Premium
A Nonparametric Model for Multiple Recurrences
Author(s) -
Cheuvart B.
Publication year - 1988
Publication title -
journal of the royal statistical society: series c (applied statistics)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.205
H-Index - 72
eISSN - 1467-9876
pISSN - 0035-9254
DOI - 10.2307/2347335
Subject(s) - nonparametric statistics , mathematics , statistics , econometrics , computer science , calculus (dental) , medicine , dentistry
SUMMARY In this paper we present a new statistical model which permits the analysis of clinical trials where each patient is regularly examined for multiple recurrences of a disease. This model, based on logistic regression, allows the estimation of the probability of recurrence adjusted for various concomitant variables, including treatment and patient characteristics. In the absence of missing data, our model turns out to be of the generalised linear type, and the computations can be performed by means of standard programmes. The EM algorithm is adapted here to deal with missing observations. We derive the parameter covariance matrix as well as a x 2 goodness‐of‐fit measure. The method is illustrated using data from a clinical trial on the treatment of superficial (Ta, T1) bladder cancer by local chemotherapy.