Introduction

Course Introduction-Matrix Concepts, Model Method and Function Selection, Data Preprocessing and Multidimensional Data Processing (Introduction to Data Transformations, Introduction to Time Series Analysis, Transformation of non-stationary to stationary time series, testing for independence.

Regression

Linear-multiple linear regression, logistic regression, inverse normal regression (Probit regression), Crest Regression, Static/Dynamic Autoregression and Spectral Analysis. Spectral regression, multivariate analysis of variance (ANOVA-MANOVA). Exploratory factor analysis. Database mining and advanced prediction techniques. Experimental design. (Experimental design). Regression-based prediction modeling (forecast prediction, cancer prediction).

Regression Applications in Matlab

Linear Regression, Logistic Regression, Ridge regression, Supervised Workflow and Algorithms, Supportive Support Machines, Supervised Learning, Unsupervised Learning, Applications.

Thoughtful process

Linear Stochastic Processes, (Moving Average (MA) Processes), Interrelationship of AR and MA Processes, Auto-Switching Average Models (ARMA) (p, q) – Skill Estimation in ARMA (p, q), Box-Jenkins Approximation, ARIMA Models – ARIMA Model Estimation, ARIMA Models, ARIMA Model Forecasting – Diagnostic and Forecasting Model, Static Processes in the Frequency Domain, Spectral Analysis, Non Stationary Time Series, State Space Models-Kalman Filter, Relaxed Dynamic Models, Moving Medium (MA) Models, Vector autoreversion model, Multivariate models, SARMA models for stationary time series and ARIMA, SARIMA for non-stationary.

Nonlinear predictive models

Time Series Forecasting with Linear and Nonlinear Models, Nonlinearity Overview, Interaction Models, Polynomial Models, Step Models, Piecewise Models, (Linear and Polynomial), Spline Models (MARS), Nonlinear Time Series Analysis and Dynamical Systems, Forecasting with Local Models.

Applications of Time Series Analysis (Matlab)

Practice using Matlab in time series analysis, Using Matlab functions for AR, MA, ARMA, SARMA models, Time Series Programming, Linear Time Series analysis, Non-linear Time Series analysis and applications.

Regression Applications in R language

The R language environment, Syntax, Libraries, Basic Structures and Functions, Linear Regression, Logistic Regression, Linear Time Series Analysis, Using functions for AR, MA, ARMA, SARIMA models.

Applications of Time Series Analysis in R language

Programming for Time Series in R, Experimentation, Functions and programs in the R computing environment, Non-linear analysis of time series, Using Measures of Analysis of Time Series (MATS), Forecasting Applications.

Neural networks

Introduction to neural networks. Activation function. The gradient-descent method. Model representation. Back-propagation algorithm.

Applications of neural networks

Implementation of the backpropagation algorithm for neural networks in MATLAB. Examples of applying neural networks to forecasting problems.

Evaluating learning/prediction models

Model selection and evaluation. Diagnostic vs. Deviation. Validity assessment. Metrics for evaluating prediction results. Learning curves.