Binary dependent and independent variable: logit result is blank

[Sanjana Mon]

Hello. The dependent variable has binary values along with the independent variables except for control variables such as age and age squared. In this form, what type of regression should I use?

When I used the "regress" command, the coefficients came out neatly, however, when I used "logit" since that is what's supposed to be used with binary values, the result shows collinearity issues and coefficient table is filled with dots.

What should I do in such a situation?

[Carlo Lazzaro]

Sanjana:
welcome to this forum.
As per FAQ, please post what you typed and what Stata gave you back. Thanks.
That said, did Stata thrwo something like -predictor predicts outcome perfectly. # observations were not used- when yoiu ran -logit-?

[Sanjana Mon]

Thank you. I did a few changes in the variables I used. The regression relation I want to find out is the correlation between female decision maker (agricultural decision making of household) and the stunting of children logit stunted
under 5 yrs. I used mother's education as a control variable however I separated the dummies between primary, secondary and tertiary level. I corrected the regression and only used primary education and omitted few of the variables that I think are causing collinearity problem and found the final result:

**I am still working in cleaning the dataset for my thesis however I thought of running a rough regression to check if the relationship is significant or not**

[Carlo Lazzaro]

Sanjana:
1) your pseudo R2 is a bit low;
2) is age2=age1^2. If this is the case, go -c.age##c.age- exploting the wonderful capabilities of -fvvarlist- notation;
3) please note that most of your predictors do not seem to explain variations in the regressand (when adjusted for the remaining predictors);

[Sanjana Mon]

Thank you for the feedback. I should probably check the predictors again and then go back to the regression.