp.dta", replace
******************************
-
******************************
+ save "`efsd'/`y'/stata/rawhh-temp.dta", replace
+ ******************************
+
+ ******************************
* rawper
di "* Need rawper file for ethnicity detail"
- use "`efsd'/`y'/stata/rawper.dta", clear
+ use "`efsd'/`y'/stata/rawper.dta", clear
* 2010 data = mixed/uppercase
if "`y'" == "2010" | "`y'" == "2011" | "`y'" == "2012" {
rename *, lower
- }
+ }
* keep HRPs
tab hrpid, nol
@@ -321,17 +513,27 @@ if `do_extracts' {
******************************
******************************
- * dvper
di "* Need dvper file to count n children aged under 14 (for OECD equivalisation weight)"
+ * dvper
+ di "* Need dvper file to count n children aged under 14 (for OECD equivalisation weight)"
+
+ use "`efsd'/`y'/stata/dvper.dta", clear
-
use "`efsd'/`y'/stata/dvper.dta", clear
* 2010 data = mixed/uppercase
if "`y'" == "2010" | "`y'" == "2011" | "`y'" == "2012" {
rename *, lower
- }
* keep only hrps
keep if a003 == 1
+ }
+
+ * keep only hrps
+ keep if a003 == 1
* Ethnicity
* NB a012 and a013 changed categories 2007->2008 to 0 = n/a, 1 = white, 2 = everyone else
- * this still works, you can get detail from rawper.dta
recode a012p (1=0) (2/max=1), gen(c_white)
lab var c_white "Constraint: non-white HRP"
lab def c_white 0 "White HRP" 1 "Non-white HRP"
lab val c_white c_white
* if HRPs are not classified - they will show up as missing
+ * this still works, you can get detail from rawper.dta
+ recode a012p (1=0) (2/max=1), gen(c_white)
+ lab var c_white "Constraint: non-white HRP"
+ lab def c_white 0 "White HRP" 1 "Non-white HRP"
+ lab val c_white c_white
+ * if HRPs are not classified - they will show up as missing
* construct list of vars to keep
* if dvper_keepvars is empty STATA will skip
@@ -346,21 +548,24 @@ if `do_extracts' {
di in red "`v' does not exist in `y' - will be missing"
}
}
-
keep case* c_white
+ keep case* c_white
qui: compress
-
save "`efsd'/`y'/stata/dvper-temp.dta", replace
- ******************************
- ************
* Now c_lli but this time need to collapse it so we count the number in the household with/out lli
- * and count the number of children of various ages
- use "`efsd'/`y'/stata/dvper.dta", clear
+ save "`efsd'/`y'/stata/dvper-temp.dta", replace
+ ******************************
+
+ ************
+ * Now c_lli but this time need to collapse it so we count the number in the household with/out lli
+ * and count the number of children of various ages
+
+ use "`efsd'/`y'/stata/dvper.dta", clear
* 2010 onwards data = mixed/uppercase
if "`y'" == "2010" | "`y'" == "2011" | "`y'" == "2012" | "`y'" == "2012" {
rename *, lower
}
-
+
* assume if someone is eligible for incapacity benefit then = lli
* even if not actually receiving
* in rawper dvincap = a + b
@@ -390,12 +595,18 @@ if `do_extracts' {
keep case* ba_* c_*
qui: compress
save "`efsd'/`y'/stata/dvper-lli.dta", replace
-
di "*** MERGE ALL FILES for year = `y'"
+
+
+ di "*** MERGE ALL FILES for year = `y'"
*
-
qui: merge case using ///
"`efsd'/`y'/stata/dvhh-temp.dta" ///
- "`efsd'/`y'/stata/rawper-temp.dta" ///
"`efsd'/`y'/stata/dvper-temp.dta" ///
- "`efsd'/`y'/stata/dvper-lli.dta" ///
"`efsd'/`y'/stata/rawhh-temp.dta" , sort
+
+ qui: merge case using ///
+ "`efsd'/`y'/stata/dvhh-temp.dta" ///
+ "`efsd'/`y'/stata/rawper-temp.dta" ///
+ "`efsd'/`y'/stata/dvper-temp.dta" ///
+ "`efsd'/`y'/stata/dvper-lli.dta" ///
+ "`efsd'/`y'/stata/rawhh-temp.dta" , sort
su _merge*
@@ -405,7 +616,8 @@ if `do_extracts' {
erase "`efsd'/`y'/stata/dvper-temp.dta"
erase "`efsd'/`y'/stata/dvper-lli.dta"
erase "`efsd'/`y'/stata/rawhh-temp.dta"
-
gen survey_year = "`y'"
+
+ gen survey_year = "`y'"
tab survey_year
aorder
@@ -422,7 +634,22 @@ if `do_extracts' {
gen ba_adults = g018 if g018 > 0
* ignore hhs with no adults (how many are there?)
- /*
1st adult = .67
spouse = .33
other 2nd adult = .33
3rd adult = .33
subsequent adults = .33
children aged < 14 = .2
children aged 14+ = .33
*/
* catch hh with no children
replace ba_under14 = 0 if ba_under14 == .
replace ba_over14 = 0 if ba_over14 == .
gen oecd_equivbhcwt = 0.67 if ba_adults >= 1
replace oecd_equivbhcwt = oecd_equivbhcwt + ((ba_adults-1) * 0.33) + (ba_under14 * 0.2) + (ba_over14 * 0.33)
di "*-> Calculating equiv income (OECD) and quartiles/deciles"
+ /*
+ 1st adult = .67
+ spouse = .33
+ other 2nd adult = .33
+ 3rd adult = .33
+ subsequent adults = .33
+ children aged < 14 = .2
+ children aged 14+ = .33
+ */
+ * catch hh with no children
+ replace ba_under14 = 0 if ba_under14 == .
+ replace ba_over14 = 0 if ba_over14 == .
+
+ gen oecd_equivbhcwt = 0.67 if ba_adults >= 1
+ replace oecd_equivbhcwt = oecd_equivbhcwt + ((ba_adults-1) * 0.33) + (ba_under14 * 0.2) + (ba_over14 * 0.33)
+ di "*-> Calculating equiv income (OECD) and quartiles/deciles"
* p344, p389 & p396 changed to *p after 2006 and top coded (!)
if `y' > 2005 {
@@ -452,10 +679,17 @@ if `do_extracts' {
* quarter labels changed in 2006
* old:
- * 1 april to june
* 2 june to september
* 3 october to december
* 4 january to march
+ * 1 april to june
+ * 2 june to september
+ * 3 october to december
+ * 4 january to march
* new:
- * a099:
* 1 january to march
* 2 april to june
* 3 july to september
* 4 october to december
+ * a099:
+ * 1 january to march
+ * 2 april to june
+ * 3 july to september
+ * 4 october to december
gen ba_month = a055
@@ -471,7 +705,8 @@ if `do_extracts' {
gen(ba_birth_cohort)
* tab ba_birth_cohort c_age, mi
-
***********************
+
+ ***********************
* End of per-year processing
gen ba_quarter = -1
@@ -499,7 +734,8 @@ if `do_extracts' {
qui: compress
- save "`outd'/EFS-`y'-extract-BA.dta", replace
}
+ save "`outd'/EFS-`y'-extract-BA.dta", replace
+ }
}
****************************
@@ -555,6 +791,6 @@ else
{
di "*-> do_extracts = `do_extracts', years not extracted so individual files not refreshed"
}
-
di "*-> Job ended at $S_DATE"
+di "*-> Job ended at $S_DATE"
-log close
+log close