Hypothesis Testing in Econometrics

This paper reviews important concepts and methods that are useful for hypothesis testing.First, we discuss the Neyman-Pearson framework. Various approaches to optimalityare presented, including finite-sample and large-sample optimality. Then, some of the mostimportant methods are summarized, as well as resampling methodology which is useful toset critical values. Finally, we consider the problem of multiple testing, which has witnesseda burgeoning literature in recent years.[...]

MoreLess

Year of publication:	2009-09-01
Authors:	Romano, Joseph P. ; Shaikh, Azeem M. ; Wolf, Michael
Institutions:	National Centre of Competence in ResearchFinancial Valuation and Risk Management
Subject:	Multipler Test \| multiple testing \| Resampling \| resamplin \| Optimum \| optimal stopping

freely available

Full text |

More access options

Check Google Scholar

In German libraries (KVK)

I need help

1 INTRODUCTION
2 THE NEYMAN-PEARSON PARADIGM
3 CONTROL OF THE SIZE OF A TEST
3.1 p-Values
3.2 The Bahadur-Savage Result
4 OPTIMALITY CONSIDERATIONS
4.1 UMPU Tests
4.2 Conditional Tests
4.3 UMPI Tests
4.4 Monotone Tests
4.5 Maximin Tests
4.6 Tests Maximizing Average or Weighted Power
4.7 Locally Most Powerful Tests
5 LARGE-SAMPLE CONSIDERATIONS
5.1 Asymptotic Optimality
6 METHODS FOR HYPOTHESIS TESTING
6.1 Testing in Parametric Models using Likelihood Methods
6.2 Testing in the Extremum Estimation Framework
7 CONSTRUCTION OF CRITICAL VALUES
7.1 Randomization Methods
7.2 Bootstrap
7.3 Subsampling
8 MULTIPLE TESTING
8.1 Motivation
8.2 Notation and Various Error Rates
8.3 Single-step vs. Stepwise Methods
8.4 Methods Based on Individual p-Values
8.5 Resampling Methods Accounting for Dependence
References

Persistent link: https://www.econbiz.de/10005868540