## Stata 15 help for tpoisson_postestimation

```
[R] tpoisson postestimation -- Postestimation tools for tpoisson

Postestimation commands

The following postestimation commands are available after tpoisson:

Command          Description
-------------------------------------------------------------------------
contrast         contrasts and ANOVA-style joint tests of estimates
estat ic         Akaike's and Schwarz's Bayesian information criteria
(AIC and BIC)
estat summarize  summary statistics for the estimation sample
estat vce        variance-covariance matrix of the estimators (VCE)
estat (svy)      postestimation statistics for survey data
* forecast         dynamic forecasts and simulations
* hausman          Hausman's specification test
lincom           point estimates, standard errors, testing, and
inference for linear combinations of coefficients
* lrtest           likelihood-ratio test
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
-------------------------------------------------------------------------
* forecast, hausman, and lrtest are not appropriate with svy estimation
results.

Syntax for predict

predict [type] newvar [if] [in] [, statistic nooffset]

statistic          Description
-------------------------------------------------------------------------
Main
n                number of events; the default
ir               incidence rate
cm               conditional mean, E(y | ll < y < ul)
pr(n)            probability Pr(y = n)
pr(a,b)          probability Pr(a < y < b)
cpr(n)           conditional probability Pr(y = n | ll < y < ul)
cpr(a,b)         conditional probability Pr(a < y < b | ll < y < ul)
xb               linear prediction
stdp             standard error of the linear prediction
score            first derivative of the log likelihood with respect to
xb
-------------------------------------------------------------------------
These statistics are available both in and out of sample; type predict
... if e(sample) ... if wanted only for the estimation sample.

Statistics > Postestimation

Description for predict

predict creates a new variable containing predictions such as numbers of
events, incidence rates, conditional means, probabilities, conditional
probabilities, linear predictions, standard errors, and equation-level
scores.

Options for predict

+------+
----+ Main +-------------------------------------------------------------

n, the default, calculates the predicted number of events, which is
exp(xb) if neither offset() nor exposure() was specified when the
model was fit; exp(xb + offset) if offset() was specified; or
exp(xb) x exposure if exposure() was specified.

ir calculates the incidence rate exp(xb), which is the predicted number
of events when exposure is 1.  This is equivalent to specifying both
the n and the nooffset options.

cm calculates the conditional mean, E(y|ll < y < ul), where ll is the
left-truncation point specified at estimation and ul is the
right-truncation point specified at estimation.

pr(n) calculates the probability Pr(y = n), where n is a nonnegative
integer that may be specified as a number or a variable.

pr(a,b) calculates the probability Pr(a < y < b), where a and b are
nonnegative integers that may be specified as numbers or variables;

b missing (b > .) means plus infinity;
pr(20,.) calculates Pr(y > 20);
pr(20,b) calculates Pr(y > 20) in observations for which b > .
and calculates Pr(20 < y < b) elsewhere.

pr(.,b) produces a syntax error.  A missing value in an observation
of the variable a causes a missing value in that observation for
pr(a,b).

cpr(n) calculates the conditional probability Pr(y = n|ll < y < ul),
where n is a nonnegative integer that may be specified as a number or
a variable.  ll and ul are as defined in cm.

cpr(a,b) calculates the conditional probability Pr(a < y < b | ll < y <
ul), where a and b are as defined in {opt pr(a,b)} with the
additional restrictions that a > ll and b < ul.  ll and ul are as
defined in cm.

xb calculates the linear prediction, which is xb if neither offset() nor
exposure() was specified when the model was fit; xb + offset if
offset() was specified; or xb + ln(exposure) if exposure() was
specified; see nooffset below.

stdp calculates the standard error of the linear prediction.

score calculates the equation-level score, the derivative of the log
likelihood with respect to the linear prediction.

nooffset is relevant only if you specified offset() or exposure() when
you fit the model.  It modifies the calculations made by predict so
that they ignore the offset or exposure variable; the linear
prediction is treated as xb rather than as xb + offset or
xb + ln(exposure).  Specifying predict ..., nooffset is equivalent to
specifying predict ..., ir.

Syntax for margins

margins [marginlist] [, options]

margins [marginlist] , predict(statistic ...) [predict(statistic ...)
...] [options]

statistic          Description
-------------------------------------------------------------------------
n                  number of events; the default
ir                 incidence rate
cm                 conditional mean, E(y | ll < y < ul)
pr(n)              probability Pr(y = n)
pr(a,b)            probability Pr(a < y < b)
cpr(n)             conditional probability Pr(y = n | ll < y < ul)
cpr(a,b)           conditional probability Pr(a < y < b | ll < y < ul)
xb                 linear prediction
stdp               not allowed with margins
score              not allowed with margins
-------------------------------------------------------------------------

Statistics not allowed with margins are functions of stochastic
quantities other than e(b).

For the full syntax, see [R] margins.

Statistics > Postestimation

Description for margins

margins estimates margins of response for numbers of events, incidence
rates, conditional means, probabilities, conditional probabilities, and
linear predictions.

Examples

Setup
. webuse runshoes
. replace shoes = . if shoes<4

Fit truncated Poisson regression
. tpoisson shoes distance male age, ll(3)

Predict the number of pairs of shoes purchased
. predict shoehat, n

Predict the number of shoes purchased, conditional on each person having
bought more than 3 pairs of shoes
. predict shoecondhat, cm

Predict the probability each person has 1-3 pairs of shoes
. predict p, pr(1,3)

Predict the probability each person has 6 or more pairs of shoes given
that they have more than 3 pairs of shoes
. predict p2, cpr(6,.)

```