Hello, I am trying to estimate the number of correct predictions in a linear model using robust and a linear model with wls. My instructor showed doing this regress diab owgt obese exer cig alc inc coll marr male age, robust
predict probl, xb
generate cdiab=(probl >=0.5 & diab==1)
generate cnodiab=(probl <0.5 & diab==0)
generate correct =(cdiab==1 | cnodiab==1)
sum diab cdiab cnodiab correct
but is this specific for either model? And it only prints out this:
Variable | Obs Mean Std. Dev. Min Max
-------------+---------------------------------------------------------
diab | 5,051 .1282914 .3344471 0 1
cdiab | 5,051 0 0 0 0
cnodiab | 5,051 .8717086 .3344471 0 1
correct | 5,051 .8717086 .3344471 0 1
It does not include a table that shows the predictions as the instructor said it would. Can anyone tell me if the information I need is hidden in here or if I did something wrong?
Thank you
Related Posts with percent of correct predictions
Carryforward/backwardDear all, I have this panel data (I'm giving the example only about one company) Code: * Example …
Robust command for logit - Stata 16Hi, I tried the command roblogit for robust check in logit regression, but it is not recognized. Whi…
Examining Pearson´s CorrelationHi, I am doing an investigation on Pearson´s Correlation Coefficient. I would like to present the f…
Attrition tableHi, I'm working with panel data and would like to compute attrition rates. However, as you can see …
Total factor productivity using micro-level cross-sectional datasetDear STATA community, I want to generate following TFP series using STATA for a cross-sectional dat…
Subscribe to:
Post Comments (Atom)
0 Response to percent of correct predictions
Post a Comment