On 27-Mar-2013 21:04:51 David Arnold wrote: > All, > How come both of these are the same. Both say "1-sample proportions > test without continuity correction." I would suspect one would say > "without" and one would say "with." > > >> prop.test(118,236,.5,correct=FALSE,conf.level=0.95) > > 1-sample proportions test without continuity correction > > data: 118 out of 236, null probability 0.5 > X-squared = 0, df = 1, p-value = 1 > alternative hypothesis: true p is not equal to 0.5 > 95 percent confidence interval: > 0.4367215 0.5632785 > sample estimates: > p > 0.5 > >> prop.test(118,236,.5,correct=TRUE,conf.level=0.95) > > 1-sample proportions test without continuity correction > > data: 118 out of 236, null probability 0.5 > X-squared = 0, df = 1, p-value = 1 > alternative hypothesis: true p is not equal to 0.5 > 95 percent confidence interval: > 0.4367215 0.5632785 > sample estimates: > p > 0.5
Note what is said (admittedly somewhat deeply tucked away) under "Details" in ?prop.test: "Continuity correction is used only if it does not exceed the difference between sample and null proportions in absolute value." In your example, the sample proportion exactly matches the null-hypothesis proportion (0.5). Confirmation: [A] Your same example: prop.test(118,236,.5,correct=TRUE,conf.level=0.95) # 1-sample proportions test without continuity correction # data: 118 out of 236, null probability 0.5 # X-squared = 0, df = 1, p-value = 1 # alternative hypothesis: true p is not equal to 0.5 # 95 percent confidence interval: # 0.4367215 0.5632785 # sample estimates: # p # 0.5 [B1] Slightly change x, but keep "correct=TRUE": prop.test(117,236,.5,correct=TRUE,conf.level=0.95) # 1-sample proportions test with continuity correction # data: 117 out of 236, null probability 0.5 # X-squared = 0.0042, df = 1, p-value = 0.9481 # alternative hypothesis: true p is not equal to 0.5 # 95 percent confidence interval: # 0.4304724 0.5611932 # sample estimates: # p # 0.4957627 [B2] Slightly change x, but now "correct=FALSE": prop.test(117,236,.5,correct=FALSE,conf.level=0.95) # 1-sample proportions test without continuity correction # data: 117 out of 236, null probability 0.5 # X-squared = 0.0169, df = 1, p-value = 0.8964 # alternative hypothesis: true p is not equal to 0.5 # 95 percent confidence interval: # 0.4325543 0.5591068 # sample estimates: # p # 0.4957627 So it doesn't do the requested continuity correction in [A] because there is no need to. But in [B1] it makes a difference (compare with [B2]), so it does it. Hoping this helps, Ted. ------------------------------------------------- E-Mail: (Ted Harding) <ted.hard...@wlandres.net> Date: 27-Mar-2013 Time: 21:21:39 This message was sent by XFMail ______________________________________________ R-help@r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
