This course aims at presenting statistical concepts and techniques in a manner that will teach students not only how and when to utilize statistical procedures but also to understand why these procedures should be used. Concepts will be motivated, illustrated, and explained in a way that attempts to increase one’s intuition. To illustrate the diverse applications of statistics (with a particular focus on the Economics applications) and to offer students different perspectives about the use of statistics, the course will provide a wide variety of examples and problems, mostly referring to real-world issues. Moreover, the use of software to apply the theoretical models and obtain concrete results in real data analysis will be largely discussed.
At the end of the course, the students will gain the ability to: a) perform point and interval estimation in the univariate statistical model. b) Perform a test of the hypothesis and interpret the relative p-value. c) Perform a linear regression model using statistical software; interpret the analysis results.
Course Prerequisites
Good knowledge of the main concepts of descriptive statistics: how to organize and describe data via tables, graphs and indices. Basic knowledge of Probability Theory.
Compulsory prerequisites required (Propedeuticità) are published on the website: https://lt-eco.unibg.it/it/node/119
Compulsory: Statistica I
Teaching Methods
The course is taught through class lectures.
Assessment Methods
The exam is in written form. It consists of several exercises. The student must identify proper techniques among those learned in the course. One exercise will be devoted to using or interpreting a linear regression model fitted with statistical software.
Contents
PROBABILITY: Conditional probability. Bayes formula. Distributions. Random variables. Expected value. Note on subjective probability. Sequences of random variables and stochastic convergences. Multiple normal. Linear combinations of normals. STATISTICAL INFERENCE. Point parametric estimation, estimation methods, efficient estimation. Interval estimation; Parametric and non-parametric hypothesis tests. Linear regression.
