Book:
Parametric & Nonparametric Statistics for Business & Social Research: IBM SPSS
ISBN: 979-8386852528,159 pages, 17 August 2026

“Parametric & Non-parametric Statistics for Business & Social Research: IBM SPSS" is written and designed in a simple and straightforward manner to introduce basic statistics for students in business and social sciences. It presents how quantitative data analysis and statistical concepts provide information & solutions to some practical research problems. With many cases and exercises in each chapter, this text is easy to understand on most common statistical methods to create data summary, report, interpretations, conclusion & inferences using IBM SPSS software.

This text consists of 7 comprehensive chapters on parametric and non-parametric statistics and covers nominal, ordinal and continuous data, descriptive statistics, histogram, graphs/plot/charts, normality test, and homogeneity of variance test. The text also discusses hypothesis testing, comparison of means, mean ranks and count / proportions among 2 or more groups of samples, analysis of variance, and analysis of covariance (General Linear Model).

The author also discusses the correlation among variables and relationship between two numeric variables (Spearman, Kendall and Pearson correlations) as well as linear relationships among two or more independent variables (multiple regression model and equation). The last 2 chapters introduce time-series prediction / estimation and factor analysis (dimension reduction) which can be applied to most common data in business & social research.

It covers popular statistical analyses and tests such as:
1. Descriptive statistics and graphical charts.
2. Hypothesis testing, ANOVA, MANOVA, ANCOVA.
3. Chi-square, Cochran, Wilcoxon, Friedman, t-test.
4. Kendal & Pearson correlations, Scatter plot / diagram.
5. Regression, Logit & Discriminant Analysis and Syntax file.
6. Time series Techniques: Linear, Exponential, Quadratic.
7. Factor Analysis, Scree Plot, KMO, and Cronbach’s α test.

----

Some SPSS files (with its data type) & corresponding test used in each chapter:
(*.sav file can be opened only if you have already installed SPSS software on your computer)

Chapter 1. Basic Statistics
UScensus.sav (Scale level data): 
    -“Normality test” (Kolmogorov-Smirnov test for distribution / histogram) of dataset on variable age.
    -“Homogeneity of variance test” (Levene’s test).

Chapter 2. Hypothesis Testing
2.1. Nonparametric statistics:
UScensus.sav (nominal level, independent data): 
   -“Chi-square hypothesis test” to check whether total population of whites, blacks and other races in US is the same or not.
McNemar.sav (nominal level, dependent/paired data with 2 treatments):  
   -“McNemar test” is used to ensure patient's condition before and after treatment whether there is any significant difference or not between them.
Cochran.sav (nominal level, dependent/paired data with 3 treatments or more): 
    -“Cochran test” to check any difference in  patients’ condition before and after treatment1 & treatment2. 
UScensus.sav (ordinal level, independent data): 
   -“Mann-Whitney test” to test level of happiness between men and women.
UScensus.sav (ordinal level, independent data): 
    -“Kruskal-Wallis test” to examine level of happiness among 3 or more groups: whites, blacks, and other races.
UScensus.sav (ordinal level, dependent/paired data): 
   -“Wilcoxon Test” to see if there is any difference between 2 groups: father's highest education and mother’s education.
UScensus.sav (ordinal level, dependent/paired data): 
   -“Friedman test” to confirm the differences between 3 groups or more.

2.2. Parametric statistics:
Data entry (Scale level, independent data): 
   -“t-test” to find out whether age of graduating students between men and women have a significant difference or not.
UScensus.sav (Scale level, independent data): 
    -“t-test” to answer if prestige work level of men & women is the same or not.
UScensus.sav (Scale level, 1 independent data): 
  -“ANOVA (Analysis of Variance) F-test” to verify the question whether the prestige level of work among 3 groups: white, black & other races are the same.
  -“MANOVA (Multivariate Analysis of Variance) test” is ANOVA (1 dependent variable) with 2 dependent y variables or more, and it can be “one-way MANOVA” test for 1 x, or 2-way for 2 x’s.
UScensus.sav (Scale level, dependent data): 
   -“ANCOVA (Analysis of Covariance) test” to ensure whether happiness level between men and women is the same or not if we add covariate variable: job prestige (prestige80) as control variable.
pairedParametric.sav (Scale level, dependent data): 
    -“Paired sample test” to prove the size of watermelon before and after given certain fertilizer is the same or not.

