Data science, data mining, big data; supervised and unsupervised methods; predictive modelling, segmentation, classification trees; objective functions, classification and regression, logistic regression; similarity and distance, metrics, nearest-neighbour methods and clustering techniques; evaluation of classifiers, expected value framework, profit and lift curves.
1. The linear regression model. Descriptive analysis: ordinary least squares method, the coefficient of determination. Inferential analysis: parameters, least squares estimates and estimators, standard assumptions for the linear regression model, hypothesis tests on the coefficients.
2. Univariate time series analysis. Decomposition model. Trend, seasonality and cycle. Simple and weighted moving average. Additive and multiplicative model. Seasonality and seasonal coefficients. Trend estimate with analytical method.
3. Interpretation and comparison between data. Statistical ratio. Index numbers (simple and composed)