Hi Gala, The default p-value is the bootstrap p-value for the ks-test. Bootstrapping is highly recommended because the bootstrapped Kolmogorov-Smirnov test, unlike the standard test, provides correct coverage even when there are point masses in the distributions being compared. The bootstrap p-value is returned in the ks.boot.pvalue object; so in your example code ks.b$ks.boot.pvalue. And the results from the standard ks.test function are contained in the ks object--i.e., ks.b$ks.
For the theorem of correct coverage even with point masses see: Abadie, Alberto. 2002. ``Bootstrap Tests for Distributional Treatment Effects in Instrumental Variable Models.'' Journal of the American Statistical Association, 97:457 (March) 284-292. For the algorithm see: http://sekhon.berkeley.edu/papers/GenMatch.pdf Cheers, Jas. ======================================= Jasjeet S. Sekhon Associate Professor Travers Department of Political Science Survey Research Center UC Berkeley http://sekhon.berkeley.edu/ V: 510-642-9974 F: 617-507-5524 ======================================= Gala writes: > Hello! > I need to compare 2 datasets whether they come from the same distribution. I > use function ks.boot{Matching}. And what is the confidence level of the > p-value, returned by ks.boot function? > > The code is: > > set=read.table("http://stella.sai.msu.ru:8080/~gala/data/testsets.csv";, > header=T,sep=',') > set1=set[!is.na(set$set1),'set1'] > set2=set[!is.na(set$set2),'set2'] > library(Matching) > ks.b=ks.boot(set1,set2,1000) > ks.b > > Thank you! > > ______________________________________________ [email protected] 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.
