svy: logit goodness-of-fit tests (subpopulation)

[Andrea Becerra]

Hi, how can I use stat gof if I need to keep subpop to keep the correct estimation of variances and covariances? Is there any other way to estimate the model's goodness of fit in these cases other than svylogitgof?

My model:

svy, subpop(if NEDU1!=. & hostility!=.): logit s_b_mb i.confi sex1 Age i.NEDU non_hostile i.confi#i.NEDU, or
Survey: Logistic Regression

Number of strata = 30 Number of obs = 6,233
Number of PSUs = 1,077 Population size = 14,518,969 Subpop
. no. obs = 6,076
Subpopulation. size = 14,276,008
Design df = 1.047
F(11, 1037) = 22.15
Odds > F = 0.0000


The error:

stat gof
gof stat is not allowed after subpopulation estimates
r(198);

Stata 14.

Greetings,

[David Radwin]

It's not quite the same approach, but you might consider this: Herron, M. C. (1999). Postestimation uncertainty in limited dependent variable models. Political analysis, 8(1), 83-98.