Hello,
I've read the other posts with regard to "chisq.test" and "goodness of fit"
and am still missing something.
1. I create a simple vector of randomly generated lognormal values with
mean=0 and sd=1;
>d1 <- rlnorm(100,meanlog=0,sdlog=1);
2. I also create a vector of probabilities that are expected for a lognormal
distribution. I suspect this is the culprit.
>pr <- dlnorm(d1,meanlog=0,sdlog=1);
3. I perform the chi-square test on the random data and expected
probabilities.
>c <- chisq.test(d1,p=pr,rescale.p=TRUE);
The output is as follows:
Warning message:
Chi-squared approximation may be incorrect in: chisq.test(d1, p = pr,
rescale.p = TRUE)
> c;
Chi-squared test for given probabilities
data: d1
X-squared = 156992.7, df = 99, p-value < 2.2e-16
I'd expect the "goodness of fit" test to pass, with a high p value. Can
someone tell me why things seem incorrect. Again I apologize for the
simpleton request.
Thanks,
John
--
View this message in context:
http://www.nabble.com/help-with-simple-goodness-of-fit-test-tf4630125.html#a13221078
Sent from the R help mailing list archive at Nabble.com.
______________________________________________
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.
