Advanced Statistics Module – IBSS DBA Program
To equip students with theoretical and practical knowledge in using and utilizing advanced statistical tools in analyzing research data.
Upon completion of this subject, students should be able to:
- Explain the rationale, discuss the usage and carry out basic computational exercise for each of the statistical tools/ topics covered to analyze the data for research purposes.
- Explain the underlying assumptions and limitations in the use of each model/ tools discussed for different types of data collected.
- Adopt and use relevant statistical tools, compute and analyze the data and evaluate and synthesis the results obtained to explain the phenomenon being studied or the issue being discussed.
Information gathering, data processing, interpretation, critical analysis of data and writing skills and ability to work independently.
Principally, this module aims to enhance students’ understanding of the advanced statistical tools to analyze data for decision making. Specifically, the focus will be on understanding the basic concepts and assumptions underlying those tools and their nature, usages and application in real life decision situations, particularly Regression. Students will also be exposed to the analysis using statistical packages. Each of the statistical procedures is examined is relation to the rationale for using them, the assumptions for using them, the process of using each tool and the interpretation of the analysis.
Combinations of class lectures, tutorials, group discussions of issues and case studies and assignments.
The Basic of Statistics – A Review
- Concepts – Statistics, statistical data, type (ordinal, nominal, categorical), data collection, analysis and decision making ·
- Presentations – frequency distribution, pie and bar charts, stem-andleaf, histogram, polygon, ogive
- Measures – of central tendency, dispersion, relative distribution-index variability and skewness
Understanding and Preparation for Analysis
- Descriptive vs Inferential statistics
- Purpose of analysis – describing and predicting
- Approaches to model building
- Revealing patterns using descriptive statistics
- Variables (nominal, ordinal and intervals)
- Distributions (normal vs skewed)
- Making predictions using inferential statistics
- Basic concepts (probability, populations, sampling)
- Types of sampling (random vs purposive) and variables (dependent vs independent, categorical vs continuous)
- How to make data more reliable (matching, precision matching and frequency distributions)
Methods of Analysis
Analyzing Individual variables
- Impacts of distributions (normal vs skewed)
- Measures (central tendencies and skewness)
Analyzing Differences Between Groups
- Matched Pairs T-Test
- Analysis of Variance (ANOVA)
Analyzing Relationships Among Variables
Models for Analysis
- Linear, nonlinear, hierarchical(nested) and mixed models
- Probabilistic vs deterministic models
- Concept, assumptions, purpose and uses of regression and how it works
- Similarities and differences between regression and correlations
- Single vs multiple regression, nonparametric regression and smoothing
- Regression line, regression statistics, R squared, least square estimation, estimating standard errors
- Making inferences and predictions using regression
- Measuring strength of linear relationships
- Statistical testing – the F test
- Problems – multicollinearity, heteroscedasticity and autocorrelation
- Logistic (logit) regression
- Probit regression
- Time series regression
- Multiple outcome (multivariate) regression
- Bayesian regression
Special Issues and Topics in Regression Analysis
- Dummy variables and interactions
- Unusual data and violation of model assumptions
- Co-linearity and principal components
For more information kindly visit our facebook page: https://www.facebook.com/IBSSEGYPT/