From fe75c4d348430bdd00d60471b9395ceaa61d73a4 Mon Sep 17 00:00:00 2001
From: Ben Anderson <b.anderson@soton.ac.uk>
Date: Fri, 6 Mar 2015 17:35:55 +0000
Subject: [PATCH] added linearity tests to all households model
---
NEED/analyse-NEED-EULF-2014-models-v2.0.do | 31 ++++++++++++++++------
1 file changed, 23 insertions(+), 8 deletions(-)
diff --git a/NEED/analyse-NEED-EULF-2014-models-v2.0.do b/NEED/analyse-NEED-EULF-2014-models-v2.0.do
index 164c377..8b9ba19 100644
--- a/NEED/analyse-NEED-EULF-2014-models-v2.0.do
+++ b/NEED/analyse-NEED-EULF-2014-models-v2.0.do
@@ -54,15 +54,15 @@ local rpath "`proot'/results/NEED"
* restricted analysis to households where gas is main heat source as it is better predicted by variables included & is more relevant to EPC (heat)
* uses 1% sample (c 30k) making sure keep proportions of property type and EE_Band to see if linktest fails with smaller n
-*local version "v2_10pc"
-*local sample 10
-*local sampleby "EE_BAND PROP_TYPE"
+local version "v2_10pc"
+local sample 10
+local sampleby "EE_BAND PROP_TYPE"
* uses 10% sample (c 300k) making sure keep proportions of property type and EE_Band to see if margin plots and co-efficients are the same
* (linktest etc will probably now fail due to larger n)
-local version "v2_100pc"
-local sample 100
-local sampleby "EE_BAND PROP_TYPE"
+*local version "v2_100pc"
+*local sample 100
+*local sampleby "EE_BAND PROP_TYPE"
* uses full sample (c 3m) to see if margin plots and co-efficients are the same
* (linktest etc will probably now fail due to larger n)
@@ -145,7 +145,11 @@ destring BOILER, force replace
replace BOILER = 0 if BOILER == .
* household level vars
+* for models
local generic_hvars "i.BOILER_YEAR i.MAIN_HEAT_FUEL i.LI_YEAR i.LOFT_DEPTH i.FLOOR_AREA_BAND WALL_CONS i.CWI_YEAR i.PROP_TYPE i.PROP_AGE i.EE_BAND"
+* for graphs
+local generic_hvarsg "BOILER_YEAR MAIN_HEAT_FUEL LI_YEAR LOFT_DEPTH FLOOR_AREA_BAND WALL_CONS CWI_YEAR PROP_TYPE PROP_AGE EE_BAND"
+* for models by type
local generic_hvarsnp "i.BOILER_YEAR i.MAIN_HEAT_FUEL i.LI_YEAR i.LOFT_DEPTH i.FLOOR_AREA_BAND WALL_CONS i.CWI_YEAR i.PROP_AGE i.EE_BAND"
* area level vars
@@ -177,6 +181,17 @@ foreach v of local vars {
i.BOILER_YEAR
est store `v'
+ * test a variable
+ predict r, resid
+ foreach testv of local generic_hvarsg {
+ di "Testing residuals against `v'"
+ * based on http://www.ats.ucla.edu/stat/stata/webbooks/reg/chapter2/statareg2.htm
+ * can't use factor variables in acprplot...
+ graph box r, over(`testv') name(rtest_`testv')
+ graph export "`rpath'/graphs/rplot_`v'_`testv'-`version'.png", replace
+ }
+
+
di "* -> `v' estat to test for heteroskedasticity & omitted vars"
estat ovtest
estat hettest
@@ -189,7 +204,7 @@ foreach v of local vars {
di "* test EPC margins for `v'"
margins EE_BAND
- marginsplot, name(mplot_`v'_EE_BAND)
+ marginsplot, name(mplot_`v'_EE_BAND) note("All dwellings")
graph export "`rpath'/graphs/mplot_`v'_EE_BAND-`version'.png", replace
* models by property type - to see if rsq & coefficients vary
@@ -212,7 +227,7 @@ foreach v of local vars {
linktest
di "* test EPC margins for `v' (`pt`p'')"
margins EE_BAND
- marginsplot, name(mplot_`v'_EE_BAND_`pt`p'')
+ marginsplot, name(mplot_`v'_EE_BAND_`pt`p'') note("Type: `pt`p''")
graph export "`rpath'/graphs/mplot_`v'_EE_BAND_`pt`p''-`version'.png", replace
}
--
GitLab