Вы находитесь на странице: 1из 2

F Test : Introduction and explanation

Site links : Home Index Search Data I/O Plots Q&A Contact Related links : Table of probability for F values Program to calculate probability of F values Table of Contents : Historical notes Use of F Test How to use the table References

Historical notes
The F-distribution is named after the famous statistician R. A. Fisher. It is also sometimes known as the Fisher F distribution or the Snecedor-Fisher F distribution. F is the ratio of two variances.
Back to Top

Use of F Test
The F-distribution is most commonly used in Analysis of Variance (ANOVA) and the F test (to determine if two variances are equal). The F-distribution is the ratio of two chi-square distributions, and hence is right skewed. It has a minimum of 0, but no maximum value (all values are positive). The peak of the distribution is not far from 0, as can be seen in the following diagram

A specific F-distribution is denoted by the numerator degrees of freedom (ndf) for the chi-square and and the degrees of freedom for the denominator chi-square (ddf), written as F(ndf,ddf). It is important to note that when referencing the F-distribution the numerator degrees of freedom are always given first, and switching the degrees of freedom changes the distribution (ie. F(10,12) does not equal F(12,10)). Interestingly, the three most famous distributions (normal, t and chi-square) can all be seen as "special" cases of the F-distribution:

normal distribution = F(1, infinite) t-distribution = F(1, ddf) chi-square distribution = F(ndf, infinite)
Back to Top

How to use the table


The table relating F and probability is a 3 dimensional table, with the numerator degrees of freedom as columns, denominator degrees of freedom as rows, and probability borders as depths. As tables are on 2 dimensional, the probability borders are presented as sub-rows of the deniminator degrees of freedom As this arrangement is rather cumbersome and can be confusing, the recommendation is to use the program and calculate the results required. However, for those requiring a large number of results sumultaneously, the table of critical F values are presented in FTest_Tab.php To find the critical F value for a probability and numerator and denominator degrees of freedom, find the column corresponding to numerator degrees of freedom and the row corresponding to denominator degrees of freedom and for the desired probability (P either 0.001, 0.005, 0.010, 0.050 and 0.100) read off the F statistic. For example, for F(3,4) and a probability of 0.05, the F statistic is 6.5914.
Back to Top

References
Press WH, Flannery BP, Teukolsky SA, and Vetterling WT. (1994) Numerical recipes in Pascal. Cambridge University Press ISBN 0-521-37516-9. p.189
Back to Top

Вам также может понравиться