Department of Public Health Sciences
|Multivariate statistical modeling of the relationship between task operations and respiratory disorders in California farmers
Wu, J.D., M. R. Orenstein, S. J. Samuels and M. B. Schenker
American Journal of Industrial Medicine. 1999. IN PRESS.
Two multivariate statistical approaches, logistic regression and classification and regression tree (CART), were applied to questionnaire collected data sets to model the relationship between exposure and respiratory disorders. The exposure was characterized by task operations or days spent on tasks. The respiratory disorders concerned in this study were doctor-diagnosed asthma, chronic bronchitis, chronic cough, work limited by lung problems, and persistent wheeze. A learning data set was used to build multiple logistic regression and CART models. A test data set was used to validate the models. Statistically significant multiple logistic regression models were observed. Sensitivity and specificity of multiple logistic regression and CART models were calculated. Generally speaking, the CART models performed better than the multiple logistic models. Most of the CART models had sensitivity equal or greater than 0.60 and specificity greater than 0.50 for the test data set. Except for smoking status and age, some important tasks repeatedly appearing in the models were field supervision; tractor driving; mixing, loading or applying pesticides; shop work such as equipment maintenance and repair, welding, grinding; planting or seeding; ground preparation. A healthy worker effect possibly occurred in the work population. Future studies may use CART to explore the association between exposure and health effect, and conduct multiple logistic regression analysis to estimate the unit change of disease risk if more quantitative estimation is needed. Such statistical models not only explore the association between exposure and health outcomes but also provide information to identify the agents responsible for the respiratory disorders and to develop control strategies to reduce the relevant agent exposure.
UC Davis Health System is pleased to provide this information for
general reference purposes only. It should not be considered as
a substitute for professional medical advice. You are urged to consult
with your health care provider for diagnosis of and treatment for
any health-related condition. The information provided herein may
not and should not be used for diagnosis and treatment.
Reproduction of material on this web site is hereby granted solely
for personal use. No other use of this material is authorized without
prior written approval of UC Regents.