Predictive Modeling with Logistic Regression using SAS

本课程是 SAS Statistical Business Analyst 专业证书的一部分

位教师：Marc Huber

访问权限由 Coursera Learning Team 提供

8,222 人已注册

7个模块

深入了解一个主题并学习基础知识。

63 条评论

中级等级

需要一些相关经验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

7个模块

深入了解一个主题并学习基础知识。

63 条评论

中级等级

需要一些相关经验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将获得的技能

Data Preprocessing
Feature Engineering
Predictive Modeling
Statistical Analysis
Statistical Machine Learning
Classification And Regression Tree (CART)
Model Evaluation
Big Data
SAS (Software)
Regression Analysis
Logistic Regression
技能部分已折叠。显示 8 项技能，共 11 项。

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

40 项作业

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

积累 Data Analysis 领域的专业知识

本课程是 SAS Statistical Business Analyst 专业证书专项课程的一部分

在注册此课程时，您还会同时注册此专业证书。

向行业专家学习新概念
获得对主题或工具的基础理解
通过实践项目培养工作相关技能
通过 SAS 获得可共享的职业证书

该课程共有7个模块

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.

涵盖的内容

1个视频7篇阅读材料

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.

涵盖的内容

15个视频1篇阅读材料6个作业

15个视频总计34分钟

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

1篇阅读材料总计10分钟

Summary 10分钟

6个作业总计75分钟

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

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.

涵盖的内容

18个视频1篇阅读材料4个作业

18个视频总计54分钟

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

1篇阅读材料总计10分钟

Summary 10分钟

4个作业总计60分钟

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

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.

涵盖的内容

26个视频9个作业

26个视频总计76分钟

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

9个作业总计105分钟

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

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

涵盖的内容

23个视频1篇阅读材料12个作业

23个视频总计92分钟

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

1篇阅读材料总计10分钟

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

12个作业总计160分钟

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

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.