Cover: New York City Fire Alarm Prediction Models

New York City Fire Alarm Prediction Models

II. Alarm Rates

Published 1975

by Grace M. Carter, John E. Rolph


Download eBook for Free

FormatFile SizeNotes
PDF file 2.7 MB

Use Adobe Acrobat Reader version 10 or higher for the best experience.


Purchase Print Copy

 Format Price
Add to Cart Paperback80 pages $20.00

Describes a prediction model for forecasting fire alarm rates using, as a working example of the model, data from the Bronx. First, estimates are made of the daily alarm rates in large regions, and then the fraction of the daily alarms occurring in each hour is estimated. Next, the resultant hourly alarm rate predictions are improved by using exponential smoothing to capture some of the effect on current alarm rates of variables that were not explicitly modeled. Finally, the large area predictions are used to derive hourly alarm predictions for the small areas, needed by the initial dispatch algorithm. At each stage in the modeling process alternative estimating procedures are evaluated. Bronx alarm data for 1964 through 1969 are used in choosing the model. The resulting predictions are compared to 1970 data. (See also R-1214.)

This report is part of the RAND report series. The report was a product of RAND from 1948 to 1993 that represented the principal publication documenting and transmitting RAND's major research findings and final research.

This document and trademark(s) contained herein are protected by law. This representation of RAND intellectual property is provided for noncommercial use only. Unauthorized posting of this publication online is prohibited; linking directly to this product page is encouraged. Permission is required from RAND to reproduce, or reuse in another form, any of its research documents for commercial purposes. For information on reprint and reuse permissions, please visit

RAND is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.