Yates’s Correction
Yates’s correction, also known as Yates’s chi-squared test, is a statistical method used to correct for the discrepancies between observed and expected frequencies in the chi-squared test. Yates’s correction is a type of continuity correction and is used to adjust the chi-squared test for samples with small sizes. Yates’s correction is used to reduce overestimation of the chi-squared statistic, which is often found in small samples.
History
Yates’s correction was first proposed by English statistician Frank Yates in 1934. Yates sought to improve the accuracy of the chi-squared test by proposing a correction to the chi-squared statistic for small samples. Yates proposed that when the sample size is small, the observed and expected frequencies are not independent of each other, which can lead to overestimation of the chi-squared statistic. To address this, Yates proposed a correction to the chi-squared statistic, which he called Yates’s correction. The correction is applied to the observed and expected frequencies to reduce the overestimation of the chi-squared statistic.
Yates’s correction is used in many statistical applications, including the chi-squared test for independence and the chi-squared test for goodness of fit. It is also used in the analysis of contingency tables. Yates’s correction can also be used in the analysis of multiple contingency tables, where each table is analyzed separately.
References
Yates, F. (1934). Contingency tables involving small numbers and the chi-square test. Journal of the Royal Statistical Society, 1(2), 217-235.
Agresti, A. (2013). Categorical data analysis. Wiley.
Kerlinger, F. N., & Lee, H. B. (2000). Foundations of behavioural research. Harcourt College Publishers.
Park, T. J., & Miller, E. A. (2012). An introduction to statistical methods and data analysis. Cengage Learning.