how to calculate variance of a variable in a panel data structure

[muhammad akhtaruzzaman]

Hello dear Stata users,
I have a panel dataset of household weekly income at regional level (10 regions) for 20 years. I need to calculate variance of household income. Is there a straightforward Stata command to calculate variance of the household income?
I think the calculated variance would represent variance in household income across the regions?
Could anyone please advise me in this regard? Look forward to hearing from you.
Thanks
Akhtar

[Clyde Schechter]

-xtsum- will give you the between, within, and overall standard deviations. Square those to get the corresponding variances. You need to clarify for yourself which of the three statistics is the relevant one for your purposes.

[muhammad akhtaruzzaman]

Thanks Clyde.
Yes xtsum generates a summary statistics of variance. Can it be generated as time series observation for each year and each id? For example, variance of income for id 1 in year 1 compared to sample average or compared to national average income.
Thanks
Akhtar

[Clyde Schechter]

Your question is unclear to me. If this is panel data on income, id 1 in year 1 refers to a single observation so the variance is necessarily 0. Evidently I'm missing something. I think you need to provide either a better description of your data (preferrably accompanied by some example data using the -dataex- command, a better description of what you want, or both.

If you are running version 15.1 or a fully updated version 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.

[muhammad akhtaruzzaman]

Sorry Clyde, I wasn't clear about the query. I attached the data file so that you could see the structure of the data. Can I use -xtsum- to generate a new variable measuring variance (within or between) of household income?
Thanks
Akhtar

[Marcos Almeida]

Please read the FAQ, particularly the topic about sharing data/command/output.

Please read #4 and act accordingly.

That being said, if I understand correctly your query, you may use - mixed - for that matter.

[David Benson]

* Example generated by -dataex-. To install: ssc install dataex
clear
input int year byte id float weekly_income
1998 1  702
1999 1  754
2000 1  736
2001 1  786
2002 1  846
2003 1  899
2004 1  925
2005 1 1074
2006 1 1055
2007 1 1175
2008 1 1030
2009 1 1144
2010 1 1186
2011 1 1205
2012 1 1116
2013 1 1231
2014 1 1288
1998 2 1066
1999 2 1074
2000 2 1097
2001 2 1162
2002 2 1206
2003 2 1264
2004 2 1362
2005 2 1365
2006 2 1344
2007 2 1426
2008 2 1517
2009 2 1468
2010 2 1521
2011 2 1601
2012 2 1658
2013 2 1664
2014 2 1767
1998 3  864
1999 3  839
2000 3  892
2001 3  921
2002 3  999
2003 3 1017
2004 3 1081
2005 3 1141
2006 3 1192
2007 3 1301
2008 3 1314
2009 3 1343
2010 3 1309
2011 3 1372
2012 3 1502
2013 3 1432
2014 3 1418
1998 4  841
1999 4  865
2000 4  815
2001 4  899
2002 4  925
2003 4 1001
2004 4 1001
2005 4 1025
2006 4 1107
2007 4 1243
2008 4 1245
2009 4 1276
2010 4 1312
2011 4 1293
2012 4 1342
2013 4 1389
2014 4 1420
1998 5  784
1999 5  846
2000 5  856
2001 5  879
2002 5  902
2003 5  975
2004 5  972
2005 5 1016
2006 5 1129
2007 5 1168
2008 5 1237
2009 5 1267
2010 5 1251
2011 5 1227
2012 5 1313
2013 5 1266
2014 5 1325
end
format %ty year
format weekly_income %9.0fc
label var weekly_income "Average Income from All Sources collected ($ weekly)"

xtset id year, yearly

. desc

Contains data
  obs:           170                          
 vars:             3                          
 size:         1,190                          
---------------------------------------------------------------------------------------------------------------------------------------------
              storage   display    value
variable name   type    format     label      variable label
---------------------------------------------------------------------------------------------------------------------------------------------
year            int     %ty                  
id              byte    %8.0g                
weekly_income   float   %9.0fc                Average Income from All Sources collected ($ weekly)
---------------------------------------------------------------------------------------------------------------------------------------------



. xtsum

Variable         |      Mean   Std. Dev.       Min        Max |    Observations
-----------------+--------------------------------------------+----------------
year     overall |      2006   4.928054       1998       2014 |     N =      85
         between |                    0       2006       2006 |     n =       5
         within  |             4.928054       1998       2014 |     T =      17
                 |                                            |
id       overall |         3   1.422607          1          5 |     N =      85
         between |             1.581139          1          5 |     n =       5
         within  |                    0          3          3 |     T =      17
                 |                                            |
weekly~e overall |  1153.682   238.3902        702       1767 |     N =      85
         between |             142.8004   1008.941       1386 |     n =       5
         within  |             200.8037   819.9176   1534.682 |     T =      17


. summ

    Variable |        Obs        Mean    Std. Dev.       Min        Max
-------------+---------------------------------------------------------
        year |         85        2006    4.928054       1998       2014
          id |         85           3    1.422607          1          5
weekly_inc~e |         85    1153.682    238.3902        702       1767



. tabstat weekly_income, by(id) stats(n mean median min max sd var)

Summary for variables: weekly_income
     by categories of: id

      id |         N      mean       p50       min       max        sd  variance
---------+----------------------------------------------------------------------
       1 |        17  1008.941      1055       702      1288  192.0513  36883.68
       2 |        17      1386      1365      1066      1767  219.3556  48116.88
       3 |        17  1172.765      1192       839      1502  219.7401  48285.69
       4 |        17  1117.588      1107       815      1420   208.222  43356.38
       5 |        17  1083.118      1129       784      1325  187.2124  35048.49
---------+----------------------------------------------------------------------
   Total |        85  1153.682      1168       702      1767  238.3902  56829.89
--------------------------------------------------------------------------------

[muhammad akhtaruzzaman]

Thanks David for this wonderful response. Cheers.