Predicting Prison Population Using the SAS/ETS Product

• NCJ Number: 101667
• Author(s): S Davis
• Date Published: 1986
• Length: 6 pages
• Corporate Author: Oklahoma Dept of Corrections
• Publication Format: Document
• Language: English
• Country: United States of America

Annotation

A comparison of two models for forecasting Oklahoma's prison populations found that a transfer function model of a prison population time series using receptions, paroles, and discharges as inputs was more accurate in producing short-term forecasts than was a univariate model using only the prison population history.

Abstract

Programs from the SAS Institute, Inc., were used to describe and plot the population changes in the Oklahoma prison population. The study used data from 1950 through 1983. Figures, tables, flow chart, 5 references.