The Gradient Test
Another Likelihood-Based Test
- 1st Edition - February 3, 2016
- Author: Artur Lemonte
- Language: English
- Paperback ISBN:9 7 8 - 0 - 1 2 - 8 0 3 5 9 6 - 2
- eBook ISBN:9 7 8 - 0 - 1 2 - 8 0 3 6 1 3 - 6
The Gradient Test: Another Likelihood-Based Test presents the latest on the gradient test, a large-sample test that was introduced in statistics literature by George R. Terrell i… Read more
The Gradient Test: Another Likelihood-Based Test presents the latest on the gradient test, a large-sample test that was introduced in statistics literature by George R. Terrell in 2002. The test has been studied by several authors, is simply computed, and can be an interesting alternative to the classical large-sample tests, namely, the likelihood ratio (LR), Wald (W), and Rao score (S) tests.
Due to the large literature about the LR, W and S tests, the gradient test is not frequently used to test hypothesis. The book covers topics on the local power of the gradient test, the Bartlett-corrected gradient statistic, the gradient statistic under model misspecification, and the robust gradient-type bounded-influence test.
- Covers the background of the gradient statistic and the different models
- Discusses The Bartlett-corrected gradient statistic
- Explains the algorithm to compute the gradient-type statistic
Can be used for a graduate course. Additionally, it can be used by researchers who are interested in developing research in likelihood-based theory. Links theory and practice and hence a lot of researchers of many areas can use the book as a reference for the gradient test
Chapter 1: The Gradient Statistic
- Abstract
- 1.1 Background
- 1.2 The Gradient Test Statistic
- 1.3 Some Properties of the Gradient Statistic
- 1.4 Composite Null Hypothesis
- 1.5 Birnbaum-Saunders Distribution Under Type II Censoring
- 1.6 Censored Exponential Regression Model
Chapter 2: The Local Power of the Gradient Test
- Abstract
- 2.1 Preliminaries
- 2.2 Nonnull Distribution up to Order O(n−1/2)
- 2.3 Power Comparisons Between the Rival Tests
- 2.4 Nonnull Distribution Under Orthogonality
- 2.5 One-Parameter Exponential Family
- 2.6 Symmetric Linear Regression Models
- 2.7 GLM With Dispersion Covariates
- 2.8 Censored Exponential Regression Model
Chapter 3: The Bartlett-Corrected Gradient Statistic
- Abstract
- 3.1 Introduction
- 3.2 Null Distribution up to Order O(n−1)
- 3.3 The One-Parameter Case
- 3.4 Models With Two Orthogonal Parameters
- 3.5 Birnbaum-Saunders Regression Models
- 3.6 Generalized Linear Models
Chapter 4: The Gradient Statistic Under Model Misspecification
- Abstract
- 4.1 Introduction
- 4.2 The Robust Gradient Statistic
- 4.3 Examples
- 4.4 Numerical Results
Chapter 5: The Robust Gradient-Type Bounded-Influence Test
- Abstract
- 5.1 Introduction
- 5.2 The Robust Gradient-Type Test
- 5.3 Robustness Properties
- 5.4 Algorithm to Compute the Gradient-Type Statistic
- 5.5 Closing Remarks
- Edition: 1
- Published: February 3, 2016
- Language: English
AL
Artur Lemonte
Artur J. Lemonte is a professor at Federal University of Pernambuco, Department of Statistics, Recife/PE, Brazil. He works on higher order asymptotics, mathematical statistics, regression models, parametric inference, and distribution theory. In the last years, he has published more than 60 papers in refereed
statistical journals (most of them about the gradient test).
Affiliations and expertise
Department of Statistics, Federal University of Pernambuco, Recife/PE, BrazilRead The Gradient Test on ScienceDirect