EXPRESS STATISTICS "Hassle Free" ® For Public Administrators, Educators, Students, and Research Practitioners

By Lewis Liddell

Looking for a research idea for your thesis or dissertation, look no further. This book contains scores of research examples that can be developed into a comprehensive research study, including survey instrument construction, sampling techniques, and many other research tools.

The goal of EXPRESS STATISTICS

• Language: English
• Publisher: Creative Software Systems
• Release date: Jan 6, 2020
• ISBN: 9781087864341

Lewis Liddell

Lewis Liddell, the author has an earned doctorate. He has experience in higher education, including Assistant to the President, Director of Institutional Research, Director of Affirmative Action, Assitant to the Dean of the College of Arts and Sciences, Department Chair, and was on the faculty of the five comprehensive research universities. Also, Liddell has been writing software since 1975. These experiences have given the author a broad understanding of attitudes toward research and statistics.

Book preview

EXPRESS STATISTICS "Hassle Free"

EXPRESS STATISTICS Hassle Free

For

Public Administrators, Educators, Students,

and Research Practitioners

Copyright © 2017 by Lewis Liddell

All Rights Reserved. No part of this book or software may be reproduced in any form without the permission of the author. For information contact Creative Software Systems PO Box 10171, Jackson, MS 39286 or by email at [e-mail]

ISBN 978-164467007-1

ISBN 978-108786434-1 (e-book)

The driving force behind this book, What Is Statistics?

Results from rolling dices and shuffling cards are based on naked probability and chance. On the other hand, results from statistical analysis are based on systematic observations and batteries of comparisons and calculations. Moreover, Kerlinger (1986), in his celebrated text Foundations of Behavioral Research, defined statistics, as stated below:

Statistics is the theory and method of analyzing quantitative data obtained from samples of observations in order to study and compare sources of variance of phenomena, to help make decisions to accept or reject hypothesized relations between the phenomena, and to aid in making reliable inferences from empirical observations (p. 175).

The above menacing-looking statistical formulas need not perturb users of the software, the formulas are not visible, and all calculations are done in the background. Hence, in this book and software, the emphasis is on objectivity, clarity, simplicity, and, most of all, Hassle-Free.

The examples presented in this book and computer software are hypothetical, and the data used are fictitious; no particular viewpoint intended.

To my wife, Frances, and our six children: Lewis, Jr., Ollie, Jeremiah, Frances, Christie, Calvin; and our grandchildren Jasmine, and Ollie, II.

Contents

Preface

Acknowledgments

Software/System Overview

Software Warranty

Chapter 1.Introduction

1.1.The Purpose of the Book

1.2.Statistics and Concepts

Chapter 2.Data Entry

2.1.Data Entry Overview

2.1.1.Creating a Data File Using the Default Data Entry

2.2.Data File Types

2.2.1.Primary Statistics Data Type

2.2.2.Reliability Coefficient Data

2.2.3.Contingency Table (chi-square data file)

2.2.4.Multiple Choice, True-False, and Likert Data Type

2.3.Working with Multiple Choice, True-False, and Likert Data Type Files

2.4.Explanation of Menu Prompts

2.4.1.Enter Headings for Each Subscale

2.4.2.Print to Screen

2.4.3.Chi-square Observed Frequencies and Expected Frequencies

2.4.4.Display Frequency Counts and Percentages Only

2.4.5.Convert Data to Contingency Table

2.4.6.Convert Data to Primary Data File

2.4.7.Help--Call the Help Routine

2.4.8.Continue Execution

2.5.Comma Delimited Files and Standard Commercial Spreadsheets

Chapter 3.Common Sense vs. the Scientific Approach

3.1.Common Sense

3.2.The Scientific Approach

3.3.An Outline of a Typical Study and the Scientific Approach

3.4 A Few Points to Consider when Evaluating a Research Study

Chapter 4.Data Types

4.1.Overview of Data Types

4.1.1.Nominal Data

4.1.2.Ordinal Data

4.1.3.Interval Data

4.1.4.Ratio Data

4.1.5.Continuous Data

Chapter 5.Independent and Dependent Variables

5.1.Overview of Types of Variables

5.2.Press Release (fictitious)

Chapter 6.Measures of Central Tendency

6.1.Overview of Measure of Central Tendency

6.1.1.Mode

6.1.2.Median

6.1.3.Mean

Chapter 7.Measures of Variability

7.1.Definition of Measures of Variability

7.1.1.Range

7.1.2.Variance

7.1.3.Standard Deviation (STD)

