How to match randomized treatment (not in order) to round (in order)?

[Scott Forrester]

Dear Statalist,

I have a randomized order of treatments in four rounds. Rounds 1-4 are always in order, but the treatments are not.

I would like to 1) understand the ordering, i.e., how often was treatment 1 in round 1, in round 2, in round 3, and 4 and so on with the remaining 3 treatments.

I thought of using count if:

 count if treatment == 1 == round ==1

and so on but I hope there is a more elegant way to present the data in a table.

2) I would like to use this information of order and treatment in my regression as an independent variable. Would I use i.round##i.treatment for that?

Here is an excerpt of the data using dataex:

 dataex round treatment

* Example generated by -dataex-. For more info, type help dataex
clear
input byte(round treatment)
1 2
2 3
3 1
4 4
1 1
2 3
3 4
4 2
1 4
2 3
3 2
4 1
1 1
2 4
3 2
4 3
1 3
2 4
3 1
4 2
end

Thank you very much in advance!

Kind regards,
Scott

[Andrew Musau]

* Example generated by -dataex-. To install: ssc install dataex
clear
input byte(round treatment)
1 2
2 3
3 1
4 4
1 1
2 3
3 4
4 2
1 4
2 3
3 2
4 1
1 1
2 4
3 2
4 3
1 3
2 4
3 1
4 2
end

table treatment round, stat(count round)

Res.:

. table treatment round, stat(count round)

----------------------------------
          |          round        
          |  1   2   3   4   Total
----------+-----------------------
treatment |                       
  1       |  2       2   1       5
  2       |  1       2   2       5
  3       |  1   3       1       5
  4       |  1   2   1   1       5
  Total   |  5   5   5   5      20
----------------------------------

Would I use i.round##i.treatment

You would do that if you wanted to see whether there was an effect of treatment, round and whether these effects interact.

[Scott Forrester]

Thank you very much! You have been most helpful!