Hello,

I have calculated four models and summarized them in a table. I am using the following programming to generate the results:

clear
use http://www.stata-press.com/data/r7/emd.dta
egen employment = seq(), f(0) t(1)

eststo m1: probit employment jantemp ln_eat income_pc

predict p_employment1
predict arg_lambda1, xb
gen lambda1=normalden(arg_lambda1) / normal(arg_lambda1)
label var lambda1 "Inverse Mills Ratio"

eststo m2: probit employment fips ln_eat median_age ln_rsales_pc

predict p_employment2
predict arg_lambda2, xb
gen lambda2=normalden(arg_lambda2) / normal(arg_lambda2)
label var lambda2 "Inverse Mills Ratio"

eststo m3: reg ln_rsales_pc jantemp fips median_age lambda1
eststo m4: reg ln_income jantemp ln_eat precipitation median_age lambda2

esttab m1 m2 m3 m4, se ar2 nostar brackets label title(This is a regression table) nonumbers mtitles("Model A" "Model B" "Model C" "Model D") ///
keep( ln_eat ln_rsales_pc jantemp lambda1 lambda2 _cons)


The output table is as follows:
Model A Model B Model C Model D
main
Median January tem~r 0.00227 0.0133 -0.00148
[0.00316] [0.000954] [0.000524]
ln(Dining sales pe~) -0.112 -0.311 0.136
[0.0997] [0.156] [0.0251]
ln(retail sales pe~) 0.182
[0.163]
Inverse Mills Ratio 8.494
[0.291]
Inverse Mills Ratio -0.700
[0.175]
Constant -0.0988 -0.116 -5.636 8.968
[0.248] [0.474] [0.243] [0.130]
Observations 845 815 766 703
Adjusted R-squared 0.532 0.344
Standard errors in brackets

The variable lambda1 and lamdda2 have the same label "Inverse Mills Ratio." that comes from the calculation of model A and model B and their values are different.But for the purposes of presenting the table, I would like to know if it is possible that a same row y with a single label "Inverse Mills Ratio" shows the coefficients of models C and D. The table would look something like this:

This is a regression table
Model A Model B Model C Model D
main
Median January tem~r 0.00227 0.0133 -0.00148
[0.00316] [0.000954] [0.000524]
ln(Dining sales pe~) -0.112 -0.311 0.136
[0.0997] [0.156] [0.0251]
ln(retail sales pe~) 0.182
[0.163]
Inverse Mills Ratio 8.494 -0.700
[0.291] [0.175]
Constant -0.0988 -0.116 -5.636 8.968
[0.248] [0.474] [0.243] [0.130]
Observations 845 815 766 703
Adjusted R-squared 0.532 0.344
Standard errors in brackets
Thanks for your helping.