Testing Consistency of Two Histograms

Abstract

Several approaches to testing the hypothesis that two histograms are drawn from the same distribution are investigated. We note that single-sample continuous distribution tests may be adapted to this two-sample grouped data situation. The difficulty of not having a fully-specified null hypothesis is an important consideration in the general case, and care is required in estimating probabilities with ``toy'' Monte Carlo simulations. The performance of several common tests is compared; no single test performs best in all situations.

35 pages, 15 figures, 5 tables. Plain TeX. Uses graphicx external package. For better quality figures, go to: http://www.hep.caltech.edu/~fcp/statistics/hypothesisTest/PoissonConsistency/PoissonConsistency.pdf

Cited by in corpus (6)

• Detection of long nulls in PSR B1706$-$16, a pulsar with large timing irregularities
• On the distinguishability of histograms
• A method for statistical comparison of histograms
• VizRec: A framework for secure data exploration via visual representation
• Unfolding by Folding: a resampling approach to the problem of matrix inversion without actually inverting any matrix
• TVOR: Finding Discrete Total Variation Outliers among Histograms