7.6 Ordinal logistic regression in domain analysis

In Chapter 6.5, we preform ordinal regression on the variable \(\texttt{ENV_AFRDWLK_MCQ}\). Suppose we are interested in \(\texttt{ENV_AFRDWLK_MCQ}\) for the group of people who answer the questionnaire in English only, we can use the following codes:

summary(svyolr(formula = ENV_AFRDWLK_MCQ ~ SEX_ASK_TRM + Age_group_5 +
       Education + WGHTS_PROV_TRM, 
       design = subset(CLSA.design.anly, startlanguage == "en"),
       na.action = na.omit, method = c("logistic")) )

SAS

PROC SURVEYLOGISTIC data = CLSAData;
CLASS ENV_AFRDWLK_MCQ WGHTS_PROV_TRM(ref = 'AB') Age_group_5(ref = '45-48') 
      SEX_ASK_TRM(ref = 'F') Education(ref = 'Low Education')/param = ref;
MODEL ENV_AFRDWLK_MCQ = SEX_ASK_TRM Age_group_5  Education WGHTS_PROV_TRM /clodds ;
DOMAIN  startlanguage;  
STRATA GEOSTRAT_TRM;                           
WEIGHT WGHTS_ANALYTIC_TRM;   
ODS output  ParameterEstimates = est       
run;  

PROC PRINT data = EST;
WHERE  startlanguage = 'en';
RUN;

SPSS

Analyze \(\rightarrow\) Complex Samples \(\rightarrow\) Ordinal Regression… \(\rightarrow\) in the “Plan” panel, select the file “\(\texttt{CLSADesignAnyl.csaplan}\)” \(\rightarrow\) click “Continue” \(\rightarrow\) select the corresponding variables to the “Dependent Variable”, “Factor” and “Covariate” panels \(\rightarrow\) click “Response Probabilities” and select “Accumulate from lowest value of dependent variable to highest value” \(\rightarrow\) select “\(\texttt{startlanguage}\)” to the “Subpopulations” panel and enter the target category \(\rightarrow\) click “Statistics…” \(\rightarrow\) select “Estimate” and “Standard error” \(\rightarrow\) click “Continue” \(\rightarrow\) click “OK”.

Stata

svy linearized, subpop(if  startlanguage == "en"):  ologit ENV_AFRDWLK_MCQ  
     i.SEX_ASK_TRM  i.Age_group_5 ib3.Education i.WGHTS_PROV_TRM

Result comparison

	R		SAS		SPSS		Stata
Population Estimates	Coeff.	SE	Coeff.	SE	Coeff.	SE	Coeff.	SE
SEX_ASK_TRM=“M”	-0.2953	0.2621	-0.2953	0.2483	-0.2953	0.2621	-0.2953	0.2621
Age Groups: relative to Age_Gpr0: Age 45-48
Age_Gpr1:Age 49-54	-0.8864	0.4833	-0.8864	0.5500	-0.8864	0.4833	-0.8864	0.4833
Age_Gpr2:Age 55-64	-1.8779	0.4652	-1.8779	0.5319	-1.8779	0.4652	-1.8779	0.4652
Age_Gpr3:Age 65-74	-2.6458	0.5664	-2.6458	0.5765	-2.6458	0.5665	-2.6458	0.5665
Age_Gpr4:Age 75+	-1.8549	0.7224	-1.8548	0.6224	-1.8550	0.7224	-1.8550	0.7224
Education Levels: relative to Lower Education
Medium Education	0.0377	0.3189	-0.4549	0.4262	0.0377	0.3189	0.0377	0.3189
Higher Education lower	-0.4549	0.4278	-0.1094	0.3637	-0.4549	0.4278	-0.4549	0.4278
Higher Education upper	-0.1094	0.3601	0.0377	0.3313	-0.1094	0.3601	-0.1094	0.3601
Provinces: relative to Alberta
British Columbia	0.4416	0.6038	0.4415	0.5546	0.4416	0.6038	0.4416	0.6038
Manitoba	-0.8341	0.5353	-0.8341	0.5276	-0.8341	0.5353	-0.8341	0.5353
New Brunswick	1.0277	0.6496	1.0276	0.6244	1.0277	0.6496	1.0277	0.6496
Newfoundland & Labrador	-0.4101	0.6474	-0.4101	0.6380	-0.4101	0.6474	-0.4101	0.6474
Nova Scotia	1.2935	0.6875	1.2935	0.6480	1.2935	0.6875	1.2935	0.6875
Ontario	0.6564	0.5061	0.6564	0.4611	0.6564	0.5061	0.6564	0.5061
Prince Edward Island	-0.0906	0.7565	-0.0906	0.7024	-0.0906	0.7565	-0.0906	0.7565
Quebec	0.0069	0.4952	0.0069	0.4659	0.0069	0.4952	0.0069	0.4952
Saskatchewan	-0.6506	0.5255	-0.6506	0.5242	-0.6506	0.5255	-0.6506	0.5255
(Intercepts)
Strongly Agree\|Agree	-4.0770	0.6693	-4.0770	0.6954	-4.0770	0.6693	-4.0770	0.6693
Agree\|Disagree	-2.9143	0.6536	-2.9144	0.6731	-2.9143	0.6536	-2.9143	0.6536
Disagree\|Strongly Disagree	-1.2303	0.6951	-1.2304	0.7207	-1.2303	0.6951	-1.2303	0.6951