Visual Assessment vs. Statistical Goodness of Fit Tests for Identifying Parent Population
View/ Open
Date
1988-10-01Author
Mari Berry
Brian Peacock
Bobbie Foote
Lawrence Leemis
Metadata
Show full item recordSee DOI for License
Abstract
Statistical tests are used to identify the parent distribution corresponding to a data set. A human observer looking at a histogram can also identify a probability distribution that models the parent distribution. The accuracy of a human observer was compared to the chi-square test for discrete data and the Kolmogorov-Smirnov and chi-square tests for continuous data. The human observer proved more accurate in identifying continuous distributions and the chi-square test proved to be superior in identifying discrete distributions. The effect of sample size and number of intervals in the histogram was included in the experimental design.
Citation
Berry, M., Peacock, B., Foote, B., & Leemis, L. (1988). Visual Assessment vs. Statistical Goodness of Fit Tests for Identifying Parent Population. Proceedings of the Human Factors and Ergonomics Society Annual Meeting, 32(7), 460-464. doi: 10.1177/154193128803200701