Statistics

A.Y. 2020/2021
9
Max ECTS
60
Overall hours
SSD
SECS-S/01
Language
Italian
Learning objectives
The teaching main aim is to ensure that students acquire an appropriate knowledge and degree of understanding of the suitable tools to synthetically describe one or more variables of interest that are found in the most varied fields (economic, sociological, political, administrative, historical, legal, etc.). This description can be made by aggregating the observed data in tables, giving an adequate graphical representation, constructing appropriate position and variability indices, identifying the most suitable measures that highlight the relationships. When the survey is not total but partial, in addition to statistical description, statistical induction is also needed; in this case the knowledge of the variables is not in "certain" terms but only "probable" and has the purpose of providing indications on the entire reference community. The basic arguments of Probability and Statistical Inference are therefore provided. Knowledge and understanding of these tools require a strong application capacity.
Expected learning outcomes
At the end of the teaching the students will know the basic concepts of Descriptive and Inferential Statistics and they will be able to apply them in different contexts. They must have developed a marked independence of judgment, acquired in the appropriate choice of the most suitable techniques for solving the proposed problems, and they will have refined their communication skills, through the presentation of the methodologies and logical paths used in solving the questions. Finally, they must have acquired a more and more refined ability to learn, developed in the analysis of new situations with a high degree of autonomy.
Course syllabus and organization

Single session

Responsible
Lesson period
First trimester
The lessons will be delivered synchronously on the Microsoft Teams platform. The exams will preferably be conducted in the classroom.
Course syllabus
Introduction to statistical methodology.
Descriptive statistics and inferential statistics.
Sampling and measurement.
Descriptive statistics: tables and graphs, describing the "center" of the data, describing variability of the data, measures of position, bivariate descriptive statistics, sample statistics and population parameters.
Probability distributions for discrete and continuous variables.
The Normal probability distribution.
Sampling distributions.
Statistical inference: point and interval estimation.
Statistical inference: significance tests.
Analyzing association between categorical variables (contingency tables, chi-square test of independence).
Linear regression and correlation.
Index numbers.
Prerequisites for admission
No prior knowledge is required
Teaching methods
In addition to the 60 hours of traditional lectures, where the topics will be presented in a theoretical way and through application examples, 20 hours of classroom exercises are planned. Moreover, to make ease the student learning, exercises have been prepared for each topic, whose commented solution can be found in Ariel under "Content - exercises".
Teaching Resources
Statistica
A. Agresti, B. Finlay, F. De Battisti, F. Porro
Corso di laurea in Scienze Politiche
Università degli Studi di Milano
9788891920607
(and on-line material available in Ariel).
Assessment methods and Criteria
The exam consists of a written test, with numerical exercises and multiple choice theoretical questions, which must be justified. During the test you can use the calculator. The evaluation, expressed in thirtieths, is aimed at verifying the understanding of the theoretical concepts presented in the lessons and the ability to face practical problems through the autonomous choice of the most suitable tools, the ability to apply them and the evaluation of the results obtained. The results of the exam will be published in Ariel. The exam archive is available in Ariel and the solutions are provided (http://ariel.unimi.it/).
SECS-S/01 - STATISTICS - University credits: 9
Lessons: 60 hours
Professor(s)