SAS/STAT® Training is an essential course, as it is a prerequisite for many courses in the statistical analysis domain. The course focuses on linear regression, logistics regression, Analysis of Variance (ANOVA), and regression diagnostics. Candidates will get exposure about the details of predictive modeling using regression model. Extensive training delivered by an industry expert will enable you to evaluate data from different sources including marketing databases, customer preference studies, health surveys, clinical trials, etc. and provide interpretation fulfilling the analytical needs of different industries including retail, telecommunication, manufacturing, biotechnology and more.
By the end of SAS/STAT® training you will hold the following capabilities:
- Explore data analysis and perform linear regression
- Illustrate the use of One-Way ANOVA and Two-Way ANOVA
- Conduct regression diagnostics and find out the influential observations
- Identify the use of logistic regression and take Tests of Association
- Interpretate predictive modeling and Adjustments for Oversampling
- Demonstrate the use of nonlinearities and multilayer perceptions
Target audience
- MBA graduates
- Academicians
- PhD scholars
- Survey researcher
- Market research
- Statisticians
- Risk analyst
Prerequisites
The candidate with the following skills can get the best out of this training:
- Basic understanding of statistics covering p-values, hypothesis testing, analysis of variance, and regression
- Create SAS data sets and run SAS programs
Module I: Introduction to SAS/STAT
1 Introduction to Statistics
- Fundamental Statistical Concepts
- Examining Distributions
- Confidence Intervals for the Mean
- Hypothesis Testing
2 Analysis of Variance (ANOVA)
- One-Way ANOVA: Two Populations
- ANOVA with More than Two Populations
- Two-Way ANOVA with Interactions
3 Regression
- Exploratory Data Analysis
- Simple Linear Regression
- Concepts of Multiple Regressions
- Model Building and Interpretation
4 Regression Diagnostics
- Examining Residuals
- Influential Observations
- Collinearity
5 Categorical Data Analysis
- Describing Categorical Data
- Tests of Association
- Introduction to Logistic Regression
- Multiple Logistic Regressions
- Logit Plots (Self-Study)
Module II: Introduction to predictive modeling using Regression Model
1. Predictive Modeling
- Introduction
- Analytical Challenges
2. Fitting the Model
- The Model
- Adjustments for Oversampling
3. Preparing the Input Variables
- Missing Values
- Categorical Inputs
- Variable Clustering
- Subset Selection
4. Classifier Performance
- Honest Assessment
- Misclassification
- Allocation Rules
- Overall Predictive Power
5. Nonlinearities and Interactions
- Detection
- Polynomials
- Multilayer Perceptions