#### Statistics 1: Introduction to ANOVA, Regression, and Logistic Regression

• Introduction to Statistics
• Examining data distributions
• Obtaining and interpreting sample statistics using the UNIVARIATE and MEANS procedures
• Render graphically in the UNIVARIATE and SGPLOT procedures
• Constructing confidence intervals
• Performing simple tests of hypothesis
• Tests and Analysis of Variance
• Tests of differences between two group means using PROC TTEST
• One-way ANOVA with the GLM procedure
• Multiple comparisons tests in PROC GLM
• Two-way ANOVA with and without interactions
• Linear Regression
• Working with correlations
• fitting a simple linear regression model
• Understanding the concepts of multiple regression
• Working with multiple models
• Interpreting models
• Linear Regression Diagnostics
• Examining residuals
• Investigating influential observations
• Assessing collinearity
• Categorical Data Analysis
• Producing frequency tables
• Examining tests for general and linear association
• Understanding logistic regression
• Fitting univariate and multivariate logistic regression models
Statisticians, researchers, and business analysts who use SAS programming to generate analyses
• Should have completed the equivalent of an undergraduate course in statistics
• Should be able to execute SAS programs and create SAS data sets
Learn to
• Understand describe data using graphical techniques
• Use Analysis of Varience (ANOVA)
• perform linear regression and assess the assumptions
• use regression model selection techniques to aid in the choice of predictor variables in multiple regression
• use diagnostic statistics to assess statistical assumptions and identify potential outliers in multiple regression
• use chi-square statistics to detect associations among categorical variables
• fit a multiple logistic regression model.
Delivery Method : Classroom Training
Duration : 21 hours
Level : Fundamental
Languages : English

#### Predictive Modeling Using Logistic Regression

Discover Knowledge on Technology This course helps participants to get a deep understanding of how logistics regression is used for predictive analytics.
• Introduction to Predictive Modeling
• Analytical challenges
• Fitting the Model
• Parameter estimation
• Input Data Preparation
• Missing values
• Categorical inputs
• Variable clustering
• Variable screening
• Subset selection
• Classifier Performance
• ROC curves and Lift charts
• K-S statistic
• c statistic
• Evaluating a series of models
Modelers, analysts and statisticians who need to build predictive models
• Must have completed statistics course on regression
• Experience in executing SAS programs and creating SAS data sets
• Experience building statistical models using SAS software
Learn how to
• Use logistic regression to model as a function of known inputs
• Create visualizations
• Handle missing data values
• Tackle multicollinearity
• Assess model performance and compare models.
Delivery Method : Classroom Training
Duration : 14 hours
Level : Intermediate
Languages : English