Chapter 8.The Normal Distribution

Chapter 9.Probability

9.1.A Brief Discussion on Probability

Chapter 10.Random Sampling

10.1.A Brief Discussion of Random Sampling

10.2.Types of Random Sample

10.2.1.Simple Random Sample

10.2.2.Stratified Sample

10.2.3.Cluster Sample

10.2.4.Systematic Sample

10.2.Sample Size

10.3.The Quick Random Table Generator

10.4.Types of Samples Generated by the Routine

10.4.1.Sampling with Replacement

10.4.2.Sampling without Replacement

10.4.3.Survey Sample

10.4.4.Coin Tossing

10.4.5.Rolling Dice

10.4.6.Generating Lottery Fireball Numbers

Chapter 11.types of statistics

11.1.Descriptive Statistics

11.2.Inferential Statistics

Chapter 12.Types of Statistical Tests

12.1.Types of Statistical Test, An Overview

12.1.1 Parametric Tests

12.1.2.Nonparametric Tests

Chapter 13.Hypotheses Testing

13.1.Hypothesis Definition

13.2.Types of Hypotheses

13.3.Hypothesis Testing: The Concept of Significance

13.4.Hypothesis Testing and Tails

13.5.Statistical Logical Errors

Chapter 14.Basic Descriptive Statistics

14.1.Types of Descriptive Statistics, An Overview

14.2.Terminology Associated with Descriptive Statistics

14.3.Execution of the Descriptive Statistics Routine

14.3.1.Description Variables

14.3.2.Measures of Central Tendency

14.3.3.The Mode and Central Tendency

14.3.4.Measures of Dispersion

14.3.5.Characteristics of Distributions

14.3.6.Frequency of Distributions

14.3.7.Scroll View

14.3.8.Percentile Ranks

14.3.9.Graphics (Descriptive Statistics and Graphics)

14.4.Confidence Interval Routines

14.4.1.Confidence interval within one sample mean

14.4.2.Interval estimation between two independent measures

14.4.3.Interval estimation between two related measures

14.4.4.Interval estimation for a single proportion (percent)

14.4.5.Interval estimation between two proportions (percent)

Chapter 15.Correlation and Association Statistics

15.1.Pearson Product Moment Correlation

15.2.Spearman (rho) Rank Correlation

15.3.Point-Biserial Correlation

15.4.Phi (φ) Coefficient

Chapter 16.The t-Tests

16.1.Correlated/Dependent t-Test

16.2.Independent t-Test

16.3.t-Test, Sample Mean vs. Population Mean

Chapter 17.Wilcoxon Test and The Mann-Whitney U

17.1.Wilcoxon Signed-Ranks Test, An Alternative to the Correlated/Dependent t-Test

17.2.Mann-Whitney U, an Alternative to the Independent t-Test

Chapter 18.Chi-square Analysis, Kolmogorov-Smirnov Statistic, Phi (φ) Coefficient, Cramer’s V, Coefficient of Contingency C, Fisher’s Exact Probability, McNemar’s Test of Two Paired Proportions, Gamma, Somers’ d, and Lambda Coefficients

18.1.Chi-square

18.2.Kolmogorov-Smirnov Test

18.3.Phi (φ) Coefficient

18.4.Cramer’s V

18.5.Coefficient of Contingency C

18.6.Fisher’s Exact Probability Test

18.7.McNemar’s Test of Two Paired Proportions

18.9.Gamma, Somers’ d, and Lambda Coefficients

Chapter 19.Analysis of Variance Statistics

19.1.One-way Parametric Analysis of Variance (ANOVA)

19.2.Two-way Parametric Analysis of Variance (ANOVA)

19.3.One-way Non-Parametric Analysis of Variance (ANOVA)

19.3.3.Post hoc Tests for the Kruskal-Wallis One-way Analysis of Variance and the Friedman One-way Analysis of Variance

19.4.Friedman One-way Analysis of Variance (ANOVA) by Ranks

19.5.Friedman Two-way (Analysis of Variance (ANOVA) by Ranks

19.6.One-way Analysis of Covariance (ANOCVA)

