Welcome to "Computational Statistics" Classes

Course Outcomes

CO1: To understand the basic concepts of computational statistics and its related applications

CO2: Apply multivariate normal distribution functions and other statistical approaches to solve computational problems.

CO3: Demonstrate the ability to estimate the parameters of different statistical computing approaches.

CO4:  To perform different clustering approaches and interpret the resulting clusters through profiling and meaningful insights.

CO5: To evaluate the multivariate analysis of variance and covariance, including different machine learning techniques, hypothesis testing, and effect size estimation.

______________________________________________________

Unit-Wise Course Learning Outcomes

Multivariate Normal Distribution:

CLO1: Understand the properties and characteristics of the multivariate normal distribution.
CLO2: Apply multivariate normal distribution functions to solve practical problems.
CLO3: Demonstrate the ability to estimate parameters of a multivariate normal distribution from data.

Multiple Linear Regression Model:

CLO4: Develop a deep understanding of standard multiple regression models.
CLO5: Analyze and detect collinearity, outliers, non-normality, and autocorrelation in regression data.

Multivariate Regression:

CLO6: Identify and justify the assumptions underlying multivariate regression models.
CLO7: Apply methods for parameter estimation in multivariate regression, including the interpretation of results.
CLO8: Perform multivariate analysis of variance and covariance, including hypothesis testing and effect size estimation.

Discriminant Analysis:

CLO9: Apply linear discriminant function analysis to classify and distinguish among groups.
CLO10: Estimate linear discriminant functions and demonstrate an understanding of their discriminative power.

Principal Component Analysis:

CLO11: Understand the concept of principal components and their role in dimensionality reduction.
CLO12: Apply methods to determine an appropriate number of principal components to retain based on the explained variance.

Cluster Analysis:

CLO13: Understand the concepts of correlations and distances in clustering analyses.
CLO14: Apply partitioning methods, hierarchical clustering, and overlapping clustering techniques.
CLO15: Perform K-means clustering and interpret the resulting clusters through profiling and meaningful insights.