Commit 50bcdcdc authored by Ben Anderson's avatar Ben Anderson
Browse files

added note & data source, updated to v1.1

v1.1: included only gas households to avoid confounding effects of potential electric & oil heating (we don't have oil consumption)
parent 5902f484
* Script to analyse DECC's NEED data
* NB this script uses 2 files derived from the original data
* Script to analyse DECC's NEED data to:
* investigate % variance of energy consumption due to dwelling type variables as a way to infer the % of variance due to people
* NB this script uses 2 data files derived from the original data using the 'process' script
* Original data available from: UK DATA ARCHIVE: Study Number 7518 - National Energy Efficiency Data-Framework, 2014
*
* http://discover.ukdataservice.ac.uk/catalogue/?sn=7518
* Ben Anderson, Energy & Climate Change, Faculty of Engineering & Environment, University of Southampton
* b.anderson@soton.ac.uk
......@@ -36,7 +38,17 @@ use "`dpath'/need_eul_may2014_consumptionfile_wide.dta", clear
keep HH_ID *2012*
* log the consumption
* log the consumption as it's very skewed -> becomes semi-normal & OK for linear regression
* Gcons = gas
* Econs = Electricity
* Presumably those without gas use oil or electricity for heating - we don't have oil so we should probably restrict analysis to gas-using hosueholds only to avoid this confounding factor?
* check what's valid
tab Gcons2012Valid Econs2012Valid, mi // what does G,L,M mean? Presumably O = off gas?
tabstat Gcons2012, by(Gcons2012Valid) s(mean min max n)
keep if Gcons2012Valid == "V"
gen log_Gcons2012 = log(Gcons2012)
gen log_Econs2012 = log(Econs2012)
......@@ -88,6 +100,7 @@ local pt104 "mid_terr"
local pt105 "bung"
local pt106 "flat"
* now loop over the energy types
local vars "Gcons Econs Allcons"
foreach v of local vars {
* all hhs model
......@@ -105,7 +118,7 @@ foreach v of local vars {
di "* http://www.ats.ucla.edu/stat/stata/webbooks/logistic/chapter3/statalog3.htm"
linktest
* by property type - to see if rsq & coefficients vary
* models by property type - to see if rsq & coefficients vary
foreach p of local ptypes {
di "* -> testing log_`v'2012 for `pt`p''"
qui: regress log_`v'2012 `generic_hvarsnp' ///
......@@ -123,7 +136,7 @@ foreach v of local vars {
di "* http://www.ats.ucla.edu/stat/stata/webbooks/logistic/chapter3/statalog3.htm"
linktest
}
* for different consumption quintiles - to see if rsq & coefficients vary
* models for different consumption quintiles - to see if rsq & coefficients vary
foreach q of numlist 0/4 {
di "* -> testing log_`v'2012 for quintile: `q'"
qui: regress log_`v'2012 `generic_hvars' ///
......@@ -144,6 +157,8 @@ foreach v of local vars {
}
* output all the results - that's a lot of t tests!
* we could put them all out in one file but it would be really hard to find the ones you want!
estout rlog_Gcons2012 using "`rpath'/NEED-EULF-2014-log-gas-model-`version'-$S_DATE.txt", replace cells("b se p _star") stats(r2 r2_a N ll)
estout rlog_Gcons2012q* using "`rpath'/NEED-EULF-2014-log-gas-models-quintiles-`version'-$S_DATE.txt", replace cells("b se p _star") stats(r2 r2_a N ll)
estout rlog_Gcons2012_* using "`rpath'/NEED-EULF-2014-log-gas-models-by-property-type-`version'-$S_DATE.txt", replace cells("b se p _star") stats(r2 r2_a N ll)
......@@ -153,3 +168,7 @@ estout rlog_Econs2012_* using "`rpath'/NEED-EULF-2014-log-elec-models-by-propert
estout rlog_Allcons2012 using "`rpath'/NEED-EULF-2014-log-energy-model-`version'-$S_DATE.txt", replace cells("b se p _star") stats(r2 r2_a N ll)
estout rlog_Allcons2012q* using "`rpath'/NEED-EULF-2014-log-energy-models-quintiles-`version'-$S_DATE.txt", replace cells("b se p _star") stats(r2 r2_a N ll)
estout rlog_Allcons2012_* using "`rpath'/NEED-EULF-2014-log-energy-models-by-property-type-`version'-$S_DATE.txt", replace cells("b se p _star") stats(r2 r2_a N ll)
di "* Done!"
log close
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment