Introduction to Statistical Data Analysis Part 2 PDF

Statistical Software SPSS SEM-PLS Minitab – Statistical Package for Structured Equation detect trends, solve the Social Sciences queries and identify...

Statistical Software SPSS SEM-PLS Minitab – Statistical Package for Structured Equation detect trends, solve the Social Sciences queries and identify Modelling (SEM) - building of behavioral relevant insights in data models, which display by performing a the relationships complete and best-in- between variables class suite of statistical SAS analysis Statistical Analysis System - predictive analysis, data mining and management, & SEM-AMOS Eviews business intelligence Structured Equation Econometric Views- Modelling (SEM) - statistical package building of behavioral focused on models, which display econometric analysis STATA the relationships between variables Statistics and Data, - general-purpose software that imports data different formats, but can only open one data set at a time Business Research Methods | CHOOSING THE RIGHT STATISTICAL SOFTWARE Research Objective Type of Possible Method Suggested Statistical Statistical Theory Software To examinethe significant differences Univariate Independent t-test SPSS between two interested groups towards one Comparison analysis continuous targeted variable analysis Mann-Whitney test SPSS analysis To measure the significant differences among Univariate One-way Analysis of SPSS more than two comparison groups towards Comparison Variance test (i.e. one continuous targeted variable analysis ANOVA) analysis Kruskal-Wallis test SPSS analysis To measure the significant differences among Multivariate Multivariate Analysis SPSS more than two comparison groups towards Comparison of Variance test (i.e. more than one continuous targeted variable analysis MANOVA) analysis Business Research Methods 2 | To determine the significant Univariate Pearson’ SPSS bivariate relationship between two Correlation Correlation continuous interested variables Analysis analysis Spearman’s Rank SPSS Correlation analysis To examine causal and effect Multivariate Multiple Linear SPSS relationship between a set of independent variables paired with Correlation Regression (i.e. one continuous dependent variable analysis MLR) analysis To examine causal and effect Multivariate Logistic Regression SPSS relationship between a set of Correlation analysisa or independent variables, where analysis these set of independent variables Multinomial involve a categorical variable Regression paired with one categorical analysis dependent variable Business Research Methods 3 | To examine causal and effect relationship Multivariate Discriminant analysis SPSS between a set of independent variables, where Correlation these set of independent variables do not analysis involve a categorical variable paired with one categorical dependent variable To examine causal and effect relationship Multivariate Covariance based AMOS between a number of independent and Correlation Structural Equation dependent variables with priority to analysis Modelling (i.e. CB- confirming or rejecting the theories SEM) analysis To examine causal and effect relationship Multivariate Variance based SmartPLS between a number of independent and Correlation Structural Equation dependent variables with priority to exploring analysis Modelling (i.e. VB- the theories SEM) analysis To refinement or reconstruct or confirm the Multivariate Exploratory Factor SPSS variables’ structure that share a common Correlation Analysis (i.e. EFA) variance analysis Business Research Methods 4 | Why use Statistics? Deal with uncertainty in repeated scientific measurements Design a valid experiment and data analysis Draw a reliable conclusion from data Be a well-informed member of society Business Research Methods 5 | Role of Statistics for Data analysis Data collection, organization, interpretation and data validation A procedure of performing various statistical operations. To use or choose the right methods for statistical analysis, which is how we process and collect the samples of data to uncover patterns and trends Business Research Methods 6 | Important Terms in Statistics In statistics, we generally want to study a population. You can think of a population as a collection of persons, things, or objects under study. To study the population, we select a sample. The idea of sampling is to select a portion (or subset) of the larger population and study that portion (the sample) to gain information about the population. Data are the result of sampling from a population. Business Research Methods 7 | Types of Applied Statistics Applied statistics can be divided into two areas: 1. Descriptive statistics and 2. Inferential statistics Business Research Methods | Descriptive statistics Descriptive statistics consists of methods for organizing, displaying, and describing data by using tables, graphs and summary measures. A raw data set in its original form is usually very large and not very helpful in drawing conclusions or making decisions. It is easier to draw conclusions from summary tables, diagrams, graphs and summary measures. Business Research Methods |  Inferential statistics Inferential statistics consists of methods that use sample results to help make discussions or predictions about a population. It is also called inductive reasoning or inductive statistics. A major portion of statistics deals with making decisions, inferences, prediction and forecast about population based on results obtained from samples. Business Research Methods | Parametric vs non-Parametric Parametric statistics Assumes that sample data comes from a population that can be adequately modelled by a probability distribution that has a fixed set of parameters Parametric tests are used only where a normal distribution is assumed. The most widely used are T-test (paired or independent), ANOVA, Pearson Correlation and linear regression. Non-parametric Not depend on any distribution Common non-parametric statistics are Chi-Square, bootstrap, Mann-Whiteney-Wilcoxon (MWW) or the Wilcoxon test Business Research Methods11 | Description/(Descriptive): Frequency Distribution Frequency Table with Frequency Count Percentage Distribution In statistics, the frequency or absolute frequency of an event is the number. of times the observation has occurred/recorded in an experiment or study. These frequencies are often depicted graphically or in tabular form.