Estimating the number of true null hypotheses from a histogram of p values

Nettleton, Dan; Hwang, J.T. Gene; Caldo, Rico; Wise, Roger

Estimating the number of true null hypotheses from a histogram of p values

File

2006_Nettleton_EstimatingNumber.pdf (249.89 KB)

Date

2006-09-01

Authors

Nettleton, Dan

Hwang, J.T. Gene

Caldo, Rico

Wise, Roger

Authors

Person

Nettleton, Dan

Department Chair and Distinguished Professor

Organizational Units

Organizational Unit

Plant Pathology and Microbiology

The Department of Plant Pathology and Microbiology and the Department of Entomology officially merged as of September 1, 2022. The new department is known as the Department of Plant Pathology, Entomology, and Microbiology (PPEM). The overall mission of the Department is to benefit society through research, teaching, and extension activities that improve pest management and prevent disease. Collectively, the Department consists of about 100 faculty, staff, and students who are engaged in research, teaching, and extension activities that are central to the mission of the College of Agriculture and Life Sciences. The Department possesses state-of-the-art research and teaching facilities in the Advanced Research and Teaching Building and in Science II. In addition, research and extension activities are performed off-campus at the Field Extension Education Laboratory, the Horticulture Station, the Agriculture Engineering/Agronomy Farm, and several Research and Demonstration Farms located around the state. Furthermore, the Department houses the Plant and Insect Diagnostic Clinic, the Iowa Soybean Research Center, the Insect Zoo, and BugGuide. Several USDA-ARS scientists are also affiliated with the Department.

Organizational Unit

Statistics

As leaders in statistical research, collaboration, and education, the Department of Statistics at Iowa State University offers students an education like no other. We are committed to our mission of developing and applying statistical methods, and proud of our award-winning students and faculty.

Department

Plant Pathology and MicrobiologyStatistics

Abstract

In an earlier article, an intuitively appealing method for estimating the number of true null hypotheses in a multiple test situation was proposed. That article presented an iterative algorithm that relies on a histogram of observed p values to obtain the estimator. We characterize the limit of that iterative algorithm and show that the estimator can be computed directly without iteration. We compare the performance of the histogram-based estimator with other procedures for estimating the number of true null hypotheses from a collection of observed p values and find that the histogram-based estimator performs well in settings similar to those encountered in microarray data analysis. We demonstrate the approach using p values from a large microarray experiment aimed at uncovering molecular mechanisms of barley resistance to a fungal pathogen.

Comments

This article is published as Nettleton, Dan, JT Gene Hwang, Rico A. Caldo, and Roger P. Wise. "Estimating the number of true null hypotheses from a histogram of p values." Journal of agricultural, biological, and environmental statistics 11, no. 3 (2006): 337. doi: 10.1198/108571106X129135.