I agree with Thorsten's diagnosis.
I've added the scope for specifying valid percents,
cumulative valid percents, and reverse cumulative
valid percents to my program -groups-. Here -- as
someone who doesn't use SPSS and isn't even clear
what it is -- I have interpreted "valid" to mean "non-missing".
This will be available in due course from SSC once
I've changed the .hlp and sent the revised files
to Kit Baum, who as announced is away from base.
Meanwhile, -groups- can mimic -tabulate <varname>-
and round percents to 1 d.p.
Use -ssc- to install -groups-.
Nick
[email protected]
Thorsten Faas <[email protected]>
> In the meantime: Here is a short list of some SPSS commands,
> together with their Stata counterpart. -tab1- corresponds exactly
> to SPSS' FREQUENCIES command.
I think that's not quite true.
FRE in SPSS procudes something like this:
Value | Label | Freq | Percent | Valid Percent | Cumulative Percent
with the difference between percent and valid percent being that one
includes missing values when calculating percentages, the other does not.
"tab1 var" in Stata produces
Value | Label | Freq | Valid Percent | Cumulative Percent
i.e. the percentages including missing values are omitted.
"tab1 var, m" produces a table without the valid percentages.
I think Sebastian's suggestions do not solve the problem either; however
I don't have one either, but would be very much interested in learning
about one, too, as I find it quite useful to have both columns that SPSS
produces in one stata table.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
