Hello everybody,
I tried to use contrast in order to see if I should use some categorical variables after my regression. I have never used this command before so please let me know if my interpretation of the use of the command is wrong per se.
So I type my regression like:
xtreg yvar xvars i.year year#country year#industry, fe vce(cluster ID)
contrast year#country
contrast year#industry
and get an almost empty table apart from: year#country not testable and denominator = 2708.
What am I doing wrong?
Related Posts with contrast doesn't work
Model Validation Using StataHi all, I have a question about how to do model validation using Stata. I used a training dataset …
Differences in correlation coefficients produced by corr and regFor certain variables, corr and reg produce different correlation coefficients that cannot be explai…
eventstudy2: why my command neglects results of Mondays?Hello everyone I am using the powerful command, eventstudy2 (Thomas Kaspereit, 2020) for a global e…
Finding the totals of string variablesHi everyone, I have this dataset that i need to calculate the totals for each program. So, for exam…
Two-way graph for panel dataDear, I want to plot a variable in panel data. Below is an example of my data. Code: year provinc…
Subscribe to:
Post Comments (Atom)
0 Response to contrast doesn't work
Post a Comment