st: st. sampclus

[César Mora <cmora@grade.org.pe>]

Hello Dear All. I have a question about sampsi and sampclus:

First, when you use "sampsi", for example:

sampsi 0.0525 0.075, sd(0.2029) alpha (0.05) power(0.8)

   Results:

Estimated sample size for two-sample comparison of means

Test Ho: m1 = m2, where m1 is the mean in population 1
                   and m2 is the mean in population 2
Assumptions:

        alpha =   0.0500  (two-sided)
        power =   0.8000
           m1 =    .0525
           m2 =     .075
          sd1 =    .2029
          sd2 =    .2029
        n2/n1 =     1.00

Estimated required sample sizes:

           n1 =     1277
           n2 =     1277


****
****

* You can capture n1 (=1277) using:  scalar name=r(N_1)

But, after using sampsi, you can use sampclus to correct the sample size 
using clusters.
For example:

sampclus, rho(0.01) numclus(48)

   Results:

Sample Size Adjusted for Cluster Design

  n1 (uncorrected) = 1277
  n2 (uncorrected) = 1277

  Intraclass correlation     = .01

  Average obs. per cluster   = 113
  Minimum number of clusters = 48


  Estimated sample size per group:

     n1 (corrected) = 2708
     n2 (corrected) = 2708


****
****

* I want to know, how to capture n1(corrected) in scalar. In other words I 
want to know the equivalent commad  "scalar name=r(N_1)" for sampclus.

Thank you very much 

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/