Professional Documents
Culture Documents
Introducing statistical inference With 95% confidence we can say that there is an
85% chance, people visiting this site twice will
Estimators and confidence intervals enroll for the course . Here, you learn how to
Central Limit theorem create a hypothesis, test and validate it through
Parametric and non-parametric statistical tests data within a statistical framework and present it
with clear and formal numbers to support decision
Analysis of variance (ANOVA) making.
Conducting statistical tests
Practice assignment
Predictive modelling in R
1. Correlation and Linear regression
Correlation A statistical model is the core of predictive analytics
Simple linear regression and regression is one of the most powerful tools for
making predictions by finding patterns in data. You
Multiple linear regression shall learn the basic of regression modelling hands-
Model diagnostics and validation on through real world cases
Case study
2. Logistic regression Logistic regression is the work-horse of the
predictive analytics world. It is used to make
Moving from linear to logistic
predictions in cases where the outcomes are dual in
Model assumptions and Odds ratio nature i.e. an X or Y scenario where we need to
Model assessment and gains table predict if X will be the case or will Y, given some
ROC curve and KS statistic data. This is a must-know technique and we shall
make you comfortable with it through real world
Case Study problems.
3. Techniques of customer segmentation
Need for segmentation
Criterion of segmentation Learn why and how to statistically divide a broad
Types of distances customer market into various segments of
customers who are similar to each other so as to be
Clustering algorithms
able to better target and meet their needs in a cost
o Hierarchical clustering effective manner. This is one of the most essential
o K-means clustering techniques in marketing analytics.
Deciding number of clusters
Case study
4. Time series forecasting techniques The ability to forecast into the future is very
Need for forecasting important for any business and it is necessary to
What are time series? have as accurate a forecasting as possible for
Smoothing techniques financial and strategic planning. In this module
Time series models learn the techniques of time series analysis without
ARIMA being misled by seasonal and cyclical impacts.
5. Decision trees Decision trees are predictive models which map
What are decision trees observations about an item to conclusions about
Entropy and Gini impurity index the item's target value. Learn the technique of
Decision tree algorithms decision trees, one of the most popular predictive
analytics techniques
CART & CHAID
Case Study
SAS Training
Fundamentals of SAS
What is the SAS software?
Why is it used? In this section we shall provide you an overview
SAS GUI layout into the SAS software and the SAS language.
Components of a SAS program
SAS libraries and library referencing
SAS datasets & variables
Accessing Data in SAS
Creating SAS datasets
Referencing SAS files
Reading SAS datasets
In this module you will learn how to read a SAS data
Read/Import raw data files in SAS file and import or read into SAS any raw data file
INPUT statement and its components for eg: an excel file or a csv file.
Infile, Informat statements and Proc Import
Reading delimited data
Combine SAS datasets using DATA step
Managing Data in SAS
Investigate SAS datasets using basic Procs
Sorting observations
Conditional execution of SAS statements This is where you shall learn how to manage and
Assignment statements in DATA step manipulate data using SAS to meet business
Variable attribute modification requirements
Using BY statement to create totals and sub-totals
Various SAS functions to manipulate data
Merging datasets
Advanced SAS
This is where you shall learn advanced ways to
PROC SQL for ETL in SAS
manage and work with data using SAS
Writing and working with SAS Macros
Predictive Analytics in SAS 1
Hypothesis testing
Correlation , Variable Transformations In this module you will learn the SAS for predictive
Simple Linear Regression modeling basics
Multiple Linear Regression
Model Diagnostics
Model Performance Assessment and Validation
Predictive Analytics in SAS 2
Introduction to classification
Supervised Classification : Logistic Regression In this module you will learn the SAS for advanced
Model Scoring and Cutoffs predictive modeling
Unsupervised Classification : Clustering
Cluster Profiling
Final Case Study
Simulation of an actual analytics project where you
shall be completely hands-on and you will
Solving an actual business problem through analytics –
understand how everything you have learnt so far
Simulating an analytics project
comes together to solve a business problem
through analytics