4

I'm switching from R to SPSS for a specific project (I'm not allowed to use SPSS/R integration) and need to summarize quickly a big dataset. In R, it's quite simple, one can use the summary() function and in few seconds obtain the summary of each variable. I would need to know if there is a function in SPSS that do the same job. If not, how could I achieve it.

For the non-R users summary.default would return labelled values for Min. , 1st Quartile, Median, Mean , 3rd Quartile, Max. for each numeric column and a counts of the 6 most common items and the count of the "(Other)" category if a factor or character variable.

IRTFM
  • 258,963
  • 21
  • 364
  • 487
José Vallejo
  • 356
  • 4
  • 17

2 Answers2

3

Descriptives comes close.

descriptives var1 var2 var3 
 /statistics = mean median stddev variance min max .

(I'm not sure about quartiles).

Jeremy Miles
  • 349
  • 1
  • 16
  • 4
    You can get all the same stuff from `FREQUENCIES` - e.g. `FREQ v1 v2 v3 /STATISTICS = MEAN MED STDDEV MIN MAX /NTILES = 4`. (You can also specify particular percentiles as well.) For factors you may want to use `/FORMAT = DFREQ`, which prints the frequency table is descending counts. – Andy W May 25 '16 at 10:38
2

If you have a mixture of continuous and categorical variables, use DESCRIPTIVES or SUMMARIZE for continuous and FREQUENCIES for categorical. You can use the SPSSINC SELECT VARIABLES extension command installed with Statistics to create macros listing variables according to the measurement level and then use the appropriate macro for each command.

JKP
  • 5,419
  • 13
  • 5