Dear Statalist,
I've recently started using coefplot command and like it's versatility, but I cannot work out how to use the keep command as a model option rather than a global option (as it seems you can from the help file (http://repec.sowi.unibe.ch/stata/coe...help-file.html).
Specifically I would like to create a graph with 5 different models: each contains an identical list of individual level variables (model 1), and model 2-5 adds one country level variable each. If I show all of the models at once the individual level coefficients (which are pretty much the same - i.e. adds very little info) fall on top of each other and it looks cluttered. Instead I would like to include them in model 1 and exclude them from model 2-5, where I would like to only show the country level coefficients. I have tried the following command:
coefplot (M1, label(Model 1)) (M2, label(Model 2), keep(zGini)) (M3, label (Model 3), keep (zGDPrev)) (M4, label (Model 4), keep (zWGIrev)) (M5, label (Model 5), keep (zMIPEXrev)) ///
drop(_cons) xline(0)
However, this does not work, and I get the error message
invalid 'keep'
r(198);
What am I doing wrong, and does anyone know a way to do this? Hope you can help,
Ingrid
Related Posts with Coefplot: keep / drop coefficients from one model, not the whole plot
Issues running ranksum - says "no observations found"I'm relatively new to Stata so I am hoping that this error is a quick fix. I've been trying to run …
Poisson regression without specifying exit variableI am conducting an analysis using a longitudinal dataset from an ongoing cohort that spans over 5.5 …
Non-linear regression with industry and year FEDear colleagues, Greetings! I have been searching different forums for the past weeks, but the mor…
Coding_column_rowDear statalist community, I am in need to do the following exercise for my research, can anyone plea…
Dropping specific addresses beginning with '#' or '$'Hello, I am trying to clean up a large dataset of addresses, where there are several different versi…
Subscribe to:
Post Comments (Atom)
0 Response to Coefplot: keep / drop coefficients from one model, not the whole plot
Post a Comment