Abstract
In this paper, we study tests of hypotheses for regression parameters in the heteroscedastic transformation model. In this model, three methods which are discrete, sieve and ROC methods are used to estimate the parameters; and each method uses the large-sample tests for the location parameters and scale parameters. These test procedures used in survival analysis are based on the asymptotic properties of the likelihood, and the tests we propose are likelihood ratio test, Wald test, and score test. Their type-one error and power are compared to that of previously described tests by using simulation experiments. Finally a real data of heroin addicts is presented as an illustration.