discrepancy for pwr.p.test

[Deleted user]

hello, What am I missing here?:

abs(ES.h(.1, .11))
0.0326294
power.prop.test(p1 = .1, p2 = .11, sig.level = .1, power = .9)
Two-sample comparison of proportions power calculation

          n = 16093.88
         p1 = 0.1
         p2 = 0.11
  sig.level = 0.1
      power = 0.9
alternative = two.sided

NOTE: n is number in each group

pwr.p.test(h = ES.h(.1, .11), sig.level = .1, power = .9)

 proportion power calculation for binomial distribution (arcsine transformation) 

          h = 0.0326294
          n = 8043.529
  sig.level = 0.1
      power = 0.9
alternative = two.sided

I validated with my own custom function and stats::power.prop.test is the right answer.
Is this a bug or am I wrong somewhere?

[heliosdrm]

power.prop.test is "Power Calculations for Two-Sample Test for Proportions", whereas pwr.p.test is "Power calculations for proportion tests (one sample)". You should compare with pwr.2p.test:

> pwr.2p.test(h=ES.h(0.1,0.11), sig.level = .1, power = .9)

     Difference of proportion power calculation for binomial distribution (arcsine transformation) 

              h = 0.0326294
              n = 16087.06
      sig.level = 0.1
          power = 0.9
    alternative = two.sided

NOTE: same sample sizes

[Deleted user]

oopsy
i turned out a newbie

sry