Droping observations with x amount of missing values

[Andreas Head]

Dear all,
I'm working with a messy data set with approximately 870 observations at the moment.
After using the command missings table, I realised that 91 observations have 99 missing values out of 108 variables. I used missings list, min(99) to see which observations
account for this.
Now, I want to drop these observations from the data set. I wonder if there is a command that would use the information produced by missings list, min(99) to drop these observations?
Can anyone help? I've been looking for a solution for quite some time, without success.

Thank you.

[Clyde Schechter]

There is no -missings list- command in official Stata. Presumably this is some user-written command you have found somewhere. Without knowing where it comes from, it isn't possible to say much about it.

Nevertheless, if your plan is to drop observations that have 99 missing values, you can do that this way:

egen mcount = rowmiss(_all)
drop if mcount == 99

[Andreas Head]

Thank you Clyde, I should have mentioned that the -missings- command is a user written one available from SSC.

Also, thank you for your suggestion, which does the job!

[Nick Cox]

Not quite. missings is (please) to be cited as published in the Stata Journal.


dm0085_1 from http://www.stata-journal.com/software/sj17-3
SJ17-3 dm0085_1. Update: A set of utilities for managing missing values /
Update: A set of utilities for managing missing / values / by Nicholas J.
Cox, Department of Geography, / Durham University, Durham City, UK /
Support: [email protected] / After installation, type help missings

dm0085 from http://www.stata-journal.com/software/sj15-4
SJ15-4 dm0085. A set of utilities for... / A set of utilities for managing
missing values / by Nicholas J. Cox, Department of Geography, / Durham
University, Durham City, UK / Support: [email protected] / After
installation, type help missings


The help is forthright:

there is no explicit support here for dropping observations or variables with some missing and
some nonmissing values. Users so minded will find other subcommands of use as an intermediate step, but
multiple imputation might be a better way forward.

So, users must make up their own minds about throwing away data, and Clyde Schechter showed you how to do your dirty deed.