Analysing the effects of anaemia on local recurrence of head and neck cancer when covariate values are missing

We present a case study in the analysis of the prognostic effects of anaemi a and other covariates on the local recurrence of head and neck cancer in p atients who have been treated with radiation therapy. Because it is believe d that a large fraction of the patients are cured by the therapy, we use a failure time mixture model for the outcomes, which simultaneously models bo th the relationship of the covariates to cure and the relationship of the c ovariates to local recurrence times for subjects who are not cured. A probl ematic feature of the data is that two covariates of interest having missin g values, so that only 75 per cent of the subjects have complete data. We h andle the missing-data problem by jointly modelling the covariates and the outcomes, and then fitting the model to all of the data, including the inco mplete cases. We compare our approach to two traditional methods for handli ng missingness, that is, complete-case analysis and the use of an indicator variable for missingness. The comparison with complete-case analysis demon strates gains in efficiency for joint modelling as well as sensitivity of s ome results to the method used to handle missing data. The use of an indica tor variable yields results that are very similar to those from joint model ling for our data. We also compare the results obtained for the mixture mod el with results obtained for a standard (non-mixture) survival model. It is seen that the mixture model separates out effects in a way that is not pos sible with a standard survival model. In particular, conditional on other c ovariates, we find strong evidence of an association between anaemia and cu re, whereas the evidence of an association between anaemia and time to loca l recurrence for patients who are not cured is weaker. Copyright (C) 2000 J ohn Wiley gr Sons, Ltd.