Introductory Statistical Procedures with SPSS

The importance of this guidebook is that it is simple to use and requires no prior knowledge, while yet presenting the core concepts of statistical theory with applications in SPSS (Statistical Package for the Social Sciences). SPSS is a user-friendly and powerful data management and statistical analysis software package. The package is especially beneficial for students and researchers in psychology, sociology, psychiatry, and other behavioral sciences, as it performs a wide range of univariate and multivariate operations commonly used in these fields. Because of the importance of multivariate statistics, two parts of Chapter 6 are devoted to this topic. The purpose of this guide is to provide concise and clear instructions on how to perform a variety of statistical analysis using the most recent version of SPSS, SPSS 21. Furthermore, the primary goal of this book, as opposed to other books, is to assist undergraduate, graduate, and postgraduate students in a variety of fields, including but not limited to statistics, economics, physics, chemistry, education, and commerce, in conducting statistical analysis using SPSS software. Each chapter focuses on a distinct sort of analytical method that may be used on a variety of data sets, mostly from the social and behavioral sciences. Furthermore, the book must be thorough in terms of dealing with a wide range of problems found in the literature as well as determining the best answer. Although we spend a lot of time talking about how to use SPSS to acquire findings and analyze them, the underlying theoretical foundation of many of the approaches is also covered in separate boxes. The reader is referred to other sources for details when more complex techniques are employed. Despite the fact that many of the boxes contain a few mathematical equations, the reader with only a basic understanding of mathematics will be able to conduct an adequate analysis of the data. The reader should have taken at least one statistical course and be familiar with concepts, such as linear regression, correlation, significance tests, and elementary analysis of variance in order to get the most out of this handbook. This guide will provide researchers and students with a relatively self-contained method of accurately analyzing their data using SPSS. Each chapter concludes with a collection of tasks, some of which are linked to the data sets covered in the chapter and others which introduce further data sets. These activities will help the readers to improve their SPSS and statistical abilities.

Dr. Arslan Nasir dedicated this book to all his teachers, who taught him in his life, especially Abdula Arbi, his teacher and his cousin, all the teachers who taught him in his graduate level, especially Prof. Kahlid Javad, all the teachers who taught him in master level, especially Prof. Amjid Shah (Late), all the teachers who taught him in M.phil level, especially Dr. Ahmed Zogo Memon, all the teachers who taught him in his P.hD level, especially Prof. Dr. Muhammad Hussain Tahir. Professor Hassan Bakouch acknowledges his family, namely his wife Noura, for saving time to collaborate to this book. Also, he wants to thank his brother Dr. Adel.

In this chapter, we discuss some prime concepts related to introductory statistics, i.e., data, population, sample, types of variables, branches of statistics, scales of measurements, error of measurements. Also, we outline how to work with syntax editor.

In this chapter, we discuss some tools of data presentation, namely classification, tabulation and frequency distribution. Moreover, many graphs are given, such as bar chart, pie graph, histogram, stem and leaf plot, box plot and time series plot. We also explain how to make a frequency distribution of primary data in SPSS for the given data. 

In this chapter, we define the average and its types, i.e., mathematical averages which include the arithmetic mean, geometric mean, harmonic mean, median and mode. Also, we show when and where these averages are suitable to be used. Position measures, namely quartiles, deciles and percentiles also have been discussed. This chapter also gives techniques to measure the spread of the data around the average, these measures include range, quartile deviations, mean deviation, standard deviations and measures of asymmetry and peakedness of the data. The procedures for all these measures are outlined by SPSS.

This chapter provides some basic concepts of probability, types of probability, i.e., classical approach, relative frequency approach, axiomatic approach and subjective approach; rules of counting, i.e., permutation and combination; laws of probability, i.e., complement law and addition law; conditional probability, axioms of conditional probability, multiplicative law of probability, dependent and independent events. 

This chapter gives a brief overview of discrete and continuous random variables, their mean and variance. Some discrete probability distributions are given, including binomial distribution, Poisson distribution, hypergeometric distribution, computation of their probabilities and frequencies and simulation for these distributions are given on SPSS. Continuous probability distributions include only normal distribution.

This chapter gives a short overview of the basic concepts of probabilistic and deterministic models, regression, regression lines, residuals, coefficient of determination, residuals and standard deviation of regression. Correlation and Spearman rank correlation are also under study. Two multivariate techniques, multiple regression and principal component analysis are also discussed. The procedures for the computations are given in SPSS

This chapter gives the methods and tools for the estimation of parameters, which includes the point estimation and interval estimation. The confidence interval includes the construction of 100(1−α)% interval limits for, single population(one sample) mean µ, the difference between two population means (independent sample) µ1 − µ2 for equal and unequal variances, the confidence interval for paired samples(related samples). The procedures to perform these methods on SPSS are given.

This chapter gives the methods and tools for the comparison of more than two samples using F-test by means of analysis of variance techniques for one-way and two-way variations (interaction effect included). The experimental design for the experiments with controlled environments includes the basic designs and the factorial experiments.

This chapter gives the methods and tools to conduct a sample survey. These methods include the sampling methods, i.e., probability and non-probability sampling. The sampling distribution of sample statistics is also under study, along with central limit theorem.

This chapter gives the methods and tools for the tests when the data do not satisfy the normality assumption, i.e., nonparametric tests. These tests include chi-square goodness-of-fit test, the single sample tests, i.e., Sign test, Wilcoxon signed rank test, run test for randomness, and also two samples and more than two-sample nonparametric tests, which include the Mann-whitney U test, median test and the Kruskal-Wallis H test test.