In addition, check out -rowranks- on SSC.
Nick
[email protected]
Stephen P Jenkins replied to Tonya Cropper
> >
> > I wrote a program to calculate a Borda count result of
> > predicted probabilities of people within groups. The program
> > calculates the results I want, but I am hoping there's a more
> > efficient way of doing it. Within each group, I want to rank
> > each person's predicted probability for three outcomes(Pd,
> > Pl, Pu). I have multiple sets of these probabilites based on
> > different models, so I performed the counts in a loop. I
> > gave each person a score of 3 for the highest probability, 2
> > for the 2nd, and 1 for the lowest. I then summed each outcome
> > to get a total Borda score. If Pd was the highest score,
> > then the Borda result is 1 and 0 otherwise (I mainly care
> > about Pd, ties will go to Pl, Pu is undecided). Below is an
> > example. I will appreciate any assistance to streamline the
> > program. Thank you.
>
> I think -reshape- helps. See below
>
>
> . list
>
> +---------------------------------+
> | id p1 p2 p3 death |
> |---------------------------------|
> 1. | 1 .275 .401 .324 0 |
> 2. | 2 .582 .163 .255 0 |
> 3. | 3 .072 .63 .298 0 |
> 4. | 4 .489 .064 .446 0 |
> 5. | 5 .242 .4 .358 0 |
> +---------------------------------+
>
>
> . reshape long p, i(id) j(pr)
> (note: j = 1 2 3)
>
> Data wide -> long
> --------------------------------------------------------------
> ----------
> -----
> Number of obs. 5 -> 15
> Number of variables 5 -> 4
> j variable (3 values) -> pr
> xij variables:
> p1 p2 p3 -> p
> --------------------------------------------------------------
> ----------
> -----
>
> . list
>
> +------------------------+
> | id pr p death |
> |------------------------|
> 1. | 1 1 .275 0 |
> 2. | 1 2 .401 0 |
> 3. | 1 3 .324 0 |
> 4. | 2 1 .582 0 |
> 5. | 2 2 .163 0 |
> |------------------------|
> 6. | 2 3 .255 0 |
> 7. | 3 1 .072 0 |
> 8. | 3 2 .63 0 |
> 9. | 3 3 .298 0 |
> 10. | 4 1 .489 0 |
> |------------------------|
> 11. | 4 2 .064 0 |
> 12. | 4 3 .446 0 |
> 13. | 5 1 .242 0 |
> 14. | 5 2 .4 0 |
> 15. | 5 3 .358 0 |
> +------------------------+
>
> . bys id (p):ge r = _n
>
> . bys pr: egen bc = sum(r)
>
> . list
>
> +---------------------------------+
> | id pr p death r bc |
> |---------------------------------|
> 1. | 1 1 .275 0 1 9 |
> 2. | 4 1 .489 0 3 9 |
> 3. | 3 1 .072 0 1 9 |
> 4. | 2 1 .582 0 3 9 |
> 5. | 5 1 .242 0 1 9 |
> |---------------------------------|
> 6. | 2 2 .163 0 1 11 |
> 7. | 3 2 .63 0 3 11 |
> 8. | 5 2 .4 0 3 11 |
> 9. | 1 2 .401 0 3 11 |
> 10. | 4 2 .064 0 1 11 |
> |---------------------------------|
> 11. | 1 3 .324 0 2 10 |
> 12. | 2 3 .255 0 2 10 |
> 13. | 3 3 .298 0 2 10 |
> 14. | 4 3 .446 0 2 10 |
> 15. | 5 3 .358 0 2 10 |
> +---------------------------------+
>
> Now manipulate as you wish.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
