Faysal AzizSAS Enterprise Guide: Query, Analysis and Reporting
A practical workflow for experienced SAS users
Why this course
An intensive two-day course for participants who already use SAS. Organise a workflow-based project in Enterprise Guide, prepare and query data, explore selected statistical/model tasks and produce a reviewed report.
Use one prepared analysis scenario rather than every chart and modelling method. Enterprise Guide provides a client/workflow interface; available tasks, procedures and advanced models depend on installed and licensed SAS components.
Learning outcomes
- Access and organise data within an Enterprise Guide project.
- Build selected queries, calculated variables, subqueries and parameterised filters.
- Produce suitable summaries and graphics and inspect generated SAS code.
- Compare selected statistical/predictive methods and validation needs.
- Present an analysis with data assumptions, limitations and reproducible project steps.
Prerequisites
- Ability to code in SAS, integrate data and perform introductory analysis.
- Familiarity with SAS data types, files and analytical workflows.
- Access to the arranged Enterprise Guide client and compatible licensed SAS environment.
2 modules
01Day 1 — Project, Data and Exploratory Analysis1 topics
Environment and Data
- UI
- Workspace
- Data Source
- Descriptive analyses
- Predictive analyses
Data
- Types
- Psychographic data
- Category comparison
- Sources
Use public or synthetic teaching data, including any illustrative customer/psychographic fields. Confirm purpose and permissions before using personal data.
Query and Reporting Workflow
- Select, sort, format and calculate variables; inspect generated SAS functions/code.
- Use a subquery and a prompt/parameter to filter a prepared dataset.
- Create selected suitable graphics and report outputs; compare chart purpose rather than generate every source-listed chart.
Exploratory Case Work
- Project initiation
- Exploratory analyses
- Segmentation and profile analyses
- Correlation analyses
Distinguish association, segmentation and causal conclusions; inspect data quality and assumptions.
02Day 2 — Models, Validation and Assessment1 topics
Statistical and Model Comparisons
- Frequency distributions
- Cluster
- Decision Tree
- Linear regression
- Logistic regression
- Neural networks
Practise one selected regression or clustering task. Decision-tree and neural-network examples are prepared demonstrations only where the required components and licences are available.
Modelling Process
- Modeling Process
- Definitions
- Development of the model
- Implementation
Separate training, validation and final evaluation where appropriate; avoid fitting learned transformations on held-out data.
Illustrative Business-model Contexts
- Prospect models
- Customer models
- Risk models
Treat prospect, customer and risk models as educational scenarios, not validated credit, underwriting or marketing decisions.
Practical Review
- Assessment
- Evaluation
Complete a small workflow-based assessment and explain the model/report assumptions, limitations and further validation required.
A programme built around your team.
Share your training goals and requirements.