![]() ![]() What is the post-hoc power in the following experiment? “Correct post-hoc analysis” I said is synonymous with “post-hoc analysis that many people criticize.” I know that there is no "correct" post-hoc analysis, as it is often screamed in mass-produced editorial. Require explanations in formulas and codes instead of words. ![]() Please chunk down words into the formula. Please show me formulas or codes instead of words. The verbal explanation is written on the mass-produced editorial. (This is likely to apply to all statutory ethics editorials that have been mass-produced recently.) Give calculation procedure before criticizing them!! Wouldn't it be strange to be able to understand these opinions like “it doesn't make sense because it is unique if other variables are set” or “circular theory” for objects whose calculation method is not shown? This looks like a barren on-air battle under the unclear premise. The strange thing is that even though many people have been criticized so much but "what is post-hoc power?" is not seems to clear. The results are different, but different ways.) (Both code 1 and code 2 below seem to meet their common definitions. However, it is not chunked down into formulas or calculation codes. Therefore, what is they want to criticize are not identified / at least not shared with me. However, it is unclear what the post-hoc power they criticize is.Ĭertainly they writes definition is written in words. I can easily to access to the definitions that are not chunked-down to formulas or codes. This kind of editorials are mass-produced and is published on many established journals. I often see the claims that post-hoc power is nonsense. It was recommended to ask this community at. It is in the spirit of the usual way of computing sample sizes, but I'm not too sure about when the underlying approximations start to be false.Īfter some fiddling around, both methods give similar results unless you have very unbalanced groups (but in that case, at some point you might want to just approximate the super large group as a known population).Įdit : just realized this does not exactly answer your question about power rather than sample size, but you can easily flip the Z method formula to compute power (exact method seems more hairy worst case, numeric trial and error should work since the relationship is monotonous).The following articles are reprinte of #3375492 of. Weirdly, it forces you to input only one variance but the formula it gives can use two (and is the same as the paper above). The Z method is also the one used in which cites Rosner B. Powere<-sum(wpdf*pt(-tdfea*sqrt(b12/sigsqt),dft,mud/hsigsqt))+1-sum(wpdf*pt(tdfea*sqrt(b12/sigsqt),dft,mud/hsigsqt)) ssize.welch = function(alpha=0.05, power=0.90, mu1, mu2, sigma1, sigma2, n2n1r, use_exact=FALSE) The article "Optimal sample sizes for Welch’s test under various allocation and cost considerations" from Show-Li Jan & Gwowen Shieh published in Behavior Research Methods in December 2011 has the following code in supplementary material A, slightly modified here for my own ergonomy. $n_1 = n_2 = 35$ gives about 90% power (with everything else the same). You might want to use 10,000 iterations if you are doing repeated runs for various sample sizes, and then use a larger number of iterations to verifyĬhanging to $n_2 = 20$ gives power 67%, so the extra 30 observations in Group 2 are not 'buying' you as much as you might hope. T.test(rnorm(n1,0,sg1),rnorm(n2,dlt,sg2))$p.val)īecause the P-value is taken directly from the procedure t.test in R, results should be accurate to 2 or 3 places, but this style of simulation runs slowly (maybe 2 or 3 min.) with \sigma_1 = 15,\,$ $n_2 = 50, \sigma_2 = 10,$ then you have about 75% power for detecting a difference $\delta = 10$ in population means with a Welch test at level 5%. Second, you can use simulation to get the power for various scenarios. Especially if the smaller sample size is used for the group with the larger population, this is not an efficient design. Comment: First, I would suggest you consider carefully whether you have a really good reason to use different sample sizes. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |