AN APPLICATION OF MARKOV PROCESSES TO THE STUDY OF THE EPIDEMIOLOGY OF MENTAL DISEASE
成果类型：
Article
署名作者：
MARSHALL, AW; GOLDHAMER, H
刊物名称：
JOURNAL OF THE AMERICAN STATISTICAL ASSOCIATION
ISSN/ISSBN：
0162-1459
DOI：
10.2307/2281101
发表日期：
1955
页码：
99-129
关键词：
摘要：
In epidemiological studies of disease, both the incidence measure (proportion of a population affected for the first time in a given period) and the prevalence measure (proportion of a population affected at a given time) are important. Methods for estimating these rates usually require expensive and time-consuming field investigations limited to small segments of the population. Furthermore, age-specific measures are frequently based on hospital records which give age-at-admission rather than age-at-onset. The authors found that mental hospitals in Ohio and Illinois had records of both kinds of data, and they have considered various models based on stochastic processes of the Markov type which may be used to estimate prevalence rates, and from these, incidence rates. Primarily to illustrate how the models are used and what data and assumptions are necessary, the method is applied to the aforementioned hospital records and age-specific rate estimates are computed.