-------------------------------------------------------------------------------
help for aipe
-------------------------------------------------------------------------------

Accuracy in Parameter Estimation

        aipe , r2(value) r2xx(value) w(value) p(value) [ quan(value)
              alpha(value) ]


Description

aipe: estimates sample size for arbitrary width confidence intervals for OLS
regression coefficients using the accuracy in parameter estimation process.
For the sample size estimates N there is approximately only a 50% chance that
the interval will be no larger than the specified 2*w.  By selecting a
chi-square quantile of .8, there is approximately an 80% that the interval will
be no larger than specified when using sample size Nm.

aipe Options

r2 R-squared for the full model.

r2xx R-squared for target predictor with remaining predictors.

w half-width of confidence interval.

p number of predictors in the full model.

quan quantile of the chi-square distribution (default = .8).

alpha the alpha level for confidence interval (default = .05).



Examples

 . aipe, r2(.17) r2xx(.29) w(.15) p(5)
 . aipe, r2(.17) r2xx(.29) w(.15) p(5) quan(.8)

Author

     Philip B. Ender UCLA Academic Technology Services enderatucla.edu

Reference

     Kelley, K. & Maxwell, S.E. 2003. Sample size for multiple regression:
          Obtaining regression coefficients that are accurate, not simply
          significant. Psychological Methods, 8(3), 305-321.