Chapter 3. Correlation Analysis
3.1. Nonparametric statistics:
UScensus.sav (Nominal vs Nominal level data): 
    -finding relationship between location of residence and race of population in the US: white, black, and other races (Cross tabulation).
UScensus.sav (Nominal vs Scale level data): 
   -finding correlation between highest education of respondent (y) and education level of father (x) (Spearman rank order correlation).
pDelivery.sav (Ordinal or Scale but not normally distributed vs Scale level data): 
    -finding relationship between delivery time and distance of delivered parcel on package delivery company (Kendall method).

3.2. Parametric statistics:
pDelivery.sav (Scale vs Scale level data): 
    -calculating correlation coefficient between delivery time and distance (Pearson and Scatter plot methods).
UScensus.sav (Scale vs Scale level data): 
   -creating correlation Matrix between highest education of respondent with some other independent variables (Pearson methods).

Chapter 4. Simple Regression Analysis 
                   (y variable & one x variable):
    -“Logistic regression test” has y = nominal or ordinal & x = nominal or ordinal level data.
pDelivery.sav (y=Scale level & x=Scale level data): 
    -Calculating regression equation and making prediction for delivery time of parcel on package delivery company such as UPS/Fed-ex based on x variable: distance.
pDelivery.sps (y=Scale level & x=Scale level data): Syntax commands for regression problem in pDelivery.sav.

Chapter 5. Multiple Regression Analysis 
                   (y var & 2 or + x variables)
5.1. Nonparametric dependent variable (y):
pDelivery.sav file (y=Scale level, but not normally distributed & 
    x=Scale level data):
    -“Binary Logistic regression test” has y = non-overlapped nominal or ordinal level & x = nominal or ordinal level data.
    -“Discriminant Analysis (Log linear regression) test” has y = nominal or ordinal & x variables can be mixes of 3 data types available on 
pDelivery.sav (y=Nominal level & x=Scale level data):  
    -Finding Discriminant Function of delivery service: express or regular service based on 2 independent variables: Distance and Number of trips.

5.2. Parametric dependent variable (y):
pDelivery.sav (y=Scale level & x=Scale level data): 
     -Finding multiple regression equations for forecasting of delivery time based on 2 independent variables: distance and number of trips (with scale level data).
Salary.sav (y=Scale level & x=Scale level data):  
    -Analyzing the amount of employee salary based on 3 independent variables or more: initial salary at job offers, type of job position, and his/her educational level.
   -“General Linear Model (GLM) analysis test” can be used to combine a number of different statistical models, such as: t-test, F-test, ANOVA, ANCOVA, MANOVA, MANCOVA, linear and multiple regression equations, etc.

Chapter 6. Time Series
UsYen.sav (y=Scale level & x=time data):  
   -Forecasting US$ exchange rate against JP Yen (SPSS Time-series method)
mAverage.xlsx (y=Scale level & x=time data): 
   -Predicting amount of product sales (MS-Excel moving average method).
Exponential.xlsx (y=Scale level & x=time data): 
   -Estimating number of product demands/ requests (MS-Excel exponential smoothing).
Stock.xlsx (y=Scale level & x=time data): 
   -Projecting stock market data (SPSS and MS-Excel exponential smoothing method).

Chapter 7. Factor Analysis (Dimension Reduction Analysis)
wellness.sav (Ordinal or Scale level variables): 
   -Searching for factors related to physical health and spiritual health (grouping var. based on their corresponding factor/ component).
    This file is also used for running the Cronbach’s alpha test.
