Mixed logit model and its application in insurance choices of the new rural cooperative medical system / 南方医科大学学报

<p><b>OBJECTIVE</b>To apply mixed logit model for analyzing the data of new rural cooperative medical with suitability and identify the factors affecting the residents choices of insurance mode.</p><p><b>METHODS</b>Hypothesis test of IIA was performed using the mogtest module of Stata10.0 to test the eligibility of the condition. The mixed logit model was established to allow the parameters to vary in the population using SAS9.1 MDC module.</p><p><b>RESULTS</b>The data in this study did not satisfy the IIA assumption (P<0.01), so that the multinomial logit model was not applicable. The adjusted Estrella of the mixed logit model was 0.6658.</p><p><b>CONCLUSION</b>The mixed logit approach does not rely on the restrictive IIA assumption and allows for correlation patterns between choices and individual variation. This approach can help in the determination of the choices in new rural cooperative medical system.</p>

An age-period-cohort modelling study on primary liver cancer incidence rate in Qidong / 中华流行病学杂志

<p><b>OBJECTIVE</b>To analyze the incidence trends of primary liver cancer (PLC) in Qidong.</p><p><b>METHODS</b>Data of PLC incidence from 1975 to 1999 in Qidong were analyzed to delineate temporal trends and birth cohort patterns, using age-period-cohort models.</p><p><b>RESULTS</b>Significant moderation or decreasing trends were began to notice in incidence rates on cohorts born in 1913 - 1917 and 1958 - 1962.</p><p><b>CONCLUSION</b>Results showed that the incidence risk of the birth cohorts after 1958 - 1962 started to decline. The changes were possibly associated with the implementation of some practical measures on prevention.</p>