Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

From |
"Carlo Lazzaro" <carlo.lazzaro@tin.it> |

To |
<statalist@hsphsun2.harvard.edu> |

Subject |
st: R: Kruskal-Wallis equality-of-populations rank test |

Date |
Sat, 13 Nov 2010 12:17:05 +0100 |

Momo wrote: "-2- some variables I got results with 1st type 1st var as follows. chi-squared = 290.697 with 172 d.f. probability = 0.0001 chi-squared with ties = 388.261 with 172 d.f. probability = 0.0001" Whenever groups of tied scores come alive in KruskalWallis (KW) test, the ranks that should be assigned are averaged, and the average rank is assigned, instead. The test statistic T is different in presence and in absence of ties: this explains the difference in the results Stata gave you excluding and including ties. For more on KW (pag. 288-300) and on nonparametric tests at large, I would recommend you to look up to Conover WJ. Practical nonparametric statistics. Third ed. New York: Wiley, 1999. Kind Regards, Carlo ----Messaggio originale----- Da: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] Per conto di momo Inviato: venerdì 12 novembre 2010 15.38 A: statalist@hsphsun2.harvard.edu Oggetto: st: Kruskal-Wallis equality-of-populations rank test Dear Colleagues I am using KW test to check the differences between Four different types of companies and I use four variables, so I check for each variables on each type each time. I mean the 1st var on 1st type, the 2nd var on 1st type and so on.. 1- so with some variables stata don't do the test and gives me "too many values" where I am using stata 11. 2- some variables I got results with 1st type 1st var as follows. chi-squared = 290.697 with 172 d.f. probability = 0.0001 chi-squared with ties = 388.261 with 172 d.f. probability = 0.0001 whats the differences between the values. so any help in explanation highly appreciated. Thanks in advance -- View this message in context: http://statalist.1588530.n2.nabble.com/Kruskal-Wallis-equality-of-population s-rank-test-tp5732513p5732513.html Sent from the Statalist mailing list archive at Nabble.com. * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/ * * For searches and help try: * http://www.stata.com/help.cgi?search * http://www.stata.com/support/statalist/faq * http://www.ats.ucla.edu/stat/stata/

**References**:**st: Kruskal-Wallis equality-of-populations rank test***From:*momo <mmsabra@gmail.com>

- Prev by Date:
**st: estout: estadd scalar returns "=exp not allowed"** - Next by Date:
**Re: st: stata runs slowly** - Previous by thread:
**st: Kruskal-Wallis equality-of-populations rank test** - Next by thread:
**st: Re: question about ivreg2** - Index(es):