The decline and fall of Type II error rates

Steve P. Verrill; Mark Durst

Treesearch

The decline and fall of Type II error rates

Formally Refereed

Authors:

Steve P. Verrill, Mark Durst

Year:

2005

Type:

Scientific Journal

Station:

Forest Products Laboratory

Source:

American Statistician

Download (PDF 412 KB)

Download (PDF 412 KB): https://research.fs.usda.gov/download/treesearch/26851.pdf

Abstract

For general linear models with normally distributed random errors, the probability of a Type II error decreases exponentially as a function of sample size. This potentially rapid decline reemphasizes the importance of performing power calculations.

Keywords

asymptotic relative efficiency, experimental design, Hodges-Lehmann efficiency, linear models, Mills’ ratio, minimum detectable difference, noncentral F, normal tail, Pitman efficiency, power, sample size

Citation

Verrill, Steve P.; Durst, Mark. 2005. The decline and fall of Type II error rates. American Statistician. 59(4): 287-291.