这个问题与另一个问题有关，我问CrossValidated：
我正在Stata中运行多个逻辑模型，并希望使用margins存储模型的结果和一些后估计。使用ado estout有两种相对简单的可能性（参见documentation）。但是，两者都缺少z统计或某些摘要统计。这是一个例子：
. webuse acmemanuf, clear
. // estadd
. eststo est1: qui logit acceptable i.temp y
. qui estadd margins, dydx(*)
. eststo est2: qui logit acceptable i.temp y i.pressure
. qui estadd margins, dydx(*)
. // margins, post
. qui logit acceptable i.temp y, nolog
. eststo est3: qui margins, dydx(*) post
. qui logit acceptable i.temp y i.pressure, nolog
. eststo est4: qui margins, dydx(*) post
. // Wrong t-statistics using "estadd"
. esttab est1 est2, cells("margins_b t") margin pr2 aic
----------------------------------------------------------------
(1) (2)
acceptable acceptable
margins_b t margins_b t
----------------------------------------------------------------
acceptable
1.temp 0 . 0 .
2.temp .122275 .8468373 .2366358 1.448193
3.temp .1028261 .6194538 .0930619 .6025044
y .0171374 2.752288 .0202188 2.993524
1.pressure 0 .
2.pressure -.2384807 -1.454117
----------------------------------------------------------------
N 49 49
pseudo R-sq 0.233 0.271
AIC 55.48 55.10
----------------------------------------------------------------
Marginal effects
. // Loosing summary statistics using "margins, post"
. esttab est3 est4, cells("b t") margin pr2 aic
----------------------------------------------------------------
(1) (2)
b t b t
----------------------------------------------------------------
1.temp 0 . 0 .
2.temp .122275 .8600932 .2366358 1.723335
3.temp .1028261 .6322357 .0930619 .6126009
y .0171374 4.103384 .0202188 5.118546
1.pressure 0 .
2.pressure -.2384807 -1.729937
----------------------------------------------------------------
N 49 49
pseudo R-sq
AIC . .
----------------------------------------------------------------
Marginal effects
我想有一个表格，显示第一个表格中的汇总统计数据和上面示例第二个表格中的z统计数据。
修改
我写了一个小型本地程序来完成这项工作，其结果可以由esttab捕获。请注意，对于生成t统计信息而不是z统计信息的模型，必须稍微修改程序代码。如果有人可以将estadd中的程序集成到webuse acmemanuf, clear
program define margzp
tempname rtab
tempname tmargins_z
tempname tmargins_p
mat `rtab' = r(table)
mat `tmargins_z' = `rtab'["z", 1..(colsof(`rtab')-1)]
mat `tmargins_p' = `rtab'["pvalue", 1..(colsof(`rtab')-1)]
estadd matrix margins_z = `tmargins_z'
estadd matrix margins_p = `tmargins_p'
end
eststo: logit acceptable i.temp y
estadd margins, dydx(*)
margzp *
eststo: logit acceptable i.temp y i.pressure
estadd margins, dydx(*)
margzp *
esttab, cells((margins_b(fmt(3) star pvalue(margins_p)) ///
margins_z)) pr2 aic bic star(+ 0.10 * 0.05 ** 0.01 *** 0.001) ///
postfoot(`"{hline @width}"' ///
`"Marginal effects, standard errors in parentheses"' `"@starlegend"') ///
的子例程中，我很想听到它，因为我只是成功地添加了线性回归模型的结果。这是我的文件：
----------------------------------------------------------------------
(1) (2)
acceptable acceptable
margins_b margins_z margins_b margins_z
----------------------------------------------------------------------
acceptable
1.temp 0.000 . 0.000 .
2.temp 0.122 0.847 0.237 1.448
3.temp 0.103 0.619 0.093 0.603
y 0.017** 2.752 0.020** 2.994
1.pressure 0.000 .
2.pressure -0.238 -1.454
----------------------------------------------------------------------
N 49 49
pseudo R-sq 0.233 0.271
AIC 55.48 55.10
BIC 63.05 64.56
----------------------------------------------------------------------
Marginal effects, standard errors in parentheses
+ p<0.10 * p<0.05, ** p<0.01, *** p<0.001
其中给出了下表：
{{1}}
答案 0 :(得分：1)
这是一个例子。我并非100％确定我合并了你想要的一切。如果没有，请添加您希望表格显示的示例：
. sysuse auto
(1978 Automobile Data)
. eststo, title(Index): logit foreign price mpg
Iteration 0: log likelihood = -45.03321
Iteration 1: log likelihood = -36.627434
Iteration 2: log likelihood = -36.462562
Iteration 3: log likelihood = -36.46219
Iteration 4: log likelihood = -36.462189
Logistic regression Number of obs = 74
LR chi2(2) = 17.14
Prob > chi2 = 0.0002
Log likelihood = -36.462189 Pseudo R2 = 0.1903
------------------------------------------------------------------------------
foreign | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
price | .000266 .0001166 2.28 0.022 .0000375 .0004945
mpg | .2338353 .0671449 3.48 0.000 .1022338 .3654368
_cons | -7.648111 2.043673 -3.74 0.000 -11.65364 -3.642586
------------------------------------------------------------------------------
(est1 stored)
. eststo, title(AMEs): margins, dydx(*) post
Average marginal effects Number of obs = 74
Model VCE : OIM
Expression : Pr(foreign), predict()
dy/dx w.r.t. : price mpg
------------------------------------------------------------------------------
| Delta-method
| dy/dx Std. Err. z P>|z| [95% Conf. Interval]
-------------+----------------------------------------------------------------
price | .0000428 .0000166 2.57 0.010 .0000102 .0000754
mpg | .0376126 .0074022 5.08 0.000 .0231045 .0521207
------------------------------------------------------------------------------
(est2 stored)
. esttab, drop(_cons)
--------------------------------------------
(1) (2)
foreign
--------------------------------------------
main
price 0.000266* 0.0000428*
(2.28) (2.57)
mpg 0.234*** 0.0376***
(3.48) (5.08)
--------------------------------------------
N 74 74
--------------------------------------------
t statistics in parentheses
* p<0.05, ** p<0.01, *** p<0.001