Riippuvuusanalyysi (Statistical Analysis of Contingency and Regression)
Note: THIS VERSION IS OUTDATED.
Updated information is available in moodle.


Code: STAT1010

Credit units: 5 ECTS credits

Course objective: Provide the student with sufficient skills to analyze the dependence between statistical variables, both with pen and paper calculations and using a spreadsheet program like Microsoft Excel.

Contents: Contingency tables, non-parametric methods, ANOVA and muliple regression analysis.

Prerequisites: Introduction to Statistics (STAT1030) or Probability and Statistics (MATH1170)

Teacher: Lecturer Bernd Pape

Teaching: 30h Lectures and 14h Exercises.

Language of Instruction: English.
Exception: Exercise groups 4, 5 and 6 will be taught in Finnish.

Statistical Software: Microsoft Excel. We shall extensively use the free Real Statistics Resource Pack by Charles Zaiontz, which adds a lot of statistical functionality to Microsoft Excel. The software can be downloaded here. Thank you Charles for your kind permission to let us use your software in this course.
After installation of the software there should be a Real Statistics option in the Add-Ins ribbon of Excel. If that is not the case, take the following steps:
1. If Excel is running, close it.
2. Find the file with the Real Statistics add-in (RealStats.xlam). Right click on the file and click on the Properties option from the menu that appears.
3. Towards the bottom of the General tab of the Properties window you will see the security message “This file came from another computer and might be blocked to help protect this computer”. Next to this message is the Unblock check box. Make sure this is checked and press the OK button.
4. Start Excel.
Note that you must activate not only the Real Statistics Add-In, but also Excels own Analysis ToolPack (Analyysityökalut) and Solver Add-In (Ratkaisin) under File / Options / Add-Ins / Manage / Excel Add-ins (Shortcut Alt-TI) in order for all examples to work. Ideally, the Solver Add-In should be activated, before the Real Statistics Add-In is installed.

Lecture Notes:
The English slides used during the lectures can be downloaded here:
Chapter 1: Introduction - Interdependence of Statistical Variables
Chapter 2: Chi Square Homogeneity Tests
Chapter 3: Nonparametric Methods
C.4.1-4.3: One-Way Analysis of Variance
Chap. 4.4: Further Analysis within ANOVA
Chap. 4.5: Two-Way Analysis of Variance
Chapter 5: Multiple Linear Regression
Chapter 5: Nonlinear Transformations, Logistic Regression, Multicollinearity

The corresponding slides of an earlier course by Pentti Suomela held in Finnish, which used SPSS software, may be downloaded here. The contents of the slides are for the most part the same as our course, but the contents you must learn for the exam is given in the English lecture notes above. I give the Finnish slides only as a support for students finding it difficult to learn from material written in English or in case you prefer using SPSS instead of Excel.

Exercises:
Exercise Sheet 1, Data Ex1.1, Data Ex1.2, Data Ex1.3;
Exercise Sheet 2, Data Ex2.3, Data Ex2.4;
Exercise Sheet 3, Data Ex3.1+2, Data Ex3.3, Data Ex3.4;
Exercise Sheet 4, Data Ex4.1, Data Ex4.2, Data Ex4.3+4;
Exercise Sheet 5, Data Ex5.2, Data Ex5.3, Data Ex5.4;
Exercise Sheet 6, Data Ex6.3, Data Ex6.4;
Exercise Sheet 7, Data Ex7.1, Data Ex7.2, Data Ex7.3.

Course literature:
Aczel, A.D.: Complete Business Statistics, McGraw-Hill, Chapters 9-11, 14;
Moore/McCabe: Introduction to the Practice of Statistics, Freeman, Chapters 9-13, 15-16;
Milton/Arnold: Introduction to Probability and Stochastics, McGraw-Hill, Chapters 11-13;

Statistical Formulas and Tables: Download here
You may and should bring the formulas and tables to the exam.

Translating Excel's Statistical Formulas into Finnish:
The lecture notes assume that the language in Excel is set to English (U.S.), as it is on campus. You may change the language settings of Excel under File => Options => Language. The names of the statistical functions change in case you use a different language. You may find the Finnish equivalent to the statistical functions from the lecture notes by using the links below:
Excelin funktiot suomeksi ja englanniksi
Excelin funktiot (luokittain)