Estadistica Aplicada a las CCSS 2

Forecasting Time Serires with ARIMA Models Logit

1. Time Series. Forecasting with ARIMA models Characteristics of a time series: Frequency, trend and seasonal cycle. Concept of a stationary time series ACF an PACF White noise Autoregressive models AR (p) Moving average models MA (q) ARMA and ARIMA models Estimation and diagnosis. Forecasting Seasonal ARIMA models : identification, diagnosis and prediction. 2. Logistic regression. Logit Model Overview. Parameter estimation. Interpretation of the parameters. Model diagnose 3. Extensions

Theory (4ECTS). Lectures with support material available via web. Practices (2ECTS) Classes in computer classroom. Debates.