variables generate with expand are not unique to duplicated observations

[Kim Gra]

Hello everyone,

I'm working on my thesis using Stata 16, I've been using it a bit in the past but I'm not too well versed in stata.

I wanted to duplicate some of my observations using the expand command and added a new variable using the ,generate(newvar) at the end of the command. I did this twice for different variables but some of the newly generated observations have an entry in both new variables and I don't understand why. Could someone offer insight?

Here is my code:


expand 2 if ReceiverRegimeTypeII == "1" | ReceiverRegimeTypeII == "2"| ReceiverRegimeTypeII == "3", generate (obs)
(70 observations created)

.
. expand 2 if ReceiverRegimeTypeIII == "1" | ReceiverRegimeTypeIII == "2"| ReceiverRegimeTypeIII == "3", generate (obs1)
(62 observations created)



. tab obs obs1

| obs1
obs | 0 1 | Total
-----------+----------------------+----------
0 | 504 32 | 536
1 | 70 30 | 100
-----------+----------------------+----------
Total | 574 62 | 636



So specifically I'm asking why do 30 observations have both 1s in obs and obs1?

Thanks in advance!!

[Kim Gra]

The moment I posted the post I figured it out! So I'm fine

I'll just figure out how to delete the post !

[Nick Cox]

You can't delete the post. This is explained. https://www.statalist.org/forums/help#closure

The main point about a forum like this is that questions and answers should interest other people. So, just as you asked it, other people may have the same question and be interested in your answer.

in #1, there is scope for (e.g.)

inlist(ReceiverRegimeTypeII, "1", "2", "3")