19.7.ANOVA Two Factor Factorial Design

19.8.ANOVA Three Factor Factorial Design

19.9.ANOVA Treatment-by-Levels Design

19.10.ANOVA Treatment-by-Repeated-Measures

19.11.ANOVA Treatments-by-Treatments-by-Repeated-Measures: Two-Factor Design

19.12.ANOVA Two-Factor Mixed Design: Repeated Measures on One Factor

19.13.ANOVA Three-Factor Mixed Design: Repeated Measures on One Factor

19.14.ANOVA Three-Factor Mixed Design: Repeated Measures on Two Factors

19.15.ANOVA Latin Square Design: Simple

19.16.ANOVA Latin Square Design: Complex

Chapter 20.Regression Statistics

20.1.Linear Regression

20.2.Multiple Regression

20.2.2 Include all Independent Variables in One Step

20.2.3.Stepwise Regression by Hierarchy

20.3.Variable Entry Select by User

20.4.Correlation Matrix

20.5.Multicollinearity Check

20.6.Multiple Correlation

Chapter 21.Multivariate Analysis

21.1.Multivariate Correlation t-Test

21.2.Multiple Independent t-Test

21.3.Comparison of Sample Centroid and the Population Value

21.4.Test for Changes Between Two Groups of Specific Measure

21.5.Multivariate Analysis of Variance (MANOVA)

21.5.4.Post hoc analysis

21.5.5.One-way Analysis of Variance (univariate) of Female Subjects

21.5.6.Scheffe’ Analysis of Female Subjects

21.5.7.One-way Analysis of Variance (univariate) of Male Subjects

21.5.9.Scheffe’ Analysis of Male Subjects

21.6.Multivariate Two-Factor Factorial Analysis

Chapter 22.Trends, Times Series, and Forecasting

22.1.An Overview

22.2.The Run Statistics

22.3.Simple Linear Regression, Time Series, Forecasting, and Trend Analysis

Chapter 23.Test Validity and Reliability

23.1.1.Content Validity

23.1.2 Criterion Validity

23.1.3.Concurrent validity

23.2.Reliability Tests

23.3.Setting Up a Data File for Reliability Testing

23.4.Terminology

23.4.1.Nominal Data

23.4.2.Ordinal Data

23.4.3.Interval Data

23.4.4.Ratio Data

23.4.5.Continuous Data

23.5.Two-way Analysis of Variance (ANOVA) Reliability

23.6.Alpha Coefficient Reliability

23.6.1.Reliability and Statistics

23.6.2.Determining the Acceptable Size of the Reliability Coefficient

23.6.3.Enter Subscales

23.6.4.Delete Subscales

23.6.5.Item Correlation Matrix

23.7.Types of Tests and Scales

23.8.Attitudinal Scales and Tests

23.8.1.Likert-Type Scale

23.8.2.Semantic Differential Scale

Appendix A.Validation of Data Gathering Instrument

Appendix B.Student Teaching Problematic Scale

Appendix C.An Affirmative Action Opinionnaire

Appendix D.Student Advisement Questionnaire

Appendix E.The Major Political Parties, Republican Party and the Democratic Party and Hot Button Issues: A Semantic Differential Scale

Appendix F.Research Design, Extraneous Variances and Invalidity

Appendix G.Setting Up a Contingency Table

Appendix H.Factorial Designs

Appendix I.Quick Statistics Finder

Appendix J.Research Examples and Hypotheses/Questions

Appendix K.Charts

Appendix L.Figures and Data Files

Appendix M.Menus

Appendix N.List of Tables

Appendix O.The Computer Software

Appendix P.Trademarks

Appendix Q.Summary of Statistical Applications and Data Files

Appendix R.Graphical Examples

Appendix S.Data Tally Routine

Appendix T.Homogeneity Tests

Appendix U.Sample and File Management Routine

Appendix V.Selected Statistical Formulas

Appendix W.More on Lambda and Proportional Reduction of Error Statistics

Appendix X.Console Display Screen Fix for Windows 10

Appendix Y.Database Navigation Tools

Selected References

Index

HOW TO OBTAIN YOUR COPY OF THE SOFTWARE?

PREFACE

The goal of EXPRESS STATISTICS, using a quantitative approach, is to assist public administrators, educators, students, and research practitioners in finding solutions to everyday real-world problems; and without being burdened with complicated formulas, calculations, and other mundane activities associated with conducting research. Notwithstanding the hassle-free presentation, the book and software include all of the pertinent statistical concepts from basic rudimentary statistics to multivariate analysis. Also, after reading this book and using the software, the author sincerely hopes that the reader will appreciate and recognize that "STAT" is more than a four-letter word.

Conceptually, the book has two parts. The first part is a basic discussion of research principles, data, and data entry. The second part deals with statistical applications via research examples. The discussions include the assumptions of the targeted statistics, coupled with a well-developed research issue. The presentations also include an explanation of the problem, hypotheses or questions, statistics to use, and a write-up of the findings. The approach is not so much concerned with how to compute statistics, but with the underlining assumptions and purpose of a particular statistic. Statistical applications are tools. The key is to know when and how to use a specific tool. Moreover, in this approach, a statistic is not regarded as an end in itself, but as a means to an end.

