SAS Statistical Business Analyst Certification Preparation Course on Regression and Modeling 

(Exam ID: A00-240)

The full “SAS programming statistical business analyst certification course” is divided into two parts:

1. SAS programming statistical business analyst certification course – Part 1: ANOVA, Data Preparation for Predictive Modeling and Linear Regression Analysis

2. SAS programming statistical business analyst certification course – Part 2: Logistic Regression Analysis and Measure of Model Performance

Together, these two parts form a comprehensive preparation program for the SAS Certified Statistical Business Analyst Using SAS 9.4: Regression and Modeling exam (Exam ID: A00-240). This SAS certification is one of the featured credentials offered by SAS, adding value to your professional portfolio. Whether you’re looking to enhance your analytical skills or advance your career, this course provides the essential knowledge and hands-on experience needed to succeed.

Prerequisites

Basic knowledge of statistical analysis is highly recommended for an optimal learning experience.

What You Will Learn

By taking this course, you will gain mastery in:

• Analysis of Variance (ANOVA)

• Preparing Inputs for Predictive Models

• Linear Regression Analysis

• Logistic Regression Analysis

• Measuring Model Performance

Course Methodology

• Each lecture begins with key concepts and coding rules presented in PowerPoint slides, followed by hands-on SAS programming sessions.

• Structured Learning: Statistical concepts are presented through engaging PowerPoint presentations.

• Comprehensive Output Analysis: Detailed explanations of all statistical outputs help solidify your understanding.

• End-to-End Predictive Modeling: Covers data preparation, sampling, model building, validation, scoring, and performance measurement.

Additional Course Features

• 24/7 access to pre-recorded, self-paced lectures

• Downloadable Resources: All datasets, SAS programs, and PowerPoint slides used in the course are available for download in Lecture 4 (Note: Materials are for practice only and are protected by copyright).

• Quizzes & Assessments: Test your knowledge with quizzes at the end of each section.

SAS Software for This Course

This course was originally developed using SAS University Edition but has been fully updated for SAS OnDemand for Academics—a free, web-based version of SAS Studio. The software’s interface, functionality, and appearance remain consistent, ensuring a seamless learning experience.

📌 Detailed instructions for using SAS OnDemand for Academics are provided in Section 2.

Course Ratings and Reviews

Your honest and thoughtful feedback is highly appreciated! Your ratings help improve course content and enhance your learning experience.

This course is regularly updated to reflect the latest SAS certification changes and incorporate student suggestions, ensuring it remains relevant and valuable. Fair and constructive reviews are essential to improving the course’s quality, and I truly appreciate your honest input. In this field, course ratings above 4.5 are widely regarded as indicators of high-quality content.

Thank you for your support!

Next, feel free to explore our full course content with detailed lecture breakdowns, watch lecture previews on YouTube, visit our course pages for more information, and browse our complete course catalog, featuring both FREE course and premium courses with flexible pricing plans. 

Course Contents

Part 1

Section: Analysis of Variance (ANOVA)

·       Using TTEST to compare means

·       Using Proc Univariate to Test the Normality Assumption Using the K-S Test

·       ANOVA 1. One-factor ANOVA model and Test Statistic in PowerPoint Presentation

·       ANOVA 2. The GLM Procedure for Investigating Mean Differences

·       ANOVA 3. generate Predicted Values & Residuals Use OUTPUT Statement in Proc GLM

·       ANOVA 4. Measures of fit: output explanation of one-way ANOVA

·       ANOVA 5. The Normality Assumption and the PLOTS Option in Proc GLM

·       ANOVA 6. Levene's Test for Equal Variances and the MEANS Statement in Proc GLM

·       ANOVA 7. Post Hoc Tests: The Tukey-Kramer Procedure and the MEANS Statement

·       ANOVA 8. Other Post Hoc Procedures, the LSMEANS Statement, and the Diffogram

·       ANOVA 9. the Randomized Block Design with example and Interpretation

·       ANOVA 10. Randomized block design: Post Hoc Tests Using the LSMEANS Statement

·       ANOVA 11. Assess Assumptions of a Randomized Block Design Using the PLOTS Option

·       ANOVA 12. Unbalanced Designs, the LSMEANS Statement and Type III Sums of Squares

·       ANOVA 13. Two factor ANOVA: overview in PowerPoint Presentation

·       ANOVA 14. Example and Interpretation of the Two-Factor ANOVA

·       ANOVA 15. Analyze Simple Effects When Interaction Exists Use LSMEANS with Slice

·       ANOVA 16. Assessing the Assumptions of a Two-Factor Analysis of Variance

·       Quiz: Analysis of Variance (ANOVA)

Section: Prepare Inputs Vars for predictive Modeling

·       Prepare Inputs Vars 1. Chapter Overview

·       Prepare Inputs Vars 2. Missing values and imputation

·       Prepare Inputs Vars 3. Categorical Input Variable 1.Knowledge points

·       Prepare Inputs Vars 3. Categorical Input Variables 2. Proc freq and Proc Means

