SAY733 - STATISTICAL ANALYSIS WITH MISSING DATA

Course Name Code Semester Theory
(hours/week)		 Application
(hours/week)		 Credit ECTS
STATISTICAL ANALYSIS WITH MISSING DATA SAY733 Any Semester/Year 2 2 3 10
PrequisitesNone
Course languageEnglish
Course typeElective 
Mode of DeliveryFace-to-Face 
Learning and teaching strategiesLecture
Drill and Practice
 
Instructor (s)Prof. Dr. Ahmet Sinan Türkyılmaz 
Course objectiveTo get an understanding of the principles of methodology and practical implementation using actual and simulated data sets for missing data. 
Learning outcomes
  1. Learning the definition of missing values, the patterns of missing values and various definitions or assumptions about the mechanism generating the missing values
  2. Understanding the differences between Missing Completely at Random, Missing at Random and Missing Not at Random mechanisms
  3. Learning the basic principles behind imputation based approaches
  4. Learning methods for imputing the missing values and how to properly analyze the data with some imputed values
  5. Learning to use multiple imputation approach as a way to incorporate uncertainty due to missing values
Course ContentDefinition and examples of Missing Values, Patterns and Mechanisms of missing values
Weighting approaches for compensating subjects with missing values such as adjustment cell and response propensity weighting
Post-stratification
Multiple Imputation based approaches including parametric and nonparametric imputation methods
Sensitivity Analysis with respect to potential systematic deviation of missing values from the observed values
Limited discussion of analyzing incomplete data using maximum likelihood method: Multivariate normal and contingency table analysis 
ReferencesHeeringa, S. G., West, B. T., Berglund P. A., (2012). Applied Survey Data Analysis (Chapman & Hall/CRC Statistics in the Social and Behavioral Sciences) [Hardcover]. 

Course outline weekly

WeeksTopics
Week 1Introduction
Week 2Definition and examples of missing values
Week 3Patterns and mechanisms of missing values
Week 4Applied exercise
Week 5Weighting approaches for compensating subjects with missing values
Week 6Weighting approaches for compensating subjects with missing values (continued)
Week 7Applied exercise
Week 8Midterm Exam
Week 9Post-stratification
Week 10Applied exercise
Week 11Multiple Imputation based approaches including parametric and nonparametric imputation methods
Week 12Applied exercise
Week 13Sensitivity analysis with respect to potential systematic deviation of missing values from the observed values
Week 14Discussion of analyzing incomplete data using maximum likelihood method: Multivariate normal and contingency table analysis
Week 15Preparation for Final Exam
Week 16Final Exam

Assesment methods

Course activitiesNumberPercentage
Attendance00
Laboratory00
Application00
Field activities00
Specific practical training00
Assignments210
Presentation00
Project120
Seminar00
Midterms120
Final exam150
Total100
Percentage of semester activities contributing grade succes450
Percentage of final exam contributing grade succes150
Total100

WORKLOAD AND ECTS CALCULATION

Activities Number Duration (hour) Total Work Load
Course Duration (x14) 16 2 32
Laboratory 0 0 0
Application000
Specific practical training000
Field activities000
Study Hours Out of Class (Preliminary work, reinforcement, ect)14456
Presentation / Seminar Preparation000
Project000
Homework assignment51680
Midterms (Study duration)14242
Final Exam (Study duration) 19090
Total Workload37154300

Matrix Of The Course Learning Outcomes Versus Program Outcomes

D.9. Key Learning OutcomesContrubition level*
12345
1. Gains theoretical knowledge on research methodology, concepts on quantitative research methods, quantitative sampling techniques, learning, implementing, and developing models and techniques in quantitative analysis, theory, and develops skills to transform and improve knowledge into design, implementation, analysis. X    
2. Gains theoretical knowledge on qualitative research methods, theory, and skills to transform and improve knowledge into design, sampling, generating data and analysis, knowledge on differences between methods and their use, improvement/combined use of these methods, evaluation with experts and institutions, focus groups and in-depth interviews, skills to implement them.    X
3. Gains ability to evaluate quality of researches, interpret/improve results with experts and institutions, transform the results into oral/written presentations, and present them at (inter)national meetings.  X   
4. Develops skills to conduct generalizable research, interpret results of analyses, transform them into publications abiding by ethics, gain ability and consciousness to prepare (inter)national projects, evaluate them with experts and institutions.     X
5. Contributes to development of methods by producing a thesis using research methods. X    
6. Follows international publications, communicate with colleguaes, using English at a level no lower than the Common European Framework of References for Languages B2.X    

*1 Lowest, 2 Low, 3 Average, 4 High, 5 Highest