Proportions in stata between 4 groups

[Ameer Muhammad]

Hello All,

I am trying to calculate proportions along with their difference, P value and CI's between 4 groups. I am not sure how to calculate, i tried to use table1_mc which given me pairwise comparison but between 3 groups not 4and no CI and differences. can any one suggest me how to do that in stata? or any one share syntax or any packages with codes.

[Clyde Schechter]

You do not provide enough information here to get a useful answer. Please show example data, using the -dataex- command. Then explain what proportions you need to calculate and which differences among them, and what are the four groups.

If you are running version 17, 16 or a fully updated version 15.1 or 14.2, -dataex- is already part of your official Stata installation. If not, run -ssc install dataex- to get it. Either way, run -help dataex- to read the simple instructions for using it. -dataex- will save you time; it is easier and quicker than typing out tables. It includes complete information about aspects of the data that are often critical to answering your question but cannot be seen from tabular displays or screenshots. It also makes it possible for those who want to help you to create a faithful representation of your example to try out their code, which in turn makes it more likely that their answer will actually work in your data.

[Ameer Muhammad]

Thank you for your reply, I am analyzing one of the randomized controlled trial data which include 4 arms and wanted to see impact of intervention on stillbirths (coded as 0 and 1) . So i wanted to analyze the data, and need to compare proportion of stillbirths in each arm.

[Clyde Schechter]

tab stillbirth arm, col chi2

will give you the numbers and percentages of stillbirths in each arm, as well as a chi square test of the null hypothesis that all four arms have equal probabilities of stillbirth.

Another approach that will give you differences in probabilities and confidence intervals around those would be:

logit stillbirth i.arm
margins arm, pwcompare

[Ameer Muhammad]

tab stillbirth arm, col chi2

will give you the numbers and percentages of stillbirths in each arm, as well as a chi square test of the null hypothesis that all four arms have equal probabilities of stillbirth.

Another approach that will give you differences in probabilities and confidence intervals around those would be:

logit stillbirth i.arm
margins arm, pwcompare

Thank you so much i worked perfectly fine. One thing is bothering me, why my odds ratios are in minus after regression? Can you comment on that please?

[Rich Goldstein]

those are not odds ratios - the -logit- command leaves coefficients in log odds form by default; see the help file; on the other hand, the -logistic- command produces odds ratios by default

[Maarten Buis]

Because they are not odds ratios, but log odds ratios. To see the odds ratios you need to add the or option to the logit command.

[Ameer Muhammad]

Yeah i got thank you Maarten Buis and Rich Goldstein

[Bruce Weaver]

And if you want to see both the coefficients and the corresponding odds ratios, you can "replay" the -logit- command with the or and noheader options added.

logit stillbirth i.arm
// Replay the -logit- command with the or and noheader options
logit, or noheader