DIGIT PREFERENCE IN ESTIMATED GESTATIONAL-AGE

被引:17
作者
PICKERING, RM
机构
[1] University of Southampton, Southampton General Hospital, Southampton, S09 4XY, South Academic Block
关键词
D O I
10.1002/sim.4780110908
中图分类号
Q [生物科学];
学科分类号
07 ; 0710 ; 09 ;
摘要
A digit preference model is developed to describe the preference for estimating gestational age at birth as an even week during the 20th to 36th week of gestation. The model incorporates a probability of misclassification to adjacent even weeks at odd gestational ages, while even gestational ages are assumed correctly classified. The model is extended to allow the misclassification probabilities to decrease linearly with week during the period. A piecewise exponential model is used to model relative risks of delivery associated with a previous spontaneous abortion and a model incorporating digit preference is fitted as a generalized bilinear model in GLIM. The estimates of relative risk in the underlying survival model are virtually the same whether the misclassification is incorporated in the model or ignored.
引用
收藏
页码:1225 / 1238
页数:14
相关论文
共 7 条
[1]  
Pickering R.M., Deeks J.J., Risks of delivery during the 20th to the 36th week of gestation, International Journal of Epidemiology, 20, pp. 456-466, (1991)
[2]  
Holford T.R., The analysis of rates of survivorship using log‐linear models, Biometrics, 36, pp. 1106-1112, (1980)
[3]  
Thompson R., Baker R.J., Composite link functions in generalized linear models, Applied Statistics, 30, pp. 125-131, (1981)
[4]  
Payne C.D., The GLIM System Release 3.77 Manual, (1985)
[5]  
Diaconis P., Efron B., Computer‐intensive methods in statistics, Scientific American, 248, 5, pp. 96-108, (1983)
[6]  
Pullum T.W., Statistical methods to adjust for date and age misreporting to improve estimates of vital rates in Pakistan, Statistics in Medicine, 10, pp. 191-200, (1991)
[7]  
Ridout M.S., Morgan B.J.T., Modelling digit preference in fecundability studies, Biometrics, 47, pp. 1423-1433, (1991)