This course provides a comprehensive understanding of time series data and forecasting techniques. It begins with classical decomposition methods, including trend and seasonality estimation using moving averages and exponential smoothing techniques such as Holt and Holt-Winters methods. The course then introduces stochastic models, covering autocorrelation functions, stationarity, and Box-Jenkins models including AR, MA, ARMA, and ARIMA. Estimation methods like Yule-Walker, maximum likelihood, and least squares are explored alongside model diagnostics and forecasting. Advanced topics include spectral analysis, seasonal ARIMA models, and an introduction to ARCH and GARCH models for modeling volatility.
This course introduces students to the fundamentals of Python programming with a focus on applications in statistical computing and data analysis. It covers core programming concepts including data types, control flow, functions, and object-oriented programming. Students will learn to process text and CSV files, handle exceptions, and visualize data using Python libraries. The course emphasizes statistical testing, data visualization techniques, and the simulation of random variables using Python. Practical applications include implementing analytical and sampling methods, performing hypothesis tests, and understanding probability distributions through simulation.
- BCM Teacher: Dona Joseph