Hello guys,
I hope someone here can help me with my stata problem.
I want to find out if the structure of 7 variables is more similar if a prerequisite is fulfilled.
More specifically, I would like to know for my data set: Is the distribution of the variables "salary, bonus, stockawards, optionawards, nonequitycomp, pensionnqdc and othercomp" within an industry (same twodigitssic value) more similar than outside the industries.

Is there an operation at Stata that can output results to this question?

Here is an example of my data set. I hope I created it correctly with dataex.


input float makeid int fiscalyear byte fiscalmonth double salary long bonus double(stockawards optionawards nonequitycomp pensionnqdc othercomp) float totalcompensation byte twodigitssic double(at epspx)
23 2006 12 800000 . 233605 594904 1308661 783980 116198 3053368 50 4496.984 2.77
23 2007 12 835000 . 334489 796194 1332340 1568728 163189 3461212 50 4774.069 2.99
6 2008 12 1500000 0 5697713 3523317 1875000 409855 647881 13243911 35 5183.3 4.91
6 2006 12 1523077 0 4090626 3735813 0 174447 812472 10161988 35 5247.7 6.74
6 2007 12 1500000 400000 3626370 3611577 1350000 0 620888 11108835 35 5410.9 8.06
29 2006 12 1500000 0 5455030 8634787 1320000 0 383278 17293094 34 12325 1.17
56 2006 12 1000000 . . 4061000 9606169 353140 324323 14991492 15 3909.875 4.77
56 2006 12 830000 . . 4061000 9606169 292277 78142 14575311 15 3909.875 4.77



I would be very grateful for your support.

I'm using Stata 15.1