Quantitative and Statistical Research Methods

From Hypothesis to Results

William E. Martin, Krista D. Bridgmon

• Publisher: Jossey-Bass
• Year: 2012
• Print ISBN: 9780470631829
• eBook ISBN: 9781118234570
• Edition: 1
• Topic: Social Sciences
• Subtopic: Social Science Research & Methodology
• Index: Social Sciences

Quantitative and Statistical Research Methods

This user-friendly textbook teaches students to understand and apply procedural steps in completing quantitative studies. It explains statistics while progressing through the steps of the hypothesis-testing process from hypothesis to results. The research problems used in the book reflect statistical applications related to interesting and important topics. In addition, the book provides a Research Analysis and Interpretation Guide to help students analyze research articles.

Designed as a hands-on resource, each chapter covers a single research problem and offers directions for implementing the research method from start to finish. Readers will learn how to:

• Pinpoint research questions and hypotheses
• Identify, classify, and operationally define the study variables
• Choose appropriate research designs
• Conduct power analysis
• Select an appropriate statistic for the problem
• Use a data set
• Conduct data screening and analyses using SPSS
• Interpret the statistics
• Write the results related to the problem

Quantitative and Statistical Research Methods allows students to immediately, independently, and successfully apply quantitative methods to their own research projects.

Chapter 1

INTRODUCTION AND OVERVIEW

LEARNING OBJECTIVES

• Understand the purpose of the book and the structure of the book.
• Review independent, dependent, and extraneous variables and their scales of measurement.
• Review measures of central tendency and variability.
• Review visual representations of data, including the normal distribution.
• Review descriptive and inferential statistical applications of the normal distribution.

The purpose of this book is to provide a hands-on approach for students to understand and apply procedural steps in completing quantitative studies. The book emphasizes a step-by-step guide using research examples for students to move through the hypothesis-testing process for commonly used statistical procedures and research methods. Statistical and research designs are integrated as they are applied to the examples. The structure of each chapter covers the following nine quantitative research procedural steps:

1. A description of a research problem, taking the student through identifying research questions and hypotheses.

2. A method of identifying, classifying, and operationally defining the study variables.

3. A discussion of appropriate research designs.

4. A procedure for conducting an a priori power analysis.

5. A discussion of choosing an appropriate statistic for the problem.

6. A statistical analysis of a data set.

7. A process for conducting data screening and analyses (IBM SPSS) to test null hypotheses.

8. A discussion of interpretation of the statistics.

9. A method of writing the results related to the problem.

The underlying philosophy of the book is to view the quantitative research process from a more holistic and sequential perspective. Concepts are discussed as they are applied during the procedural steps. It is hoped that after completion of the book readers will be better able to plan research and conduct statistical analyses using several commonly used statistical and research designs. The quantitative methodological tools learned by students can actually be applied to their own research, hopefully with less oversight by faculty.

The use of statistical software is an essential tool of researchers. Psychological, educational, social, and behavioral areas of research typically have multifactor or multivariate explanations. Statistical software provides a researcher with sophisticated techniques to analyze the effects and relationships among many independent variables (factors) and dependent variables (variates) in various combinations all at once and instantly. We will use IBM SPSS statistical software, which has been developed over many decades and is one of the most widely used statistics programs in the world.

Statistical techniques may have more meaning, understandability, and relevance when learned within the context of research. One needs to have an understanding of statistical analyses to consume and construct professional research competently. Knowledge of quantitative research methods is especially important today because of the emphasis on evidence-based practice in psychology (EBPP) to improve clinical work with clients. EBPP refers to using the best available research with clinical expertise in the context of patient characteristics, culture, and preferences (American Psychological Association, 2006).

Ideally, the goal is to help a student achieve self-efficacy in understanding, planning, and conducting actual independent research. Information and skills grow, leading to advanced understanding. We next present a review of foundational information related to research and statistics that will be useful to review prior to completing the chapters that follow.

REVIEW OF FOUNDATIONAL RESEARCH CONCEPTS

A review of foundational concepts related to research and statistics is presented next. Quantitative research involves the interplay among variables after they have been operationalized, allowing a researcher to measure study outcomes. Essential statistical methods used to assess scores of variables include central tendency, variability, and the characteristics of the normal distribution.

Independent, Dependent, and Extraneous Variables

At the core of quantitative research is studying and measuring how variables change. Kerlinger and Pedhazur (1973) stated, “It can be asserted that all the scientist has to work with is variance. If variables do not vary, if they do not have variance, the scientist cannot do his work” (p. 3). Even the father of modern statistics, Sir Ronald Fisher (1973), said, “Yet, from the modern point of view, the study of the causes of variation of any variable phenomenon, from the yield of wheat to the intellect of man, should be begun by the examination and measurement of the variation which presents itself” (p. 3).

An independent variable (IV) in a study is the presumed cause variable. In experimental research, the IV is designed and employed to influence some other variable. It is an antecedent condition to an observed resultant behavior. Changes in the independent variable produce changes in the dependent variable.

All variables need to be able to vary. Kerlinger and Lee (2000) identified two types of independent variables: active and attribute. An active independent variable is one that is manipulated by the researcher. For example, a researcher designs a study with an IV that has a researcher-specified treatment condition compared to a no-treatment control condition. Other terms used for an active IV are stimulus variable, treatment variable, experimental variable, intervention variable, and X variable.

A second type of IV is called an attribute independent variable, which is not manipulated but is ready-made or has preexisting values such as gender, age, or ethnocultural grouping. Other terms used are organismic or personological variables.

The terms classification variable and categorical variable are often used as an IV label. They can be used as either active or attribute types. For example, a manipulated IV that has a treatment condition and a control condition could be called a classification variable. Also, an attribute variable such as gender (male or female) may be referred to as a classification or categorical variable.

A dependent variable (DV) is the presumed resulting outcome in research. It is u...

Table of contents

• Cover
• Contents
• Title
• Copyright
• Tables and Figures
• Preface
• The Authors
• Dedication
• Chapter 1: Introduction and Overview
• Chapter 2: Logical Steps of Conducting Quantitative Research
• Chapter 3: Maximizing Hypothesis Decisions Using Power Analysis
• Chapter 4: Research and Statistical Designs
• Chapter 5: Introduction to IBM SPSS 20
• Chapter 6: Diagnosing Study Data for Inaccuracies and Assumptions
• Chapter 7: Randomized Design Comparing Two Treatments and a Control Using a One-Way Analysis of Variance
• Chapter 8: Repeated-Treatment Design Using a Repeated-Measures Analysis of Variance
• Chapter 9: Randomized Factorial Experimental Design Using a Factorial ANOVA
• Chapter 10: Analysis of Covariance
• Chapter 11: Randomized Control Group and Repeated-Treatment Designs and Nonparametics
• Chapter 12: Bivariate and Multivariate Correlation Methods Using Multiple Regression Analysis
• Chapter 13: Understanding Quantitative Literature and Research
• References
• Index