Repeated Measures Design for Empirical Researchers

J. P. Verma

• Publisher: Wiley
• Year: 2015
• Print ISBN: 9781119052715
• eBook ISBN: 9781119052500
• Edition: 1
• Topic: Biological Sciences
• Subtopic: Science General
• Index: Biological Sciences

Introduces the applications of repeated measures design processes with the popular IBM® SPSS® software

Repeated Measures Design for Empirical Researchers presents comprehensive coverage of the formation of research questions and the analysis of repeated measures using IBM SPSS and also includes the solutions necessary for understanding situations where the designs can be used. In addition to explaining the computation involved in each design, the book presents a unique discussion on how to conceptualize research problems as well as identify appropriate repeated measures designs for research purposes.

Featuring practical examples from a multitude of domains including psychology, the social sciences, management, and sports science, the book helps readers better understand the associated theories and methodologies of repeated measures design processes. The book covers various fundamental concepts involved in the design of experiments, basic statistical designs, computational details, differentiating independent and repeated measures designs, and testing assumptions. Along with an introduction to IBM SPSS software, Repeated Measures Design for Empirical Researchers includes:

• A discussion of the popular repeated measures designs frequently used by researchers, such as one-way repeated measures ANOVA, two-way repeated measures design, two-way mixed design, and mixed design with two-way MANOVA
• Coverage of sample size determination for the successful implementation of designing and analyzing a repeated measures study
• A step-by-step guide to analyzing the data obtained with real-world examples throughout to illustrate the underlying advantages and assumptions
• A companion website with supplementary IBM SPSS data sets and programming solutions as well as additional case studies

Repeated Measures Design for Empirical Researchers is a useful textbook for graduate- and PhD-level students majoring in biostatistics, the social sciences, psychology, medicine, management, sports, physical education, and health. The book is also an excellent reference for professionals interested in experimental designs and statistical sciences as well as statistical consultants and practitioners from other fields including biological, medical, agricultural, and horticultural sciences.

J. P. Verma, PhD, is Professor of Statistics and Director of the Center for Advanced Studies at Lakshmibai National Institute of Physical Education, India. Professor Verma is an active researcher in sports modeling and data analysis and has conducted many workshops on research methodology, research designs, multivariate analysis, statistical modeling, and data analysis for students of management, physical education, social science, and economics. He is the author of Statistics for Exercise Science and Health with Microsoft® Office Excel®, also published by Wiley.

Chapter 1
Foundations of Experimental Design

Introduction

Empirical research provides knowledge to the researchers through direct or indirect observations or experiences. Empirical research may either involve correlational or experimental approach. In correlational research one looks to establish relationship between two variables. In such studies a premise is made that two variables may be related in some way and then values of both the variables are obtained under different conditions to test a hypothesis if indeed there is a relationship between the two. The obtained correlation is tested for its significance. The drawback of the correlational study is that it does not establish the cause and effect relationship even if the correlation is found to be statistically significant. For instance, if the observed correlation between the caffeine intake and concentration of mind is significant and positive, it cannot be said that caffeine causes concentration. The increase in the concentration due to the increase in the caffeine intake may be due to age, motivation, gender, other lifestyle parameters.

On the other hand, experimental research provides cause and effect relationship because in such experiment a treatment is deliberately administered by a researcher on a group of individuals or objects to see its impact under a controlled environment. In other words, if changes are made in the variable A that leads to changes in variable B, one can conclude that A causes B. For example, to see the impact of exercise on muscular strength a researcher may administer different intensity of exercise to different groups of individuals to see its effect. If a particular intensity of exercise improves muscular strength more than others, one may conclude that exercise intensity causes muscular strength. On the other hand, if there is no difference in the average muscular strength among different exercise groups, it may be inferred that the exercise intensity has nothing to do with muscular strength.

Authenticity in an experimental research is ensured only when an appropriate experimental design is used. Experimental design is a blueprint of the procedures which enables a researcher to test his hypothesis under a controlled environment. It describes the procedure of allocating treatments to the individuals in a sample. There are many ways in which an experimental design can be classified. One such classification is based on the method of allocating treatments to the subjects. On the basis of this criterion, experimental design can be classified into three categories; independent measures design, repeated measures design, and mixed design. In independent measures design each subject gets one and only one treatment, whereas in repeated measures design each subject is tested under all treatments. In mixed design each subject receives one and only treatment of first factor, but gets tested in all the treatments of second factor. This book specifically deals with some of the important repeated measures designs and mixed designs. To understand these designs and its applications, it is important to understand different aspects of experimental research such as principles of experimental design, types of statistical designs, terminologies used, and other considerations in planning an experimental research.

