[Matty Cleary]

Clyde,

Those are great points, thank you. I'm going to meet with the person who collected the data and inquire about reasons why there are so many missing entries. If the missingness is truly random the I'll look into multiple imputation. Thank you for your help!

[Clyde Schechter]

And I am able to run a regression using variables with a similar amount of missing values. I unfortunately don't have a good enough handle on how STATA thinks to understand why these variables (Vo1 - Vo10) don't function in a model when the sociodemographic variables that I also fixed using real(x) do work. Thank you all again for your help!

For the third time, Stata (and every statistical package) omits from the estimation every observation for which any of the variables mentioned in the regression command has a missing value. So while Vo1 may be the variable with the most missing data,* you still have to worry about the other variables as well. In the example data you showed earlier, every single observation had missing values for at least one of the regression variables. And I am confident this is true of your full data set as well. The more variables you include in the model, the more opportunities an observation has to be thrown out for missing data on some variable.

*I say this based on your assertion in #12, although in your example data, Vo1 is the variable with the least amount of missing data--the other variables are much worse! But perhaps your example is unrepresentative of the full data in this respect.

[Chifundo Luwayo]

Dear all,
I am using Stata 15 on windows 10. Whenever I ran a regression, Stata shows no observation error. I have tried to check in all my seven variables for missing observations using codebook. I have realised that some observations have been dropped. For examples, variables like SEXChild and edu_head, their observations are missing. I need help on how i can fix these problem.

Looking forward for your timely assistance.