Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.
| From | Nick Cox <njcoxstata@gmail.com> |
| To | statalist@hsphsun2.harvard.edu |
| Subject | Re: st: Summarize data |
| Date | Sat, 9 Jun 2012 14:09:50 +0100 |
If I understand what you want correctly, the key is that the mean of the row means is the table mean. So, summarize row_mean On Stata not STATA, see http://www.stata.com/support/faqs/res/statalist.html#spell Nick On Sat, Jun 9, 2012 at 1:43 PM, Patricia Biedermann <pati.stat@gmail.com> wrote: > Oh! I got the mistake! Sorry for that! But still one question remains! > So far I have the mean of the rows... > >> egen row_mean = rowmean(Q1A Q2A Q3) >> list Q1A Q2A Q3A row_mean > > Is there a possibility to receive ONE MEAN of several columns(=variables) ? > > Thank you > > On Sat, Jun 9, 2012 at 1:23 PM, Patricia Biedermann <pati.stat@gmail.com> wrote: >> Hello! >> Thank you for your answer! >> >> I tried this command: >> >> egen row_mean = rowmean(Q1A Q2A Q3) >> list Q1A Q2A Q3A >> >> but I just get a table and I need actual values. and how do I sort it >> by groups? (if group==1 ????) >> >> Sorry, I'm still quite new to STATA but I'm glad for any help! >> >> Thank you. >> >> On Fri, Jun 8, 2012 at 8:30 PM, Nick Cox <njcoxstata@gmail.com> wrote: >>> -egen- offers a bundle of functions (in its own sense) for summarising >>> rowwise. You can apply -if- and/or -in-. >>> >>> Nick >>> >>> On Fri, Jun 8, 2012 at 5:46 PM, Patricia Biedermann <pati.stat@gmail.com> wrote: >>> >>>> I need to summarize data in the following way: >>>> >>>> My questionnaire looks like that: >>>> >>>> Question 1 option1 option2 option3 (options >>>> are numeric 1-5) >>>> >>>> Question 2 >>>> >>>> Question 3 >>>> >>>> Etc. (up to 16 question in the same structure) >>>> >>>> The database in Stata looks like that: >>>> >>>> ID Q1A Q1B Q1C Q2A Q2B Q3B …ETC (GROUP) >>>> >>>> Respectively option1 of question 1 represents Q1A >>> >>>> Now I want to summarize the data of all questionnaires in that way: >>>> >>>> - summarize (mean) option 1 for ALL QUESTIONS AND ALL >>>> questionnaires (mean of Q1A, Q2A, Q3A,...etc) >>>> >>>> - summarize (mean) option 2 etc…(mean of Q1B, Q2B, Q3B,...etc) >>>> >>>> So, maybe the solution is simpler then I think or my database is >>>> crap…but can anyone help me to figure out the right commands? (I >>>> already tried sum and collapse commands...) >>>> >>>> Is there also a possibility to summarize it by grouping (same >>>> questionnaires, but e.g. different location of interview…) * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/