Re: st: check 2 of 3 variables agree a majority decision captured in 4th variable

["Austin Nichols" <austinnichols@gmail.com>]

Eamonn--
input   var1   var2   var3   var4
      2      2      5      2
      2      3      5      5
gen vmax=max(var1,var2,var3)
gen check4=var1 if var1==var2
replace check4=var1 if var1==var3
replace check4=var2 if var3==var2
replace check4=vmax if mi(check4)
drop vmax
tab var4 check4

On 10/5/06, Eamonn O'Brien <Eamonn.O'Brien@icr.ac.uk> wrote:
> I wonder if someone can get me started on how to approach a problem I
> wish to solve. I have searched the archives and not seen anything that's
> too similar.
>
> I have variables var1, var2, var3 & var4. Variables var1 var2 & var3
> are three independent results of a screening test. The independent
> result (ordered categorical) is either normal, borderline, mild, mod or
> severe. Variable Var4 is the final result and it is meant to be based on
> the majority decision. So if var1 & var3 are borderline for example,
> var4 should be borderline, regardless of var2. Another example, if var2
> & var3 are severe, var4 should be severe regardless of var1. Where all
> three differ I would like to check that var4 is the worst of var1, var2,
> var3. If I can get started I think I can develop it to check for missing
> values, but I am not sure if I should approach this problem with if
> statements or -assert- or something else?
>
>
>
> *
> *   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/
*
*   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/