Entering sum of coefficients hypothesis test in a regression table

[Chinmay Sharma]

Hi All,

I have data that resembles the following:

* Example generated by -dataex-. To install: ssc install dataex
clear
input float(y x time)
213 321  1
 23   3  2
  2   2  3
  2   1  4
  1   2  5
  3   3  6
  1   2  7
  2   3  8
  3   1  9
  2   2 10
end

Here, I have data for y and x, by year. I first declare the data as time series using the -tsset- command. Thereafter, I run a simple regression as follows:

regress y x L.x

I normally export the regression to LaTex using the -esttab- class of commands as follows

esttab using "table1.tex", scalar(F) varwidth(25) keep(x L.x ) star(+ 0.15 * 0.10 ** 0.05 *** 0.01) p  label replace

What I wish to do now is to include an additional row (without typing out the results by hand in Latex), that performs a simple hypothesis test of the null:

H0: beta1+beta2=0
HA: not H0

I could implement this on Stata quite simply as:

test x= -L.x

However, instead of just providing the p-value of this test statistic, I would like the sum of the coefficients along with the standard error of the sum displayed as well. Is there a simple way to do this?

Many thanks,
CS

[Dimitriy V. Masterov]

I think you can modify this example easily:

https://www.statalist.org/forums/for...cance-stars-to lincom-in-esttab?p=1466698#post1466698

[Chinmay Sharma]

Awesome, Dimitriy V. Masterov . Very helpful.