Re: st: Re: Simulated data

[Nick Cox <njcoxstata@gmail.com>]

You can use Stata to get help:

. search power simulation

Keyword search

        Keywords:  power simulation
          Search:  (1) Official help files, FAQs, Examples, SJs, and STBs

Search of official help files, FAQs, Examples, SJs, and STBs


FAQ     . . . . . . . . . . . . . . . . . . .  Calculating power by simulation
        . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  A. Feiveson
        11/01   How can I use Stata to calculate power by simulation?
                http://www.stata.com/support/faqs/stat/power.html

Example . . . . . . . . . Data analysis examples: One-way anova power analysis
        . . . . . . . . . . . . . . . . . .  UCLA Academic Technology Services
        7/08    http://www.ats.ucla.edu/stat/stata/dae/fpower.htm

Example . . . . . . . . . . . . . Stata Analysis Tools: Anova power simulation
        . . . . . . . . . . . . . . . . . .  UCLA Academic Technology Services
        7/08    http://www.ats.ucla.edu/stat/ado/analysis/simpower.html

SJ-2-2  st0010  . . . . . . . . . . . . . . . . . . . . .  Power by simulation
        . . . . . . . . . . . . . . . . . . . . . . . . . . . . A. H. Feiveson
        Q2/02   SJ 2(2):107--124                                 (no commands)
        describes how to perform power and sample size estimation
        using simulation in Stata

Nick

On Thu, Aug 30, 2012 at 9:06 PM, Janet Hill <janethill73@yahoo.co.uk> wrote:

> I have a variable which is an integer in the range 0-20 and I have compared 3 groups using the Kruskal-Wallis test:
> . kwallis x,by(_j)
> Kruskal-Wallis equality-of-populations rank test
>   +---------------------+
>   | _j | Obs | Rank Sum |
>   |----+-----+----------|
>   |  1 |  20 |   705.00 |
>   |  2 |  20 |   395.50 |
>   |  3 |  20 |   729.50 |
>   +---------------------+
> chi-squared =    11.363 with 2 d.f.
> probability =     0.0034
> chi-squared with ties =    11.467 with 2 d.f.
> probability =     0.0032
>
> A referee has accepted this in a paper but has added the comment "The authors should investigate the power of this test using simulated datasets, as they are using Stata for the analysis this is trivial".
> It may be trivial to the referee and people who understand such things but I have no idea how to simulate data to test this.
> I would be grateful if somebody could give me some advice on how to generate such data.
>
> I am using Stata 12.
*
*   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/