ANALYTICS PLUS

Simple statistical models for smarter decision-making. This course introduces participants to fundamental concepts of statistics, and guides them all the way to building predictive models using multiple linear and logistic regressions. All topics are explained with the help of hands-on practice on live case studies and data, enabling a deeper understanding of the underlying concepts

ADVANCED ANAYTICS Course Contents

o Introduction to analytics, measures of central tendency & test of competence

o Cross Tabulation & Introduction to Probability

o Bayesian Probability

o Regression - Fundamental concepts & assumptions of OLS Regression, Multi co linearity, Outlier detection, Model validation & Stepwise regression

o Logistic Regression - Fundamental concept & Sampling of Logistic Regression, Interpreting & Preparing data

o Evaluating model performance (Lifts, ROC curve, KS statistics, C statistic), Industry concepts / application with live case, CRISP DM, Example of attrition modeling

o Factor Analysis - FA and Principal Component analysis, Factor extraction, Assessing the fit of the model, Rotating the factors for aiding interpretability, Computing factor scores

o Cluster Analysis - Selecting the variables for use In clustering, Choosing a distance measure, Assessing different solutions, K-Means clustering for large datasets

o Discriminant Analysis - Fundamental concept & Assumptions of linear discriminate analysis (LDA), Similarities and differences between LDA and logistic regression. Applications

o Other topics in Predictive modeling - Typical challenges in data analysis, Missing values and their treatment, A case of too few and too many (too few records and too many variables)