怎样避免卡方检验的"局限"

各位老师,上午好. 我想在这里说一下我的困惑. 希望能得到帮忙.
我最近在写一篇论文,正好用到SPSS中卡方检验. 但是卡方对小于5的数值的检验并不合适, 我不知到该如何处理这种情况.
 
回复: 怎样避免卡方检验的"局限"

Use Fisher's Exact test instead if the expected value of a cell is less than 5. Fisher's Exact test computes the exact significance level. Check your SPSS manual for how to do this.
 
回复: 怎样避免卡方检验的"局限"

Log likelihood ratio is preferred to chi-sqaure test.
 
回复: 怎样避免卡方检验的"局限"

Log likelihood ratio compares the full range of the data and chi-sqaure basically the two ends of the data.
 
回复: 怎样避免卡方检验的"局限"

Just tried it. It's really convenient! Thanks a lot!
 
回复: 怎样避免卡方检验的"局限"

An LL test is accepted as more reliable than chi-shquared tests in the corpus field as an LL test, unlike a chi-square test, does not assume normal distribution of data. However, a minimum of 5 for expected cell value also applies as for chi square tests, in which case an exact test is recommended.
 
回复: 怎样避免卡方检验的"局限"

I tried. it's so nice, but is it widely accepted?
Mathematic justification of the reliability of LL in corpus linguistic studies can be found in Paul Rayson's PhD thesis
Rayson, P. (2003). Matrix: A statistical method and software tool for linguistic analysis through corpus comparison. Ph.D. thesis, Lancaster University.
Available at:http://lingo.lancs.ac.uk/llwizard.html
 
Back
顶部