What is Experimental Research?

An experimental research is a process of studying the effect of manipulating independent variable on some dependent variable(s) observed on subjects in a controlled environment. For instance, in studying the effect of progressive relaxation on concentration, the progressive relaxation is an independent variable whereas the concentration is a dependent one. While conducting an experimental research, a researcher always tries to maintain control in an experiment so that valid conclusion can be drawn on the basis of findings. In experimental research the experimenter is allowed to manipulate independent variable to see its impact on the dependent variable. For instance, in the above example the experimenter can decide the duration or the intensity of the progressive relaxation program. Since the experimenter manipulates an independent variable to see its impact on dependent variable, cause and effect relationship can be explained on the basis of findings.

On the other hand in observational study, a researcher collects and analyzes data without manipulating independent variable. Here also the relationship is investigated between independent and dependent variable observed on the subjects. Since researcher is not allowed to manipulate an independent variable, causal interpretations cannot be efficiently made. If relationship is investigated between height and vertical jump performance of sprinters, the observed correlation may not be the strong evidence for causal relationship between them because the independent variable, height, has not been manipulated to see its impact on the vertical jump performance. This is because the experimenter cannot observe the control on the study. The subjects might have different weight, skill, motivation, and fitness level which do not allow interpreting the strong cause and effect relationship between height and the vertical jump performance. The observational study is also known as correlational study or status study.

Since validity of findings in an experiment depends upon the control observed during the experimentation, it is important to design the experiment in such a way so as to minimize the error involved in it. Using appropriate design in an experiment ensures proper allocation of treatments to the subjects so that experimental error is minimized. This ensures internal validity in the experiment. Design of experiment along with its principles has been discussed in detail in the following section.

Design of Experiment and its Principles

Design of experiment can be defined as a roadmap for organizing an experimental study for testing a research hypothesis in an efficient manner. Design of experiment facilitates an experimenter to observe control in an experiment, thereby reducing the experimental error and ensuring internal validity in findings. More specifically it provides a plan according to which treatments are allocated to the subjects in order to reduce experimental error. While planning a study a researcher needs to design an experiment in such a manner that the similarity is ensured among the experiential groups. The experimental error is controlled by controlling the effect of extraneous variables. To design an experiment a researcher must have the knowledge about homogeneity of experimental material or the subjects on which the experiment is required to be conducted. Besides, one should be able to identify those extraneous variables which may affect findings if not controlled. Depending upon the homogeneous conditions of subjects, an experimental design is identified. There are ways and means in testing the efficiency of design used in a research study. The efficiency of two different designs in the same experiment may be compared by using the error variance. This has been shown in Chapter 2. To have the control in an experiment and ensuring maximum accuracy in findings, Ronald A. Fisher has suggested the three basic principles of design of experiment, namely, Randomization, Replication, and Blocking.

Randomization

One of the main principles of design of experiment is randomization. Randomization refers to randomly allocating treatments to the subjects. Randomization ensures similarity in the experimental groups. It controls bias and extraneous variables which might affect findings of the study. Readers must note that the random selection of subjects and random allocation of treatments are two different things. Consider a study in which three different types of beverages, tea, coffee, and soft drink, are compared for their effect on reaction time. If 30 subjects are selected in the study let us see how randomization is done. Firstly, the initial sample of 30 subjects is selected randomly from the population of interest. Out of these subjects three subjects are randomly selected and the treatments are allocated randomly to them. Then another three samples are selected randomly from the remaining lot and treatments are again randomly allocated to them. In this all 30 subjects are assigned to three different treatment groups. In this study selecting 30 sample subjects randomly from the population of interest does not ensure that the treatment groups are similar, but helps the researcher to generalize findings about the population from which the sample has been drawn.

In other words, random selection of subjects ensures external validity in findings. Complete randomization is only possible if subjects are uniform. On the other hand, perfect random allocation of treatments to the subjects ensures that treatment groups...

Table of contents

• Cover
• Title Page
• Copyright
• Table of Contents
• Dedication
• Preface
• Illustration Credits
• Chapter 1: Foundations of Experimental Design
• Chapter 2: Analysis of Variance and Repeated Measures Design
• Chapter 3: Testing Assumptions in Repeated Measures Design Using SPSS
• Chapter 4: One-Way Repeated Measures Design
• Chapter 5: Two-Way Repeated Measures Design
• Chapter 6: Two-Way Mixed Design
• Chapter 7: One-Way Repeated Measures Manova
• Chapter 8: Mixed Design with Two-Way Manova
• Appendix
• Index
• End User License Agreement