Significance level = 0.05, Power = 0.9
     

     
Estimated power from simulation study


Scenario

m
_{1}

m
_{2}

ϕ
_{1}

ϕ
_{2}

n

log ttest

MW test

ttest


1

0.1

0.3

\(\frac {0.1}{\log (2)}\)

\(\frac {0.3}{\log (2)}\)

29

0.890

0.933

0.975

2

1

1.5

\(\frac {1}{\log (2)}\)

\(\frac {1.5}{\log (2)}\)

211

0.900

0.948

0.985

3

10

7

\(\frac {10}{\log (2)}\)

\(\frac {7}{\log (2)}\)

272

0.898

0.947

0.985

4

20

15

\(\frac {20}{\log (2)}\)

\(\frac {15}{\log (2)}\)

418

0.900

0.950

0.986

5

60

48

\(\frac {60}{\log (2)}\)

\(\frac {48}{\log (2)}\)

695

0.899

0.949

0.985

6

80

70

\(\frac {80}{\log (2)}\)

\(\frac {70}{\log (2)}\)

1939

0.898

0.949

0.985

 Here, m
_{
j
} and ϕ
_{
j
} denote the median and standard deviation of the outcome data for group j. Estimated powers are shown for a twosample ttest of logtransformed outcomes (‘log ttest’), a MannWhitney U test of untransformed outcomes (‘MW test’) and a twosample ttest of untransformed outcomes (‘ttest’)