Heteroscedasticity Test for Partial Linear EV Model with Missing Response Variables

This paper mainly considers the problem of heteroscedasticity test for partial linear EV model with missing response variables. First, use the completely observed data to estimate the unknown parameters and smooth function of the model, and then use the regression method to fill in the missing data. Then, the empirical likelihood ratio statistic for testing the heteroscedasticity of the random error of the model is established, and it is proved that the statistic asymptotically obeys the chi-square distribution. Finally, the nature of the limited sample of the test under different missing probabilities is studied through numerical simulation, and the partial linear EV model is used in the case analysis to test the missing data for heteroscedasticity.