Problems
The approximation to the chi-squared distribution breaks down if expected frequencies are too low. It will normally be acceptable so long as no more than 20% of the events have expected frequencies below 5. Where there is only 1 degree of freedom, the approximation is not reliable if expected frequencies are below 10. In this case, a better approximation can be obtained by reducing the absolute value of each difference between observed and expected frequencies by 0.5 before squaring; this is called Yates's correction for continuity.
In cases where the expected value, E, is found to be small (indicating either a small underlying population probability, or a small number of observations), the normal approximation of the multinomial distribution can fail, and in such cases it is found to be more appropriate to use the G-test, a likelihood ratio-based test statistic. Where the total sample size is small, it is necessary to use an appropriate exact test, typically either the binomial test or (for contingency tables) Fisher's exact test; but note that this test assumes fixed and known marginal totals.
Read more about this topic: Pearson's Chi-squared Test
Famous quotes containing the word problems:
“One of the annoying things about believing in free will and individual responsibility is the difficulty of finding somebody to blame your problems on. And when you do find somebody, it’s remarkable how often his picture turns up on your driver’s license.”
—P.J. (Patrick Jake)
“While the onset of puberty can vary by as much as six years, every adolescent wants to be right on the 50-yard line, right in the middle of the field. One is always too tall, too short, too thin, too fat, too hairy, too clear-skinned, too early, too late. Understandably, problems of self-image are rampant.”
—Joan Lipsitz (20th century)
“All problems are finally scientific problems.”
—George Bernard Shaw (1856–1950)