The Application Of Multiple Comparison Methods In Stock Selection

With the continual development and progress of the information era,large amount of high-throughput data increasingly emerges,so that the statistical analysis of mega data becomes so important and significant.As one of the main fundamentals in contemporary statistics,multiple testing problems attract many attention.Central and the most important issue to the problems is how to control the overall testing error rate when we simultaneously perform many tests of significance.Since Benjamini and Hochberg proposed a new approach,research of multiple testing problems has focused on the false discovery rate(FDR).in this dissertation,various multiple testing procedures based on FDR are studied and developed.The dissertation consists of six chapters that are organized as follows.In Chapter one,we describe the backgrounds of multiple testing problems,and the topic basis of of this article.In chapter two,we introduce the definition of a variety of overall testing error rate measurements in multiple testing problems,and show their differences and connections.We also introduce knowledge of CAPM model and its development.In Chapter three,we discuss several testing procedures,including improvements of testing over differences methods and testing based on FDR.And how to make tests based on FDR and how to use CAPM model to test.In Chapter four,we do a simulation by R,compared three testing methods,and the conclusion shows that FDR method has great advantages.In Chapter five,we choose stock data and do empirical analysis.Doing multiple testing based on CAPM model,and control FDR.At last,we choose good stocks.In the last Chapter,we made a summary of this whole article,propose existing problems and deficiencies,we hope to find more further improvements.