Yapısal model belirlenmesi için birleşik test

Aim of this thesis is to propose a test statistic that can test for truestructural model in time series. Main concern of the thesis is to suggest a teststatistic, which has joint null of unit root and no structural break (differencestationary model). When joint null hypothesis is rejected, source of deviation fromthe null model may be structural break or (and) stationarity. Sources of thedeviation correspond to different structural models: Pure stationary model, trend-break stationary model and trend-break with unit root model. The thesis suggests atest statistic that can discriminate null model from alternative models and moreimportantly, one alternative model from another. The test statistic that is proposedin the thesis is able to detect specific source of deviation from the null model. Bydoing so, we can determine the true structure model in time series. The thesisiiicompares power properties of the test statistic that is proposed with the mostfavorable test in the literature. Simulation results indicate the power dominanceover the test statistics in the literature. Moreover, we are able to specify truealternative model.Key Words: Unit root, Structural Break, Joint Hypothesis Testing, Monte CarloSimulations