37321 - Statistics for Data Analysis

Learning outcomes

At the end of the course the student will have acquired knowledge of the main tools used in auditing for statistical sampling and basic concepts of prediction and classification. The student will be able to study the dependence of a selected variable from a set of explanatory variables through a multiple regression model; to tackle problems of classification both through discriminant analysis and logistic regression. 

Course contents

The contents of the course will include:

1) Review of Statistical Inference tools

Brief review of the main concepts of point estimation, hypothesis testing and confidence intervals.

2) Review of the simple linear regression model

Motivation and definition of the simple linear mode. Parameter estimation and hypothesis testing. Goodness-of-fit of the model.

3) Multiple linear regression model

Motivation and definition of multiple linear regression. Parameter estimation and hypothesis testing. Goodness-of-fit of the model.

4) Logistic regression model

Motivation and definition of logistic regression model. Parameter estimation and hypothesis testing. Application of the logistic regression to classification problems.

5) Applications through the software R

Each topic will be completed with the analysis of case studies through the statistical software R.

Readings/Bibliography

• Textbook used for the Statistics course of the Bachelor degree and possible other textbooks used in subsequent courses of Statistics (e.g. Business Statistics).                                       
  
• Lectures notes that will be made available online on the course site on Virtuale
• For R:
  1. E-Book: "R Programming", tutorialspoint, Websidte https://www.tutorialspoint.com/r/index.htm
  2. Website: "Quick-R – Home Page", at  https://www.statmethods.net/
     

Teaching methods

Traditional lectures in the classroom. For the applications, students are asked to bring their own portable computer to the classroom on which they have previously installed the packages R and RStudio. (See Teaching tools for details on the installation.)

Assessment methods

FORMAT

Students will be assessed by a written examination that will focus on all the topics covered during the course (including questions on R.

Students can choose to solve a home assignment on data analysis that will count for up to 3 points of the final mark. For the home assignment, students will work in pairs and will  identify a problem and a data that can be studied either with a linear regression model or classification tools. Solutions to the home assignment will have to be returned within the date specified during the lectures. The home assignment points will be added to the written exam mark, only if the latter is sufficient and will be considered up to the September exam (included).

Note: The exam format might change according to the evolution of the health situation.

 

GRADE REJECTION

The exam mark can be rejected at most once. For the rejection, students must send an email to paola.bortot@unibo.it within the specified date. 

 

Teaching tools

• The software R will be used for the application of the taught tools. R can be freely downloaded from the web site http://www.r-project.org/. The package RStudio will be used as an interface for R. RStudio can be freely downloaded from https://www.rstudio.com/products/rstudio/download/  (Make sure that the free version suitable for the operating system used is downloaded.)

• The teaching material (including lectures notes) will be available on the platform Virtuale at the beginning of the course.

 

Office hours

See the website of Paola Bortot