Jimma University
College of Natural Science
Department of Statistics
Course title: Introduction to Multivariate Methods
Course code: Stat3063
Credit hours: 3
Credit: 5 EtCTS
Contact hours: Lecture 3 hrs, 2 hour Tutorial and Computer Lab 1 hour per week
Instructor: Yasin N.(MSc)
Introduction; Review of Matrix algebra; Practical examples of multivariate data; Preliminary
data analysis; Examination of a data matrix, reduction of a data matrix; definition and
calculation of sample summary statistics: means, variances, covariance's, correlations;
Examination and interpretation of sample correlation matrix; the multivariate normal
distribution. Study of relationships (association); One-sample test of mean vector;
simultaneous confidence intervals for detecting important components; test of structural
relationship; Extension to two-sample tests; principal components and factor analysis as a
means of reducing dimensionality: Calculation and interpretation of principal components
and common factors.
Objectives
• To equip students with sound knowledge of extending the statistical ideas of univariate
data analysis to that of multivariate;
• To equip them with skills of computing multivariate methods;
• To motivate them to apply the multivariate methods to solve real life problems.
Learning outcomes
At the end of the course students are expected to:
• State the basic statistical ideas of multivariate data analysis;
• Use the basic multivariate statistical methods and interpret them.
Course Outline
1. Introduction ( 6 lecture hours)
1.1. Introduction
1.2. Objectives
1.3. Areas of application
1.4. Organizing multivariate data
1.5. Organization of data
1.6. Descriptive statistics
1.7. Measures of linear association
2. Review of Matrix Algebra and Random Vectors (10 lecture hours)
2.1. Basics concepts
2.2. Vector and matrix
2.3. Matrix algebra
2.4. Positive definite matrix
2.5. Square root matrix
2.6. Mean vectors and covariance matrices
2.7. Matrix inequalities and maximization
3. Multivariate ,Normal Distribution (7 lecture hours)
3.1. Multivariate normal density
3.2. Sampling from multivariate normal distribution
3.3. Maximum likelihood estimation
3.4. Sampling distribution of a sample multivariate mean and a covariance matrix
4. Inference about a Multivariate Mean Vector (7 lecture hours)
4.1. Inference about a mean vector
4.2. Hypothesis testing
4.3. Hotelling's test statistic
4.4. Confidence regions and simultaneous comparison of components
4.5. Large sample inference about the mean vector
5. Comparisons of Several Multivariate Means (4 lecture hours)
5.1. Paired comparisons and a repeated measures
5.2. Comparing mean vectors from two populations
5.3. Comparing several multivariate population means
6. Principal components and Factor analysis (8 lecture hours)
6.1. Population principal components
6.2. Summarizing sample variation by principal components
6.3. Large sample inferences
6.4. Common factors and estimation
Textbook
Johnson, R.A and Wichern, D.W. (2007). Applied Multivariate Statistical Analysis (6th
Edition). Prentice-Hall, Inc., New Jersey.
References
1. Hair, J.F., Black, W.C., Babin, B.J., and Anderson, R.E. (2009). Multivariate Data
Analysis (7th Edition)
2. Anderson, T.W. (2003). An Introduction to Multivariate Statistical Analysis (3 rd
Edition). Wiley, New York.
3. Ho, R. (2006). Handbook of Univariate and Multivariate Data Analysis and
Interpretation with SPSS.
4. Montgomery, D.C. (2009). Design and Analysis of Experiments, MINITAB Manual.
5. Hair, J.F., Black, B., Babin, B. and Anderson, R.E. (2005). Multivariate Data Analysis
(6th Edition).
6. Ho, R. (2006). Handbook of Univariate and Multivariate Data Analysis and
Interpretation with SPSS.
7. Hair, J.F., Anderson, R.E., Tatham, R.L. and Black, W.C. (1995). Multivariate Data
Analysis: With Readings.
8. Everitt, B.S. and Dunn, G. (2001). Applied Multivariate Data Analysis.
9. Grimm, L.G. and Yarnold, P.R. (1995). Reading and Understanding Multivariate
Statistics.
10. Manly, B.F.J (2004). Multivariate Statistical Methods: A Primer (3rd Edition).