·       Prepare Inputs Vars 3. Categorical Input Variables 3. Proc Cluster

·       Prepare Inputs Vars 3. Categorical Input Variables 4. Cut off point

·       Prepare Inputs Vars 3. Categorical Input Variables 5. cluster var

·       Prepare Inputs Vars 4. Variable Cluster: 1. Slides on VARCLUS for redundancy

·       Prepare Inputs Vars 4. Variable Cluster: 2. Proc VARCLUS for reduce redundancy

·       Prepare Inputs Vars 5. Variable Screening: 1. Overview on Knowledge Points

·       Prepare Inputs Vars 5. Variable Screening: 2. Proc CORR detect Association_Part A

·       Prepare Inputs Vars 5. Variable Screening: 3. Proc CORR detect Association_Part B

·       Prepare Inputs Vars 5. Variable Screening: 4. Proc CORR detect Association_Part C

·       Prepare Inputs Vars 5. Variable Screening: 5. Empirical Logit detect Non-Linear

·       Quiz: Prepare Inputs Vars

Section: Linear Regression Analysis

·       Exploring the Relationship between Two Continuous Variables using Scatter Plots

·       Producing Correlation Coefficients Using the CORR Procedure

·       Multiple Linear Regression: fit multiple regression with Proc REG

·       Multiple Linear Regression: Measures of fit

·       Multiple Linear Regression: Quantifying the Relative Impact of a Predictor

·       Multiple Linear Regression: Check Collinearity Using VIF, COLLIN, and COLLINOINT 

.    Fit simple linear regression with Proc GLM

·       Multiple Linear Reg: Var Selection With Proc REG: all possible subset: adjust R2

·       Multiple Linear Reg: Var Selection With Proc REG: all possible subset: Mallows Cp

·       Multiple Linear Regression: Variable Selection With Proc REG: Backward Elimination

·       Multiple Linear Regression: Variable Selection With Proc REG: Forward selection

·       Multiple Linear Regression: Variable Selection With Proc REG: Stepwise selection

·       Multiple Linear Regression: Variable Selection With Proc GLMSELECT

·       Multiple Linear Regression: PowerPoint Slides on regression assumptions

·       Multiple Linear Regression: regression assumptions

·       Multiple Linear Regression: PowerPoint Slides on influential observations

·       Multiple Linear Regression: Using statistics to identify influential observation

·       Quiz: Linear Regression Analysis

Part 2

Section: Logistic Regression Analysis

·       Logistic Regression Analysis: Overview

·       logistic regression with a continuous numeric predictor Part 1

·       logistic regression with a continuous numeric predictor Part 2

·       Plots for Probabilities of an Event

·       Plots of the Odds Ratio

·       logistic regression with a categorical predictor: Effect Coding Parameterization

·       logistic reg with categorical predictor: Reference Cell Coding Parameterization

·       Multiple Logistic Regression: full model SELECTION=NONE

·       Multiple Logistic Regression: Backward Elimination

·       Multiple Logistic Regression: Forward Selection

·       Multiple Logistic Regression: Stepwise

·       Multiple Logistic Regression: Customized Options

·       Multiple Logistic Regression: Best Subset Selection

·       Multiple Logistic Regression: model interaction

·       Multiple Logistic Reg: Scoring New Data: SCORE Statement with PROC LOGISTIC

·       Multiple Logistic Reg: Scoring New Data: Using the PLM Procedure

·       Multiple Logistic Reg: Scoring New Data: the CODE Statement within PROC LOGISTIC

·       Multiple Logistic Reg: Score New Data: OUTMODEL & INMODEL Options with Logistic

·       Quiz: Logistic Regression Analysis

Section: Measure of Model Performance

·       Measure of Model Performance: Overview

·       PROC SURVEYSELECT for Creating Training and Validation Data Sets

·       Measures of Performance Using the Classification Table: PowerPoint Presentation

·       Using The CTABLE Option in Proc Logistic for Producing Classification Results

·       Assessing the Performance & Generalizability of a Classifier: PowerPoint slides

·       The Effect of Cutoff Values on Sensitivity and Specificity Estimates

·       Measure of Performance Using the Receiver-Operator-Characteristic (ROC) Curve

·       Model Comparison Using the ROC and ROCCONTRAST Statements

·       Measures of Performance Using the Gains Charts

·       Measures of Performance Using the Lift Charts

·       Adjust for Oversample: PEVENT Option for Priors & Manually adjust Classification

·       Manually Adjusting Posterior Probabilities to Account for Oversampling

·       Manually Adjusted Intercept Using the Offset to account for oversampling

·       Automatically Adjusted Posterior Probabilities to Account for Oversampling

·       Decision Theory: Decision Cutoffs and Expected Profits for Model Selection

·       Decision Theory: Using Estimated Posterior Probabilities to Determine Cutoffs

·       Quiz: Measure of Model Performance