## Stata 15 help for svy postestimation

```
[SVY] svy postestimation -- Postestimation tools for svy

Postestimation commands

The following postestimation commands are available after svy:

Command        Description
-------------------------------------------------------------------------
contrast       contrasts and ANOVA-style joint tests of estimates
estat (svy)    postestimation statistics for survey data
lincom         point estimates, standard errors, testing, and inference
for linear combinations of coefficients
margins        marginal means, predictive margins, marginal effects, and
average marginal effects
marginsplot    graph the results from margins (profile plots, interaction
plots, etc.)
nlcom          point estimates, standard errors, testing, and inference
for nonlinear combinations of coefficients
predict        predictions, residuals, influence statistics, and other
diagnostic measures
predictnl      point estimates, standard errors, testing, and inference
for generalized predictions
pwcompare      pairwise comparisons of estimates
suest          seemingly unrelated estimation
test           Wald tests of simple and composite linear hypotheses
testnl         Wald tests of nonlinear hypotheses
-------------------------------------------------------------------------

predict after svy

The syntax of predict (and even if predict is allowed) after svy depends
on the command used with svy.  Specifically, predict is not allowed after
svy: mean, svy: proportion, svy: ratio, svy: tabulate, or svy: total.

margins after svy

The syntax of margins (and even if margins is allowed) after svy depends
on the command used with svy.  Specifically, margins is not allowed after
svy: mean, svy: proportion, svy: ratio, svy: tabulate, or svy: total.

Example 1: Linear and nonlinear combinations

. webuse nhanes2
. generate male = (sex == 1)
. svy, subpop(male): mean zinc, over(race)
. lincom [zinc]White - [zinc]Black

. webuse nhanes2d, clear
. svy: logistic highbp height weight age age2 female
. nlcom peak: -_b[age]/(2*_b[age2])
. testnl -_b[age]/(2*_b[age2]) = 70

Example 3: Predictive margins

. webuse nhanes2d
. svyset
. svy: logistic highbp height weight age c.age#c.age i.female i.race,
baselevels
. margins race, vce(unconditional)
. margins, vce(unconditional) dydx(race)
. margins, vce(unconditional) dydx(race) over(region)

Example 4: Nonlinear predictions and their standard errors

. webuse nhanes2d
. svy: regress loglead age age2 i.female i.race i.region

Example 5: Multiple-hypothesis testing

. test 2.region 3.region 4.region
. test 2.region 3.region 4.region, nosvyadjust
. test 2.region 3.region 4.region, mtest(bonferroni)

Example 6: Using suest with survey data

. webuse nhanes2f, clear
. svyset psuid [pw=finalwgt], strata(stratid)
. svy: ologit health female black age age2
. estimates store H5
. gen health3 = clip(health, 2, 4)
. svy: ologit health3 female black age age2
. estimates store H3
. suest H5 H3
. test [H5_health=H3_health3]
. test (/H5:cut2=/H3:cut1) (/H5:cut3=/H3:cut2)

```