Using classification and regression trees : a practical primer / authored by Xin Ma, (University of Kentucky).

Format:

Book

Author/Creator:

Ma, Xin, 1963- author.

Language:

English

Subjects (All):

Education--Research--Statistical methods.

Education.

Discriminant analysis.

Regression analysis.

Physical Description:

1 online resource (166 pages)

Place of Publication:

Charlotte, NC : Information Ages Publishing, Inc., [2018]

Summary:

Classification and regression trees (CART) is one of the several contemporary statistical techniques with good promise for research in many academic fields. There are very few books on CART, especially on applied CART.This book, as a good practical primer with a focus on applications, introduces the relatively new statistical technique of CART as a powerful analytical tool. The easy-to-understand (non-technical) language and illustrative graphs (tables) as well as the use of the popular statistical software program (SPSS) appeal to readers without strong statistical background. This book helps readers understand the foundation, the operation, and the interpretation of CART analysis, thus becoming knowledgeable consumers and skillful users of CART.The chapter on advanced CART procedures not yet well-discussed in the literature allows readers to effectively seek further empowerment of their research designs by extending the analytical power of CART to a whole new level. This highly practical book is specifically written for academic researchers, data analysts, and graduate students in many disciplines such as economics, social sciences, medical sciences, and sport sciences who do not have strong statistical background but still strive to take full advantage of CART as a powerful analytical tool for research in their fields.

Contents:

Preface

Introduction

Scientific reasoning in the computer age

Making the case for inductive or data-driven research

Putting the case in a practical perspective

Demonstration of CART as an exploratory technique

Advantages of art

Notes

Statistical principles of CART

Important functions of cart

Statistical concepts of CART

Statistical procedures of CART

Growing the CART tree

Stopping the cart tree

Pruning the cart tree

Basic techniques of care

Statistical techniques of classification trees

Using costs and priors

Statistical techniques of regression trees

Using cost complexity

Contents

Using r-squared

Using surrogates

Issues in cart

Analysis

CART versus traditional statistical techniques

Formulating research questions

Determining important variables

Revealing unique variables

Examining terminal nodes

Handling missing data

Determining node size

Assessing cart performance

Applications of cart

Operation of CART software programs

Application 1: Growth in mathematics achievement during middle and high school

Application 2: Dropping out of advanced mathematics in middle and high school

Application 3: Science coursework among tenth graders in high school

Advanced techniques of cart

Extending analytical power of cart

Concept of hybrid statistical models

Longitudinal cart analysis

Multivariate cart analysis

Multilevel cart analysis

Cart procedure for meta-analysis

Concluding statement

References

A functionally equivalent binary tree

B common cart software programs

C spss decision tree syntax

SPSS decision tree output

E SPSS decision tree syntax using costs and profits

F SPSS decision tree syntax using priors

G SPSS decision tree syntax for drinking and smoking data

H SPSS decision tree syntax for mental health

And physical health data

I SPSS decision tree syntax for cart produce for meta-analysis

About the author.

Notes:

Includes bibliographical references.

Print version record.

ISBN:

1-64113-239-6

OCLC:

1031544297