Issue No. 03 - May/June (1985 vol. 2)
Dean Bandes , LTX Corporation
This article introduces a few modern statistical techniques that are especially well suited to analysis of data obtained fromsemiconductor testing. Test data is particularly likely to be distributed in non-Gaussian fashion, thus data summaries anddisplays based on sample means and standard deviations are likely to be misleading. Engineers?test engineers in particular?shouldbecome familiar with stem-and-leaf displays, box-plots, medians, letter-value displays, and pseudosigmas. These displays andstatistics can supplement and gradually replace the more traditional histogram, mean, and standard deviation in test datareporting and in testing literature over the next several years.
D. Bandes, "Exploratory Data Analysis for Semiconductor Manufacturing," in IEEE Design & Test of Computers, vol. 2, no. , pp. 45-55, 1985.