Predictive Modeling with Logistic Regression using SAS

This course is part of SAS Statistical Business Analyst Professional Certificate

Instructor: Marc Huber

Access provided by BAC Education Group

8,226 already enrolled

7 modules

Gain insight into a topic and learn the fundamentals.

63 reviews

Intermediate level

Some related experience required

2 weeks to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

7 modules

Gain insight into a topic and learn the fundamentals.

63 reviews

Intermediate level

Some related experience required

2 weeks to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

Skills you'll gain

Tools you'll learn

SAS (Software)

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

40 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your Data Analysis expertise

This course is part of the SAS Statistical Business Analyst Professional Certificate

When you enroll in this course, you'll also be enrolled in this Professional Certificate.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate from SAS

There are 7 modules in this course

This course covers predictive modeling using SAS/STAT software with emphasis on the LOGISTIC procedure. This course also discusses selecting variables and interactions, recoding categorical variables based on the smooth weight of evidence, assessing models, treating missing values, and using efficiency techniques for massive data sets. You learn to use logistic regression to model an individual's behavior as a function of known inputs, create effect plots and odds ratio plots, handle missing data values, and tackle multicollinearity in your predictors. You also learn to assess model performance and compare models.

What's included

1 video7 readings

1 video Total 1 minute

Meet the Instructor 1 minute

7 readings Total 71 minutes

What You Learn in This Course 5 minutes
Learner Prerequisites 1 minute
Using Forums and Getting Help 5 minutes
Access SAS Software for this Course 10 minutes
Set Up Data for This Course (REQUIRED) 30 minutes
About the Demos and Practices in this Course 10 minutes
Frequently Asked Questions 10 minutes

In this module, you review the fundamentals of predictive modeling. Then you explore the business scenario data that is used throughout the course. Finally, you learn about common analytical challenges that you might encounter as a modeler.

What's included

15 videos1 reading6 assignments

15 videos Total 34 minutes

Overview 1 minute
Introduction 0 minutes
Goals of Predictive Modeling 2 minutes
Terms for Elements in Predictive Modeling 1 minute
Basic Steps of Predictive Modeling 3 minutes
Applications of Predictive Modeling 2 minutes
Demonstration Scenario: Target Marketing for a Bank 2 minutes
Demo: Examining the Code for Generating Descriptive Statistics and Frequency Tables 2 minutes
Introduction 0 minutes
Data Challenges 6 minutes
Analytical Challenges 2 minutes
Separate Sampling 2 minutes
Avoiding the Optimism Bias: Honest Assessment 2 minutes
Splitting the Data for Model Training and Assessment 3 minutes
Demo: Splitting the Data 5 minutes

1 reading Total 10 minutes

Summary 10 minutes

6 assignments Total 75 minutes

Practice: Exploring the Bank Data for the Target Marketing Project 20 minutes
Practice: Exploring the Veterans' Organization Data Used in the Practices 20 minutes
Question 1.01 5 minutes
Question 1.02 5 minutes
Question 1.03 5 minutes
Practice: Splitting the Data 20 minutes

In this module, you investigate the concepts behind the logistic regression model. Then you learn to use the LOGISTIC procedure to fit a logistic regression model. Finally, you learn how to score new cases and adjust the model for oversampling.

What's included

18 videos1 reading4 assignments

18 videos Total 54 minutes

Overview 1 minute
Introduction 0 minutes
Understanding the Logistic Regression Model 3 minutes
Constraining the Posterior Probability Using the Logit Transformation 2 minutes
Understanding the Fitted Surface 1 minute
Interpreting the Model by Calculating the Odds Ratio 3 minutes
Understanding Logistic Discrimination 2 minutes
Estimating Unknown Parameters Using Maximum Likelihood Estimation 2 minutes
Interpreting Concordant, Discordant, and Tied Pairs 2 minutes
Using PROC LOGISTIC to Fit Logistic Regression Models 0 minutes
Demo: Fitting a Basic Logistic Regression Model, Part 1 8 minutes
Demo: Fitting a Basic Logistic Regression Model, Part 2 12 minutes
Scoring New Cases 0 minutes
Demo: Scoring New Cases 8 minutes
Introduction 0 minutes
Understanding the Effect of Oversampling 1 minute
Understanding the Offset 2 minutes
Demo: Correcting for Oversampling 7 minutes

1 reading Total 10 minutes

Summary 10 minutes

4 assignments Total 60 minutes

Question 2.01 5 minutes
Question 2.02 5 minutes
Practice: Fitting a Logistic Regression Model 20 minutes
Fitting the Model Review 30 minutes

In this module, you learn how to deal with common problems with your predictor variables such as missing values, categorical predictors with many levels, a high number of redundant predictors, and nonlinear relationships with the response variable.

