3622351 Statistical Data analysis, 6 Cp
Code 
3622351 
Validity 
01.01.1950 

Name 
Statistical Data analysis 
Abbreviation 
TDA 
Credits  6 Cp 
Date of expiry 

Type  Intermediate Studies 
Subject  0390 Statistics 
Class  Study Unit 
Hours 

Study right 

Grading  05 
Recommended scheduling  
 


 
Organisation 
Computer Science (J,K) 

Description
Learning outcomes 
The student understands the linear model and its most important extensions and is able to do these analyses using Rsoftware. 
Content 
Simple linear regression and multiple linear regression using matrix notations, when residual errors are independent and they have constant variance. Use of categorical and continuous predictors in the model and interpretation of model parameters. Use of transformations. Estimation using ordinary least squares (OLS) and the properties of the estimator. Test of hypothesis, model diagnostics and prediction. ttest, analysis of variance and analysis of covariance as special cases of the model. Model formulation if the assumption of constant error variance and independence is not met (so called general linear model). Generalized least squares (GLS), maximum likelihood (ML), and restricted maximum likelihood. Review of generalized linear models (GLM, e.g. binary logistic regression). 
Modes of study 
Exercises and written exam 
Teaching methods 
Lectures (36 h) and exercises (18 h) 
Study materials 
Fahrmeir, L., Kneib, T., Lang, S. and Marx, Brian 2013. Regression models, methods and applications. Springer. Chapters 35. 
Evaluation criteria 
05 
Prerequisites 
Basic course in statistics, Rlanguage. Probabilistic inference for data science 1 and 2 / Introduction to statistical inference 1 and 2 are also suggested. Special tutorials on matrices will be arranged if needed. 

Letter (J, K) in front of the name of the course/exam indicates the campus on which teaching or exam takes place: J = Joensuu, K = Kuopio.
Present and future teaching
Future exams