BÄ°S654 - LINEAR REGRESSION ANALYSIS

Course Name Code Semester Theory
(hours/week)		 Application
(hours/week)		 Credit ECTS
LINEAR REGRESSION ANALYSIS BÄ°S654 2nd Semester 3 0 3 7
PrequisitesHaving successfully completed the lectures BÄ°S 605 or BÄ°S 735
Course languageTurkish
Course typeElective 
Mode of DeliveryFace-to-Face 
Learning and teaching strategiesLecture
Discussion
 
Instructor (s)ASSIST. PROF. SEVÄ°LAY KARAHAN, PhD - LECT. H. YAÄžMUR ZENGÄ°N, PhD - PROF. ERDEM KARABULUT, PhD  
Course objectiveTo teach the reasons of using simple and multiple linear regression models, how to construct, analyze and interpret the linear models and how to use different software programs for analyzing linear models. To provide having introductory knowledge on non-linear regression models. 
Learning outcomes
  1. Student knows what the simple and multiple linear regression models are used for.
  2. Student knows how the simple and multiple linear regression models are constructed.
  3. Student knows how to analyze the linear models.
  4. Student analyzes linear regression models by using different software programs.
  5. Student solves the problems about simple and multiple linear regression methods individually.
  6. Student interprets results.
  7. Student also has introductory knowledge on nonlinear regression
Course Content- Aims of linear regression analysis.
- Usage of linear regression analysis.
- Assumptions of linear regression analysis.
- Simple linear regression.
- Some non-linear regression models.
- Multiple linear regression.
- Adequacy measures of regression models.
- Regression models with qualitative independent variables.
- Methods of independent variable selection.
- Principal component regression.
- Validity of regression models. 
References1. Daniel, Wayne W., Chad L. Cross. Biostatistics: a foundation for analysis in the health sciences. 10th Edition, John Wiley&Sons, 2018.
2. Montgomery D.C., Peck E.A., Vining G. G. Introduction to Linear Regression Analysis. 5th Edition, John Wiley-Sons, Inc. Publications, New Jersey, 2012.
3. Kleinbaum D. G., Kupper L. L., Nizam A., Muller K. E., Rosenberg, E.S. Applied Regression Analysis and Other Multivariable Methods. 5th Edition, Cengage Learning, 2013.
4. Chatterjee S. and Hadi A. S. Regression Analysis by Example. 5th Edition, John Wiley-Sons, Inc. Publications, New Jersey, 2012.
5. Alpar R. Çok DeÄŸiÅŸkenli Ä°statistiksel Yöntemler, Detay Yayıncılık, Ankara, 2021. 

Course outline weekly

WeeksTopics
Week 1Objectives, usage, properties and assumptions of linear regression analysis and modules of different software programs on linear regression.
Week 2Simple linear regression analysis, calculating the regression coefficients and standard error of coefficients, confidence intervals of the coefficients and confidence intervals of predictions, hypothesis tests for coefficients.
Week 3Non-linear regression models and non-linear regression models that can be linearized.
Week 4Multiple linear regression analysis, calculating the regression coefficients, confidence intervals of the coefficients and confidence intervals of the predictions, hypothesis tests for coefficients.
Week 5Adequacy measures related with regression models. Examining the residuals (raw residuals, standardized residual, studentized residuals, and etc.) and graphical representations for residuals.
Week 61st Midterm Examination
Week 7Adequacy measures related with regression models (Cook distance, leverage points, Mahalanobis distance, DFBETA, DFITS, and etc.) and graphical representations.
Week 8Problem of heteroscadasticity in regression, determination of heteroscadasticity, elemination of heteroscadasticity. Problem of collinearity in regression, determination of collinearity, elemination of collinearity.
Week 9Problem of normality of residuals, problem of autocorrelation, elimination of outocorrelation, Measures used for validity of the models (PRESS statistic, and etc.)
Week 10Use of dummy variables in case of independent categorical variables.
Week 112nd Midterm Examination
Week 12Methods of independent variable selection, principal component regression.
Week 13Examining different articles from the medical literature.
Week 14Term project presentation.
Week 15Preparation to final exam
Week 16Final Exam

Assesment methods

Course activitiesNumberPercentage
Attendance00
Laboratory00
Application00
Field activities00
Specific practical training00
Assignments1230
Presentation00
Project00
Seminar00
Midterms220
Final exam150
Total100
Percentage of semester activities contributing grade succes1450
Percentage of final exam contributing grade succes150
Total100

WORKLOAD AND ECTS CALCULATION

Activities Number Duration (hour) Total Work Load
Course Duration (x14) 14 3 42
Laboratory 0 0 0
Application000
Specific practical training000
Field activities000
Study Hours Out of Class (Preliminary work, reinforcement, ect)14684
Presentation / Seminar Preparation000
Project000
Homework assignment12448
Midterms (Study duration)21122
Final Exam (Study duration) 11414
Total Workload4338210

Matrix Of The Course Learning Outcomes Versus Program Outcomes

D.9. Key Learning OutcomesContrubition level*
12345
1. A specialist with a graduate diploma in biostatistics: Has the knowledge to lead research planning, execution, and finalization, staying updated on literature and current studies.     X
2. Critically evaluates studies and scientific papers in presentations, courses, seminars, and conferences, encouraging a critical perspective.   X 
3. Has the sufficient theoretical and practical knowledge of statistics to determine the appropriate statistical analysis and to grasp the results correctly.   X 
4. Be proficient in computer use and statistical software, ensuring data suitability and recommending solutions for data management and analysis methods.    X 
5. Effectively communicates analysis issues through active participation in discussions, exchanging information with the advisor, and presenting seminars.   X 
6. Provides method suggestions in consultancy, does research planning, prepares research reports.   X 
7. Maintains scientific accuracy and ethical values, remaining careful against any conscious or unconscious biases throughout the study.  X  
8. Supports a counseling service under faculty supervision, may handle independent projects, and participates in conferences, presenting papers or posters with the academic advisor.   X 
9. Be ready for multidisciplinary studies, collaborating professionally in group settings and gains the ability to assign individuals in the group.   X 
10. Integrates diverse disciplines to analyze and synthesize information, offering solutions.  X  

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