The companion software is easy to use, self-prompting, interactive, and menu-driven, with clear and straightforward explanations. The learning curve is less than an hour. The tables, charts, and graphical depictions are complete, including all of the necessary statistical information needed for dissemination. Also, for immediate use and portability, the tables, charts, and graphics can be saved, available for retrieval directly into theses, dissertations, research projects, and other documents.

Although this book has a companion software package, the software is optional. The concepts presented can be mastered without using a computer program. Moreover, any statistical software program may be used providing the sample data files are converted to common-delimited data files then formatted to meet the requirements of the software. However, for simplicity and the ease of use, the companion software is recommended.

Finally, the author personally thanks you for taking the time out of your busy schedule to review his book and computer program. Your endorsement of this book and computer program will be much appreciated.

Lewis Liddell

May 2019

ACKNOWLEDGMENTS

The writer acknowledges, without naming them, his research, statistics, and computer science professors for equipping him with the attitudes and skills needed to undertake this task. Also, the writer pays homage to the thousands of computer scientists who contributed to the development of hardware and software that revolutionized research and quantitative analysis. They have indeed changed our lives.

Notwithstanding the previous acknowledgments, gratitude is given to the writer’s wife, Frances, for her patience, help, and encouragement, and whose persuasion initiated this endeavor. The writer recognizes his parent, Eugene and Colia Robinson Liddell for instilling in him the lifelong desire to do well, Also, recognition is extended to the writer’s mother-in-law and father-in-law, Ollie, and Olivia William Payne, for their support and encouragement

SOFTWARE/SYSTEM OVERVIEW

Express Statistics is easy and straightforward to use, requiring no specialized knowledge of computer programming or database management. The program can be operated without the assistance of this short manual (book), providing the menus and instructions on the screen are carefully read and followed. Also, the System has a comprehensive help routine.

As noted above, in developing Express Statistics, the author intended to create a program that was not restricted by a manual. Every effort was exhausted to make menus explicit and straightforward to follow; however, a little practice with the demo data and the manual should prove to be most helpful in understanding the basic operations of Express Statistics.

System Requirements

Express Statistics is designed for use on all IBM 486 compatible computers or higher running Windows XP, Vista, Windows 7, Windows 8, or Windows 10. A minimum configuration of one gigabyte of memory is required. Your computer must consist of at least one CD drive or one USB port, and one hard disk drive with 320 megabytes of free storage space. A color monitor is required. A printer is optional.

Installing Express Statistics

Insert the Express Statistics installation disk or USB thumb device into your CD drive or the appropriate port–the program should start automatically. If not, click the Start button, and then click Run. Then, follow the instructions on the screen as prompted. The execution files will be installed on drive C. If your software was delivered electronically, click on the self-extracting file named "EXPSTAT.ZIP. Next, click on the file install.exe," then follow the installation instructions as prompted.

As noted, the execution files will be installed on drive C in the execution directory "HASSLE. And all sample data files will be installed in the default data directory EXPDATA9. Upon completion of the installation, the name and drive of the data directory can be changed. But, all data directories must be at level one (subdirectories are not allowed). Please note, the path of the execution directory HASSLE" is fixed and cannot be changed.

Uninstalling Express Statistics

To uninstall Express Statistics, left click on "uninstall. All files and traces of the program will be deleted. Also, the program directory HASSLE and the default data directory EXPDATA9" will be removed.

SOFTWARE WARRANTY

Express Statistics and its associated manual (book) are licensed with a Limited 90-Day Warranty. While every effort has been made to provide error-free software and documentation, the author and Creative Software Systems assume no responsibility for the consequences of the use or misuse of this or any other software and documentation. The user is the sole judge of his/her ability to install and operate this software and to make any modifications to any equipment or software.

Introduction

1.1. The Purpose of The Book

This book and software program were written to assist public administrators, educators, students, and practitioners in finding solutions to everyday real-world problems. A prime objective is an approach that frees the user from the burden of all those formulas, calculations, and other mundane activities associated with conducting research. However, the completeness and the integrity of the research process and results are not compromised.

Most graduate programs in public policy, the social sciences, and education require six to nine hours of research and statistics. For many students, this is a dreadful and painful experience, one they would prefer to forget. After graduation, many of these students do not utilize statistics and research in their professional endeavors. Hence, this statistical book and software program were written to articulate to public administrators, educators, and students the importance of research. In short, the book and software were written to encourage these entities to utilize a more systematic and research-based approach to problem solving and management.

