To test the hypothesis that time series analysis can provide accurate
predictions of future ambulance service run volume, a prospective stoc
hastic time series modeling study was conducted at a community based r
egional ambulance service. For all requests for ambulance transport du
ring two sequential years, the time and date, total run time, and acui
ty code of the run were recorded in a computer database. Time series V
ariables were formed for ambulance service runs per hour, total run ti
me, and acuity, Prediction models were developed from one complete yea
r's data (1994) and included four model types: raw observations, movin
g average, means with moving average smoothing, and autoregressive int
egrated moving average. Forecasts from each model were tested against
observations from the first 24 weeks of the subsequent year (1995). Ea
ch model's adequacy was tested on residuals by autocorrelation functio
ns, integrated periodograms, linear regression, and differences among
the variances. A total of 68,433 patients were seen in 1994 and 32,783
in the first 24 weeks of 1995. Large periodic variations in run volum
e with time of day were found (P < .001). A model based on arithmetic
means of each hour of the week with 3-point moving average smoothing y
ielded the most accurate forecasts and explained 54.3% of the variatio
n observed in the 1995 test series (P < .001). Time series analysis ca
n provide powerful, accurate short range forecasts of future ambulance
service run volume, Simpler, less expensive models performed best in
this study. Copyright (C) 1998 by W.B. Saunders Company.