Survival Analysis and Generalized Estimating Equations for Repeated Measures in Mosquito Dose-Response

Abstract

Dose-response studies in arthropod research usually involve observing and collecting successive information at different times on the same group of organisms (insects) exposed to different concentrations of stimulus such as botanical extracts. When successive observations are made on the same group of organisms at several concentrations over time the data becomes correlated. Correlated insect mortality data cannot be analyzed using Probit Analysis technique which is the usual way of analyzing data from bioassay experiments. In addition, when the speed of kill is of interest since mortality varies over time, estimating lethal time is the best. The objective of the study was to evaluate a complementary approach, Survival Analysis and repeated measures logistic regression using Generalized Estimating Equations, for lethal time determination in mosquito dose response. Mortality data from anopheles larva exposed to botanical extracts of different concentrations were used in the study. The Kaplan-Meier survival analysis technique and repeated measures logistic regression using GEE were used in estimating lethal time (LT50) of the botanical extracts for control of mosquito larva and their performances were then compared. Results of this study suggest that different botanical extracts and the different concentration levels were significantly different from each other. Concentration 500 mg/ml was found to the most virulent chemical across all extracts, followed by concentration 250 mg/ml and concentration 50 mg/ml was the least active. The confidence intervals of the LT50 estimates from repeated measures logistic regression using GEE were consistently wider compared to those from Kaplan-Meier. Kaplan-Meier survival function and repeated measures logistic regression using GEE were effective tools for analyzing repeated v measures data from mosquito dose response. Repeated measures logistic regression using GEE was a better method of estimating LT50 since it consistently gave precise LT50 estimates with a smaller confidence interval. It’s suggested that the repeated measures logistic regression using GEE method can be incorporated into arthropod dose response studies for repeated measures together with other existing methods for analyzing data from bioassay experiments.