SAS Institute Of Management Studies - Statistics with SAS 

Welcome and Meet the Instructor

Demo: Exploring Ames Housing Data

Learner Prerequisites

Choosing and Setting Up SAS Software for this Course

Follow These Instructions to Set Up Data for This Course (REQUIRED)

Completing Demos and Practices

Using Forums and Getting Help

Overview

Statistical Modeling: Types of Variables

Overview of Models

Explanatory versus Predictive Modeling

Population Parameters and Sample Statistics

Normal (Gaussian) Distribution

Standard Error of the Mean

Confidence Intervals

Statistical Hypothesis Test

p-Value: Effect Size and Sample Size Influence

Scenario

Performing a t Test

Demo: Performing a One-Sample t Test Using PROC TTEST

Scenario

Assumptions for the Two-Sample t Test

Testing for Equal and Unequal Variances

Demo: Performing a Two-Sample t Test Using PROC TTEST

Parameters and Statistics

Normal Distribution

Question 1.01

Question 1.02

Question 1.03

Question 1.04

Question 1.05

Practice - Using PROC TTEST to Perform a One-Sample t Test

Question 1.06

Practice - Using PROC TTEST to Compare Groups

Introduction and Review of Concepts

Overview

Scenario

Identifying Associations in ANOVA with Box Plots

Demo: Exploring Associations Using PROC SGPLOT

Identifying Associations in Linear Regression with Scatter Plots

Demo: Exploring Associations Using PROC SGSCATTER

Scenario

The ANOVA Hypothesis

Partitioning Variability in ANOVA

Coefficient of Determination

F Statistic and Critical Values

The ANOVA Model

Demo: Performing a One-Way ANOVA Using PROC GLM

Scenario

Multiple Comparison Methods

Tukey's and Dunnett's Multiple Comparison Methods

Diffograms and Control Plots

Demo: Performing a Post Hoc Pairwise Comparison Using PROC GLM

Scenario

Using Correlation to Measure Relationships between Continuous Variables

Hypothesis Testing for a Correlation

Avoiding Common Errors When Interpreting Correlations

Demo: Producing Correlation Statistics and Scatter Plots Using PROC CORR

Scenario

The Simple Linear Regression Model

How SAS Performs Simple Linear Regression

Comparing the Regression Model to a Baseline Model

Hypothesis Testing and Assumptions for Linear Regression

Demo: Performing Simple Linear Regression Using PROC REG

What Does a CLASS Statement Do?

Correlation Analysis and Model Building

Question 2.01

Question 2.02

Question 2.03

Question 2.04

Practice - Performing a One-Way ANOVA

Question 2.05

Question 2.06

Practice - Using PROC GLM to Perform Post Hoc Parwise Comparisons

Question 2.07

Question 2.08

Practice - Describing the Relationship between Continuous Variables

Question 2.09

Practice - Using PROC REG to Fit a Simple Linear Regression Model

ANOVA and Regression

Overview

Scenario

Applying the Two-Way ANOVA Model

Demo: Performing a Two-Way ANOVA Using PROC GLM

Interactions

Demo: Performing a Two-Way ANOVA With an Interaction Using PROC GLM

Demo: Performing Post-Processing Analysis Using PROC PLM

Scenario

The Multiple Linear Regression Model

Hypothesis Testing for Multiple Regression

Multiple Linear Regression versus Simple Linear Regression

Adjusted R-Square

Demo: Fitting a Multiple Linear Regression Model Using PROC REG

The STORE Statement

Question 3.01

Practice - Performing a Two-Way ANOVA Using PROC GLM

Question 3.02

Practice - Performing Multiple Regression Using PROC REG

More Complex Linear Models

Overview

Scenario

Approaches to Selecting Models

The All-Possible Regressions Approach to Model Building

The Stepwise Selection Approach to Model Building

Interpreting p-Values and Parameter Estimates

Demo: Performing Stepwise Regression Using PROC GLMSELECT

Scenario

Information Criteria

Adjusted R-Square and Mallows' Cp

Demo: Performing Model Selection Using PROC GLMSELECT

Activity - Optional Stepwise Selection Method Code

Information Criteria Penalty Components

All-Possible Selection

Question 4.01

Practice - Using PROC GLMSELECT to Perform Stepwise Selection

Practice - Using PROC GLMSELECT to Perform Other Model Selection Techniques

Model Building and Effect Selection

Overview

Scenario

Assumptions for Regression

Verifying Assumptions Using Residual Plots

Demo: Examining Residual Plots Using PROC REG

Scenario

Identifying Influential Observations

Checking for Outliers with STUDENT Residuals

Checking for Influential Observations

Detecting Influential Observations with DFBETAS

Demo: Looking for Influential Observations Using PROC GLMSELECT and PROC REG

Demo: Examining the Influential Observations Using PROC PRINT

Handling Influential Observations

Scenario

Exploring Collinearity

Visualizing Collinearity

Demo: Calculating Collinearity Diagnostics Using PROC REG

Using an Effective Modeling Cycle

Practice: Using PROC REG to Examine Residuals

Question 5.01

Practice: Using PROC REG to Generate Potential Outliers

Question 5.02

Question 5.03

Practice: Using PROC REG to Assess Collinearity

Model Post-Fitting for Inference

Overview

Scenario

Predictive Modeling Terminology

Model Complexity

Building a Predictive Model

Model Assessment and Selection

Demo: Building a Predictive Model Using PROC GLMSELECT

Scenario

Preparing for Scoring

Methods of Scoring

Demo: Scoring Data Using PROC PLM

Partitioning a Data Set Using PROC GLMSELECT

Question 6.01

Practice: Building a Predictive Model Using PROC GLMSELECT

Practice: Scoring Using the SCORE Statement in PROC GLMSELECT

Model Building for Scoring and Prediction

Overview

Scenario

Associations between Categorical Variables

Demo: Examining the Distribution of Categorical Variables Using PROC FREQ and PROC UNIVARIATE

Scenario

The Pearson Chi-Square Test

Odds Ratios

Demo: Performing a Pearson Chi-Square Test of Association Using PROC FREQ

Scenario

The Mantel-Haenszel Chi-Square Test

The Spearman Correlation Statistic

Demo: Detecting Ordinal Associations Using PROC FREQ

Scenario

Modeling a Binary Response

Demo: Fitting a Binary Logistic Regression Model Using PROC LOGISTIC

Interpreting the Odds Ratio

Comparing Pairs to Assess the Fit of a Logistic Regression Model

Scenario

Specifying a Parameterization Method

Demo: Fitting a Multiple Logistic Regression Model with Categorical Predictors Using PROC LOGISTIC

Scenario

Interactions between Variables

Demo: Fitting a Multiple Logistic Regression Model with Interactions Using PROC LOGISTIC

Demo: Fitting a Multiple Logistic Regression Model with All Odds Ratios Using PROC LOGISTIC

Demo: Generating Predictions Using PROC PLM

Question 7.01

Question 7.02

Practice: Using PROC FREQ to Examine Distributions

Question 7.03

Question 7.04

Question 7.05

Question 7.06

Practice: Using PROC FREQ to Perform Tests and Measures of Association

Question 7.07

Question 7.08

Practice: Using PROC LOGISTIC to Perform a Binary Logistic Regression Analysis

Question 7.09

Question 7.10

Practice: Using PROC LOGISTIC to Perform a Multiple Logistic Regression Analysis with Categorical Variables

Question 7.11

Question 7.12

Practice: Using PROC LOGISTIC to Perform Backward Elimination and PROC PLM to Generate Predictions

Categorical Data Analysis