К содержимому
learnspaceYOUR NEXT CHAPTER
ПРОСТРАНСТВО ОБУЧЕНИЯ
ГлавнаяКаталог курсовМоё обучениеCoursera

Знания без границ

Учитесь у лучших университетов и компаний мира.

Открыть Coursera
Интеграция
Пространство университета
Моё пространствоСтраница курса
↵
ЯЛичный кабинетСтудент
© 2026 LearnSpaceКаждый день — возможность узнать больше.Помощь
Predictive Modeling with Logistic Regression using SAS · LearnSpace
Назад в каталог
courseraАнализ данных

Predictive Modeling with Logistic Regression using SAS

Курс от SAS
Средний≈ 16.7 чАнглийский
О курсеНавыкиПрограммаПреподаватели

О курсе

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.

Навыки, которые вы освоите

SAS (Software)Logistic RegressionPredictive ModelingModel EvaluationStatistical SoftwareFeature EngineeringStatistical AnalysisPredictive AnalyticsBusiness AnalyticsStatistical MethodsModel TrainingStatistical ModelingData PreprocessingSampling (Statistics)Regression AnalysisSupervised Learning

Программа курса

6 модулей · 165 учебных материалов

01Course Overview & Understanding Predictive Modeling29 материалов

Course Overview

Meet the InstructorВидеоWhat You Learn in This CourseЧтениеLearner PrerequisitesЧтениеBuilding your Foundation for Predictive ModelingDIALOGUE

Logistics

Учитесь у экспертов

Marc Huber

Sr Analytical Training Consultant

Predictive Modeling with Logistic Regression using SAS
В каталоге вашей программы

Инвестируйте в себя

Новые знания — в удобное для вас время.

Начать на Coursera

Обучение откроется на Coursera
в новой вкладке

Обучение на Coursera

≈ 16.7 ч

6 модулей

Язык: Английский

Субтитры: Арабский, Французский, Украинский, Китайский (Китай), Греческий, Итальянский, Бразильский португальский, Нидерландский, Корейский, Немецкий, Пушту, Русский, Тайский, Индонезийский, Шведский, Турецкий, Испанский, Дари, Хинди, Японский, Казахский, Венгерский, Польский

Часть программы вашего университета
Access SAS Software & Set up DataЧтение
About the Demos and Practices in this CourseЧтение
Frequently Asked QuestionsЧтение

Overview

OverviewВидео

Predictive Modeling Fundamentals

IntroductionВидеоGoals of Predictive ModelingВидеоTerms for Elements in Predictive ModelingВидеоBasic Steps of Predictive ModelingВидеоApplications of Predictive ModelingВидеоDemonstration Scenario: Target Marketing for a BankВидеоPractice: Exploring the Bank Data for the Target Marketing ProjectЗаданиеDemo: Examining the Code for Generating Descriptive Statistics and Frequency TablesВидеоPractice: Exploring the Veterans' Organization Data Used in the PracticesЗадание

Predictive Modeling Challenges

IntroductionВидеоData ChallengesВидеоAnalytical ChallengesВидеоSeparate SamplingВидеоAvoiding the Optimism Bias: Honest AssessmentВидеоSplitting the Data for Model Training and AssessmentВидеоKnowledge Check: Model Training & SamplingЗаданиеDemo: Splitting the DataВидеоKnowledge Check: Splitting the DataЗаданиеPractice: Splitting the DataЗадание

Review

SummaryЧтениеModule-End Graded AssessmentЗадание
02Fitting the Model23 материалов

Overview

OverviewВидео

Understanding the Logistic Regression Model

IntroductionВидеоUnderstanding the Logistic Regression ModelВидеоConstraining the Posterior Probability Using the Logit TransformationВидеоUnderstanding the Fitted SurfaceВидеоInterpreting the Model by Calculating the Odds RatioВидеоQuestion 2.01ЗаданиеUnderstanding Logistic DiscriminationВидеоEstimating Unknown Parameters Using Maximum Likelihood EstimationВидеоInterpreting Concordant, Discordant, and Tied PairsВидеоUsing PROC LOGISTIC to Fit Logistic Regression ModelsВидеоDemo: Fitting a Basic Logistic Regression Model, Part 1ВидеоDemo: Fitting a Basic Logistic Regression Model, Part 2ВидеоQuestion 2.02ЗаданиеScoring New CasesВидеоDemo: Scoring New CasesВидео

Correcting for Oversampling

IntroductionВидеоUnderstanding the Effect of OversamplingВидеоUnderstanding the OffsetВидеоDemo: Correcting for OversamplingВидеоPractice: Fitting a Logistic Regression ModelЗадание

Review

SummaryЧтениеFitting the Model ReviewЗадание
03Preparing the Input Variables, Part 135 материалов

Overview

OverviewВидео

Handling Missing Values

IntroductionВидеоReasons for Missing DataВидеоComplete Case AnalysisВидеоMethods for Imputing Missing ValuesВидеоMissing Value Imputation with Missing Value Indicator VariablesВидеоQuestion 3.01ЗаданиеDemo: Imputing Missing ValuesВидеоCluster ImputationВидеоPractice: Imputing Missing ValuesЗадание

Working with Categorical Inputs

IntroductionВидеоQuestion 3.02ЗаданиеProblems Caused by Categorical InputsВидеоSolutions to Problems Caused by Categorical InputsВидеоLinking to Other Data SetsВидеоCollapsing Categories by ThresholdingВидео

