See also [[http://stat.ubc.ca/~rollin/stats/ssize/b1.html|here.]] Computes power for testing prop=const where prop and const are observed and expected (constant) proportions respectively, ntot is the total sample size and alpha is the (two-tailed) type I error. Power computation is also available using a [[attachment:bin1.xls|spreadsheet]] and [[FAQ/Rpowprop|in R.]] [COPY AND PASTE THE SYNTAX BELOW INTO A SPSS SYNTAX WINDOW AND RUN; SET DATA AS DESIRED] {{{ DATA LIST free /prop const ntot alpha. BEGIN DATA. 0.45 0.5 900 .05 END DATA. set errors=none. matrix. get m /variables=prop const ntot alpha /missing=omit. compute prop=make(1,1,0). compute const=make(1,1,0). compute ntot=make(1,1,0). compute alpha=make(1,1,0). compute prop=m(:,1). compute const=m(:,1). compute ntot=m(:,2). compute alpha=m(:,3). end matrix. COMPUTE #chisq1 = ((prop-const)**2)/(const*(1-const)). compute #df=1. compute #conf = 1-alpha. compute #chisq=ntot*#chisq1. compute power = 1 - NCDF.CHISQ(IDF.CHISQ(#conf,#DF),#DF,#CHISQ). formats prop (f5.2) const (f5.2) alpha (f5.2) ntot (f5.2) power (f5.2). variable labels prop 'Proportion' const 'Constant' /alpha 'Two-Tailed Alpha' /ntot 'Total Sample Size' /power 'Power'. report format=list automatic align(center) /variables=prop const alpha ntot power /title "Power for given sample size for One sample test for a single proportion" . }}}