Data-Based Choice of Histogram Bin Width

M. P. Wand

The American Statistician · 1997 · 273 citations · 21 references

Concepts

TL;DR

The bin width of a histogram is crucial for balancing detail and smoothness, yet few studies have examined how to estimate an optimal width, and standard defaults in common software are often far from optimal, though Scott’s rule improves large‑sample performance but remains inconsistent. The study extends Scott’s bin‑width rule to achieve root‑n convergence to the L2‑optimal width, providing scientific justification. The authors extend Scott’s bin‑width rule to achieve root‑n convergence to the L2‑optimal width. The proposed rules are simple, fast to compute, and perform well in simulations. Keywords include binning, data analysis, density estimation, kernel functional estimation, and smoothing parameter selection.

Abstract

Abstract The most important parameter of a histogram is the bin width because it controls the tradeoff between presenting a picture with too much detail ("undersmoothing") or too little detail ("oversmoothing") with respect to the true distribution. Despite this importance there has been surprisingly little research into estimation of the "optimal" bin width. Default bin widths in most common statistical packages are, at least for large samples, quite far from the optimal bin width. Rules proposed by, for example, Scott lead to better large sample performance of the histogram, but are not consistent themselves. In this paper we extend the bin width rules of Scott to those that achieve root-n rates of convergence to the L 2-optimal bin width, thereby providing firm scientific justification for their use. Moreover, the proposed rules are simple, easy and fast to compute, and perform well in simulations. Key Words: BinningData analysisDensity estimationKernel functional estimatorSmoothing parameter selection.

References

21