What's included

26 videos9 assignments

26 videos Total 76 minutes

Overview 1 minute
Introduction 0 minutes
Reasons for Missing Data 3 minutes
Complete Case Analysis 2 minutes
Methods for Imputing Missing Values 3 minutes
Missing Value Imputation with Missing Value Indicator Variables 4 minutes
Demo: Imputing Missing Values 4 minutes
Cluster Imputation 2 minutes
Introduction 0 minutes
Problems Caused by Categorical Inputs 4 minutes
Solutions to Problems Caused by Categorical Inputs 1 minute
Linking to Other Data Sets 1 minute
Collapsing Categories by Thresholding 1 minute
Collapsing Categories by Using Greenacre's Method 3 minutes
Demo: Collapsing the Levels of a Nominal Input, Part 1 6 minutes
Demo: Collapsing the Levels of a Nominal Input, Part 2 10 minutes
Replacing Categorical Levels by Using Smoothed Weight-of-Evidence Coding 3 minutes
Demo: Computing the Smoothed Weight of Evidence 5 minutes
Introduction 0 minutes
Problem of Redundancy 2 minutes
Variable Clustering Method 1 minute
Understanding Principal Components 5 minutes
Divisive Clustering 4 minutes
PROC VARCLUS Syntax 1 minute
Selecting a Representative Variable from Each Cluster 1 minute
Demo: Reducing Redundancy by Clustering Variables 9 minutes

9 assignments Total 105 minutes

Question 3.01 5 minutes
Practice: Imputing Missing Values 20 minutes
Question 3.02 5 minutes
Question 3.03 5 minutes
Question 3.04 5 minutes
Practice: Collapsing the Levels of a Nominal Input 20 minutes
Practice: Computing the Smoothed Weight of Evidence 20 minutes
Question 3.05 5 minutes
Practice: Reducing Redundancy by Clustering Variables 20 minutes

In this module, you learn how to select the most predictive variables to use in your model.

What's included

23 videos1 reading12 assignments

23 videos Total 92 minutes

Introduction 0 minutes
Detecting Nonlinear Relationships 4 minutes
Demo: Performing Variable Screening, Part 1 6 minutes
Demo: Performing Variable Screening, Part 2 4 minutes
Univariate Binning and Smoothing 3 minutes
Demo: Creating Empirical Logit Plots 10 minutes
Remedies for Nonlinear Relationships 2 minutes
Demo: Accommodating a Nonlinear Relationship, Part 1 6 minutes
Demo: Accommodating a Nonlinear Relationship, Part 2 8 minutes
Introduction 0 minutes
Specifying a Subset Selection Method in PROC LOGISTIC 2 minutes
Best-Subsets Selection 1 minute
Stepwise Selection 3 minutes
Backward Elimination 2 minutes
Scalability of the Subset Selection Methods in PROC LOGISTIC 3 minutes
Detecting Interactions 3 minutes
BIC-based Significance Level 3 minutes
Demo: Detecting Interactions 7 minutes
Demo: Using Backward Elimination to Subset the Variables 4 minutes
Demo: Displaying Odds Ratios for Variables Involved in Interactions 4 minutes
Demo: Creating an Interaction Plot 3 minutes
Demo: Using the Best-Subsets Selection Method 4 minutes
Demo: Using Fit Statistics to Select a Model 10 minutes

1 reading Total 10 minutes

Summary of Preparing the Input Variables, Parts 1 and 2 10 minutes

12 assignments Total 160 minutes

Question 3.06 5 minutes
Practice: Performing Variable Screening 20 minutes
Practice: Creating Empirical Logit Plots 20 minutes
Question 3.07 5 minutes
Question 3.08 5 minutes
Question 3.09 5 minutes
Practice: Using Forward Selection to Detect Interactions 20 minutes
Question 3.10 5 minutes
Practice: Using Backward Elimination to Subset the Variables 20 minutes
Question 3.11 5 minutes
Practice: Using Fit Statistics to Select a Model 20 minutes
Preparing the Input Variables Review 30 minutes

In this module, you learn how to assess the performance of your model and how to determine allocation rules that maximize profit. Finally, you learn how to generate a family of increasingly complex predictive models and how to select the best model.