Diagnostic Tests Based on Quantile Residuals for Nonlinear Time Series Models

This thesis studies quantile residuals and uses different methodologies to develop test statistics that are applicable in evaluating linear and nonlinear time series models based on continuous distributions. Models based on mixtures of distributions are of special interest because it turns out that for those models traditional residuals, often referred to as Pearson's residuals, are not appropriate. As such models have become more and more popular in practice, especially with financial time series data there is a need for reliable diagnostic tools that can be used to evaluate them. The aim of the thesis is to show how such diagnostic tools can be obtained and used in model evaluation. The quantile residuals considered here are defined in such a way that, when the model is correctly specified and its parameters are consistently estimated, they are approximately independent with standard normal distribution. All the tests derived in the thesis are pure significance type tests and are theoretically sound in that they properly take the uncertainty caused by parameter estimation into account. -- In Chapter 2 a general framework based on the likelihood function and smooth functions of univariate quantile residuals is derived that can be used to obtain misspecification tests for various purposes. Three easy-to-use tests aimed at detecting non-normality, autocorrelation, and conditional heteroscedasticity in quantile residuals are formulated. It also turns out that these tests can be interpreted as Lagrange Multiplier or score tests so that they are asymptotically optimal against local alternatives. Chapter 3 extends the concept of quantile residuals to multivariate models. The framework of Chapter 2 is generalized and tests aimed at detecting non-normality, serial correlation, and conditional heteroscedasticity in multivariate quantile residuals are derived based on it. Score test interpretations are obtained for the serial correlation and conditional heteroscedasticity tests and in a rather restricted special case for the normality test. In Chapter 4 the tests are constructed using the empirical distribution function of quantile residuals. So-called Khmaladze s martingale transformation is applied in order to eliminate the uncertainty caused by parameter estimation. Various test statistics are considered so that critical bounds for histogram type plots as well as Quantile-Quantile and Probability-Probability type plots of quantile residuals are obtained. Chapters 2, 3, and 4 contain simulations and empirical examples which illustrate the finite sample size and power properties of the derived tests and also how the tests and related graphical tools based on residuals are applied in practice.

Non-small cell lung cancer : studies on pathogenesis, tumour targeting and treatment outcomes

Lung cancer accounts for more cancer-related deaths than any other cancer. In Finland, five-year survival ranges from 8% to 13%. The main risk factor for lung cancer is long-term cigarette smoking, but its carcinogenesis requires several other factors. The aim of the present study was to 1) evaluate post-operative quality of life, 2) compare clinical outcomes between minimally invasive and conventional open surgery, 3) evaluate the role of oxidative stress in the carcinogenesis of non-small lung cancer (NSCLC), and 4) to identify and characterise targeted agents for therapeutic and diagnostic use in surgery. For study I, pneumonectomy patients replied to 15D quality of life and baseline dyspnea questionnaires. Study III involved a prospective quality of life assessment using the 15D questionnaire after lobectomy or bi-lobectomy. Study IV was a retrospective comparison of clinical outcomes between 212 patients treated with open thoracotomy and 116 patients who underwent a minimally invasive technique. Study II measured parameters of oxidative metabolism (myeloperoxidase activity, glutathione content and NADPH oxidase activity) and DNA adducts. Study V employed the phage display method and identified a core motif for homing peptides. This method served in cell-binding, cell-localisation, and biodistribution studies. Following both pneumonectomy and lobectomy, NSCLC patients showed significantly decreased long-term quality of life. No significant correlation was noted between post-operative quality of life and pre-operative pulmonary function tests. Women suffered more from increased dyspnea after pneumonectomy which was absent after lobectomy or bi-lobectomy. Patients treated with video-assisted thoracoscopy showed significantly decreased morbidity and shorter periods of hospitalization than did open surgery patients. This improvement was achieved even though the VATS patients were older and suffered more comorbid conditions and poorer pulmonary function. No significant differences in survival were noted between these two groups. An increase in NADPH oxidase activity was noted in tumour samples of both adenocarcinoma and squamous cell carcinoma. This increase was independent from myeloperoxidase activity. Elevated glutathione content was noted in tumour tissue, especially in adenocarcinoma. After panning the clinical tumour samples with the phage display method, an amino acid sequence of ARRPKLD, the Thx, was chosen for further analysis. This method proved selective of tumour tissue in both in vitro and in vivo cell-binding assay, and biodistribution showed tumour accumulation. Because of the significantly reduced quality of life following pneumonectomy, other operative strategies should be implemented as an alternative (e.g. sleeve-lobectomy). To treat this disease, implementation of a minimally invasive surgical technique is safe, and the results showed decreased morbidity and a shorter period of hospitalisation than with thoracotomy. This technique may facilitate operative treatment of elderly patients with comorbid conditions who might otherwise be considered inoperable. Simultaneous exposure to oxidative stress and altered redox states indicates the important role of oxidative stress in the pathogenesis and malignant transformation of NSCLC. The studies showed with great specificity and with favourable biodistribution that Thx peptide is specific to NSCLC tumours. Thx thus shows promise in imaging, targeted therapy, and monitoring of treatment response.