goodness of fit

Share This

“A method of testing how closely two distributions match each other. The distribution values are split into J categories. The number of observed observations within each category are counted and compared to the number of observations expected to fall within each category. The statistic X = ∑ (O-E)2/E has a chi-square distribution with J-1 degrees of freedom. If the sum is too high, the null hypothesis of equal distributions is rejected.”

« Back to Glossary Index Download Tooltip Pro
By |February 1st, 2019|Comments Off on goodness of fit