Collectives™ on Stack Overflow

Find centralized, trusted content and collaborate around the technologies you use most.

Teams

Q&A for work

Connect and share knowledge within a single location that is structured and easy to search.

I am attempting to fit a regression model in Stata. My variables are are all continuous variables of type float.

regress _gdp all_indexn_c 90_days consistent _incpc all_indexn_c#90_days
all_indexn_c:  factor variables may not contain noninteger values
r(452);
How do I fix this issue? I don't have factor variables and I'd like to use float variables in the model.
                Cross-posted at statalist.org/forums/forum/general-stata-discussion/general/… It's always courteous to tell people about cross-posting.
– Nick Cox
                Sep 27, 2021 at 8:21
The problem arises because you're asking for an interaction term and if you do that Stata requires you to flag that a variable with non-integer values is continuous. See for example help fvvarlist.
Running this reproducible example shows a similar problem and its fix.
sysuse auto, clear
regress price mpg headroom mpg#headroom
regress price mpg headroom mpg#c.headroom
P.S. Regressions with GDP pc as outcome usually work better on a logarithmic scale.
        
Thanks for contributing an answer to Stack Overflow!
Please be sure to answer the question. Provide details and share your research!
But avoid …
Asking for help, clarification, or responding to other answers.
Making statements based on opinion; back them up with references or personal experience.
To learn more, see our tips on writing great answers.