Code ENS 505
Term 201802
Title Methods of Statistical Inference
Faculty Faculty of Engineering and Natural Sciences
Subject Engineering Sciences(ENS)
SU Credit 3
ECTS Credit 10.00
Instructor(s) Hans Frenk -frenk@sabanciuniv.edu,
Language of Instruction English
Level of Course Doctoral
Master
Type of Course Click here to view.
Prerequisites
(only for SU students)
--
Mode of Delivery Formal lecture
Planned Learning Activities Discussion based learning,Simulation
Content

The main objective of this course is to review the basic concepts of the theory of statistics and further develop understanding of some fundamental applied statistical methods. Our emphasis will be on applications of the theory in the development of statistical procedures. Practical applications of statistics to some problems in engineering and management will be given. Computational assignments will be given to help the students to understand the concepts and to have an opportunity to practice applying them. Computer aided analysis of data; fundamental concepts of statistics and related distributions; design of experiments and analysis of variance; regression and correlation analysis; methods for stationary time series data; linear methods for classification.

Objective

The main objective of this course is to review the basic concepts of the theory of statistics and further develop an advanced-level understanding of fundamental statistical inference procedures.

Learning Outcome

Describe the types of statistics: descriptive statistics, parametric inferential statistics and non-parametric statistics
Obtain descriptive statistics and employ the basic graphical visualization techniques to summarize and analyze the data
Describe the general properties of estimators: biasedness, mean square error, consistency and efficiency
Determine the point estimators of unknown parameters of interest based on three widely-applied methods: maximum likelihood estimation, the method of moments and Bayes estimation
Derive the confidence interval estimators of unknown parameters of interest based on three approaches: exact methods, approximations based on the large sample properties and approximations using bootstrapping
Discuss the basic principals of the methods of hypothesis testing
Identify key points in Diagnostics and Remedial Measures for the regression analysis
Perform simple and multiple regression analyses by the help of a software such as SPSS and MATLAB.

Programme Outcomes