A Goodness-of-Fit Test Based on P-P Probability Plots

Abstract

A quantitative measure of linearity of a P-P probability plot is the square of the correlation coefficient of points on the plot. This statistic aids in the assessment of goodness of fit of a hypothesized distribution. A computer program is presented for computing the p value of this statistic when testing the goodness of fit of a normal, a Gumbel, or an exponential distribution. The program can also construct a normal, a Gumbel, or an exponential P-P probability plot.

• Exponential Distribution
• Gumbel Distribution
• Normal Distribution
• Shapiro-Francia Statistic
• Shapiro-Wilk Statistic

Additional information

Notes on contributors

F. F. Gan

Dr. Gan is a Statistical Consultant and Senior Lecturer in the Department of Mathematics. He is a Member of ASQC.

K. J. Koehler

Dr. Koehler is a Professor in the Department of Statistics.