The book employs a nonthreatening practical approach to the study of research and statistics. Also, the book is not cluttered with complicated statistical formulas. In the same vein, each chapter is short and concise. The approach presented in the book emphasizes the practical application of statistics and research--the things that you can use. Although, every effort has been exhausted to keep the explanations and instructions concise and to the point; however, all of the important concepts necessary to understanding and utilizing the statistical analysis and research results are included.

Furthermore, to maintain speed and clarity, the computer software is written in the classical text mode. The software is self-prompting, interactive, and menu-driven, with clear and straightforward explanations. The software will set up all of the statistical results for graphical depiction. The graphics can be printed out or saved as bitmap files that can be retrieved by most standard word processors. Also, for immediate use, the tables, charts, and graphics can be saved to the hard drive, available for retrieval directly into theses, dissertations, and research projects. The tables and charts are complete, including all of the necessary statistical information needed for dissemination. For the ease of portability, all data and tables are stored on the hard drive in the ASCII (text) format.

1.2. Statistics and Concepts

The following statistics and concepts are covered in the book and software:

- Observations

- Differences

- Z-Score

- Median

- Mean

- Mode

- Minimum Value

- Maximum Value

- Range

- Variance

- Standard Deviation

- Skewness

- Kurtosis

- Frequency Distribution

- Percentile Ranks

- Confidence Intervals

- Sampling and Random Number Generation

- Graphics (Bar Chart, Plot Chart, and Pie Chart)

- Chi-square and Contingency Tables

- Fisher’s Exact Probability Test

- McNemar’s Test of Two Paired Proportions

- Contingency Coefficient C

- Kolmogorov-Smirnov (KS) Test

- Cramer's V

- Phi (φ) Coefficient

- Gamma Coefficient

- Somers’ d

- Lambda

- Pearson Product Moment Coefficient Correlation

- Spearman (rho) Rank Coefficient Correlation

- Point-Biserial Correlation

- Independent t-Test

- Correlated t-Test

- Wilcoxon Signed-Ranks Test Statistic

- Mann-Whitney U Test

- One-way Parametric Analysis of Variance

- Two-way Parametric Analysis of Variance (ANOVA)

- Nonparametric Analysis of Variance

- Friedman One-Way Analysis of Variance (ANOVA) by Ranks

- Friedman Two-way Analysis of Variance by Ranks

- Three Factor Factorial Design

- Analysis of Covariance

- ANOVA Treatment-by-Levels Design

- ANOVA Treatment-by-Repeated-Measures

- ANOVA Treatments-by-Treatments-by-Repeated-Measures: Two-Factors

- ANOVA Two-Factor Mixed Design: Repeated Measures on One Factor

- ANOVA Three-Factor Mixed Design: Repeated Measures on One Factor

- ANOVA Three-Factor Mixed Design: Repeated Measures on Two Factors

- ANOVA Latin Square Design: Simple

- ANOVA Latin Square Design: Complex

- Kendall's Coefficient of Concordance, W

- Two-way Factorial Analysis of Variance (ANOVA)

- One-way Analysis of Covariance

- Simple Linear Regression

- Interpolation (Forecasting)

- Correlation Matrix

- Multicollinearity Check

- F-Maximum Test Homogeneity of Variances

- Levene’s Homogeneity Test

- Multiple Regression

Include all Independent Variables

Stepwise Regression by Hierarchy

Variable Entry Selected by User

- Multiple Correlation

- Multivariate Correlated t-Test

- Multivariate Independent t-Test

- Multivariate Analysis of Variance (MANOVA)

- Multivariate Factorial Analysis of Variance

- The Run Statistics

- Times Series, Trend Analysis and Forecasting

- Two-way Analysis of Variance Reliability

- Alpha Coefficient Reliability

- Test Validity and Instrumentation

Content Validity

Validation Data Collection Instrument

CHAPTER 2

Data Entry

2. Data Entry Overview

Most statistical books do not begin with data entry. However, the approach presented in this statistical book utilizes a companion computer software program to facilitate understanding of the concepts advanced. Here again, the emphasis is on practical application. The software is an interactive menu-driven and straightforward program—Hassle Free. Every statistical procedure in the book is explained by using a practical research example. The researcher should be up and working in short order. The learning curve for the software is lee than an hour. Although the software is simple and hassles free, the book and computer software cover all the statistics needed for a quick and accurate approach to statistical analysis. The software is a fully developed stand-alone statistical program. Therefore, an experienced researcher may forego reading this section and load the program to start using the software as a research tool.

The data entry routine is the most challenging aspect of the software, as with any computer program. The data entry process is similar to those found in most commercially available statistical software programs but much more straightforward. However, the data entry process and the spreadsheet used have