Reducing Redundancy by Clustering Variables

IntroductionВидеоProblem of RedundancyВидеоVariable Clustering MethodВидеоUnderstanding Principal ComponentsВидеоDivisive ClusteringВидеоPROC VARCLUS SyntaxВидеоSelecting a Representative Variable from Each Cluster
04Preparing the Input Variables, Part 236 материалов

Performing Variable Screening

IntroductionВидеоDetecting Nonlinear RelationshipsВидеоDemo: Performing Variable Screening, Part 1ВидеоDemo: Performing Variable Screening, Part 2ВидеоQuestion 3.06ЗаданиеPractice: Performing Variable ScreeningЗаданиеUnivariate Binning and SmoothingВидеоDemo: Creating Empirical Logit PlotsВидеоPractice: Creating Empirical Logit PlotsЗаданиеRemedies for Nonlinear RelationshipsВидеоQuestion 3.07ЗаданиеDemo: Accommodating a Nonlinear Relationship, Part 1ВидеоDemo: Accommodating a Nonlinear Relationship, Part 2ВидеоQuestion 3.08Задание

Selecting Variables Sequentially

IntroductionВидеоSpecifying a Subset Selection Method in PROC LOGISTICВидеоBest-Subsets SelectionВидеоStepwise SelectionВидеоBackward EliminationВидеоScalability of the Subset Selection Methods in PROC LOGISTICВидео

Review

Summary of Preparing the Input Variables, Parts 1 and 2ЧтениеPreparing the Input Variables ReviewЗадание
05Measuring Model Performance40 материалов

Overview

OverviewВидео

Honest Assessment of the Model

IntroductionВидеоFit versus ComplexityВидеоAssessing Models when Target Event Data Is RareВидеоQuestion 4.01ЗаданиеDemo: Preparing the Validation DataВидео

Common Metrics for Model Performance

IntroductionВидеоUnderstanding the Confusion MatrixВидеоMeasuring Performance across Cutoffs by Using the ROC CurveВидеоChoosing Depth by Using the Gains ChartВидеоEffects of Oversampled Data on Performance MeasuresВидеоAdjusting a Confusion Matrix for OversamplingВидеоQuestion 4.02ЗаданиеDemo: Measuring Model Performance Based on Commonly-Used MetricsВидеоQuestion 4.03ЗаданиеPractice: Assessing Model PerformanceЗадание

Profit-Based Metrics

IntroductionВидеоUnderstanding the Effect of Cutoffs on Confusion MatricesВидеоUnderstanding the Profit MatrixВидеоChoosing the Optimal Cutoff by Using the Profit MatrixВидеоUsing the Central CutoffВидеоUsing Profit to Assess FitВидео

Kolmogorov-Smirnov Statistic

IntroductionВидеоPlotting Class SeparationВидеоAssessing Overall Predictive PowerВидеоDemo: Using the K-S Statistic to Measure Model PerformanceВидеоQuestion 4.06Задание

Model Selection Plots

IntroductionВидеоComparing ROC Curves of Several Models"ВидеоDemo: Comparing ROC Curves to Measure Model PerformanceВидеоUsing Macros to Compare Many ModelsВидеоDemo: Comparing and Evaluating Many Models, Part 1ВидеоDemo: Comparing and Evaluating Many Models, Part 2Видео

Review

SummaryЧтениеMeasuring Model Performance ReviewЗадание
06SAS Certification Practice Exam - Statistical Business Analysis Using SAS®9: Regression and Modeling2 материалов

Certification Practice Exam

About the Certification ExamЧтениеAccess the Practice ExamВнешний инструмент
Collapsing Categories by Using Greenacre's MethodВидео
Question 3.03Задание
Demo: Collapsing the Levels of a Nominal Input, Part 1Видео
Question 3.04Задание
Demo: Collapsing the Levels of a Nominal Input, Part 2Видео
Practice: Collapsing the Levels of a Nominal InputЗадание
Replacing Categorical Levels by Using Smoothed Weight-of-Evidence CodingВидео
Demo: Computing the Smoothed Weight of EvidenceВидео
Practice: Computing the Smoothed Weight of EvidenceЗадание
Видео
Demo: Reducing Redundancy by Clustering VariablesВидео
Question 3.05Задание
Practice: Reducing Redundancy by Clustering VariablesЗадание
Question 3.09Задание
Detecting InteractionsВидео
BIC-based Significance LevelВидео
Demo: Detecting InteractionsВидео
Practice: Using Forward Selection to Detect InteractionsЗадание
Demo: Using Backward Elimination to Subset the VariablesВидео
Question 3.10Задание
Practice: Using Backward Elimination to Subset the VariablesЗадание
Demo: Displaying Odds Ratios for Variables Involved in InteractionsВидео
Demo: Creating an Interaction PlotВидео
Demo: Using the Best-Subsets Selection MethodВидео
Demo: Using Fit Statistics to Select a ModelВидео
Question 3.11Задание
Practice: Using Fit Statistics to Select a ModelЗадание
Question 4.04Задание
Calculating Sampling WeightsВидео
Demo: Using a Profit Matrix to Measure Model PerformanceВидео
Question 4.05Задание
Question 4.07Задание