Confidence Regions in Curved Exponential Families: Application to Matched Case-Control and Survival Studies with General Relative Risk Function
Moolgavkar, Suresh H. ; Venzon, David J.
Ann. Statist., Tome 15 (1987) no. 1, p. 346-359 / Harvested from Project Euclid
Differential geometric methods are used to construct approximate confidence regions for curved exponential families. The $\alpha$-connection geometries discussed by Amari (1982), and another geometry introduced here, the $c$ geometry, are exploited to construct confidence regions. Survival and case-control studies with general relative risk functions are interpreted in the context of curved exponential families, and an example illustrates the construction of confidence regions for matched case-control studies. Simulations indicate that the geometric procedures have good coverage and power properties.
Publié le : 1987-03-14
Classification:  Alpha connections,  differential geometry,  inference,  logistic regression,  partial likelihood,  variance-stabilizing parametrizations,  62E20,  62B10
@article{1176350270,
     author = {Moolgavkar, Suresh H. and Venzon, David J.},
     title = {Confidence Regions in Curved Exponential Families: Application to Matched Case-Control and Survival Studies with General Relative Risk Function},
     journal = {Ann. Statist.},
     volume = {15},
     number = {1},
     year = {1987},
     pages = { 346-359},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176350270}
}
Moolgavkar, Suresh H.; Venzon, David J. Confidence Regions in Curved Exponential Families: Application to Matched Case-Control and Survival Studies with General Relative Risk Function. Ann. Statist., Tome 15 (1987) no. 1, pp.  346-359. http://gdmltest.u-ga.fr/item/1176350270/