Statistics

The course aims to introduce students to statistical inference: population and samples, likelihood function, point, and interval estimation, hypothesis testing, and prediction. The multivariate Gaussian distribution and multiple linear regression are described, along with diagnostics measures and predictions. 

Elements of time series data analysis are introduced: autocovariance and autocorrelation functions and  related plots, white noise and stationary processes, and AR(1) and MA(1) processes. 

The course  provides skills in using the semantics of the free software environment R for descriptive univariate and multivariate data analysis, inferential methods, and estimation of statistical models. 

Theory and practical applications are jointly developed to support students with deep theoretical and practical   knowledge. The R environment within the RStudio and RMarkdown is employed to create live code, output, and comments on the results in the same interface and to produce reproducible          documents.

The course aims to provide students with methodological and applied background on inferential statistics, multiple linear regression models, and specific descriptive and inferential procedures for analyzing  financial time series. 

Prior knowledge of the following topics is required: probability, expectation, and variance of a random   variable, principal continuous and discrete distributions of random variables, and basic notions of matrix algebra.             

Knowledge of the statistical software R is expected with the simultaneous Programming in Finance and Economics I course.

• Partnerships for the goals

In presence

Lectures ex-cathedra.
Students are requested to bring their laptops.

Teaching notes will be distributed during the course. 

Homework assignments and a final written exam with open questions on the theoretical part and an application to develop using the R software.