SAS A00-255 Certification Exam Syllabus

A00-255 Syllabus, A00-255 PDF Download, SAS A00-255 Dumps, SAS Predictive Modeler Dumps PDF Download, SAS Predictive Modeling Using SAS Enterprise Miner 14  PDF DownloadThis page is a one-stop solution for any information you may require for SAS Predictive Modeling Using SAS Enterprise Miner 14 (A00-255) Certification exam. The SAS A00-255 Exam Summary, Syllabus Topics and Sample Questions provide the base for the actual SAS Certified Predictive Modeler Using SAS Enterprise Miner 14 exam preparation, we have designed these resources to help you get ready to take your dream exam.

The SAS Predictive Modeling Using SAS Enterprise Miner 14 credential is globally recognized for validating SAS Predictive Modeler knowledge. With the SAS Certified Predictive Modeler Using SAS Enterprise Miner 14 Certification credential, you stand out in a crowd and prove that you have the SAS Predictive Modeler knowledge to make a difference within your organization. The SAS Predictive Modeling Using SAS Enterprise Miner 14 Certification (A00-255) exam will test the candidate's knowledge on following areas.

SAS A00-255 Exam Summary:

Exam Name SAS Predictive Modeling Using SAS Enterprise Miner 14
Exam Code A00-255
Exam Duration 165 minutes
Exam Questions 55-60
Passing Score 725/1000
Exam Price $250 (USD)
Training Applied Analytics Using SAS Enterprise Miner
Books Predictive Modeling With SAS® Enterprise Miner™: Practical Solutions for Business Applications
Exam Registration Pearson VUE
Sample Questions SAS Predictive Modeler Certification Sample Question
Practice Exam SAS Predictive Modeler Certification Practice Exam

SAS A00-255 Exam Topics:

Objective Details

Data Sources - 20-25%

Create data sources from SAS tables in Enterprise Miner - Use the Basic Metadata Advisor
- Use the Advanced Metadata Advisor
- Customize the Advanced Metadata Advisor
- Set Role and Level meta data for data source variables
- Set the Role of the table (raw, scoring, transactional, etc)
Explore and assess data sources - Create and interpret plots, including Histograms, Pie charts, Scatter plot, Time series, Box plot
- Identify distributions
- Find outlying observations
- Find number (or percent) of missing observations
- Find levels of nominal variables
- Explore associations between variables using plots by highlighting and selecting data
- Compare balanced and actual response rates when oversampling has been performed
- Explore data with the STAT EXPLORER node.
- Explore input variable sample statistics
- Browse data set observations (cases)
Modify source data - Replace zero values with missing indicators using the REPLACEMENT node
- Use the TRANFORMATION node to be able to correct problems with input data sources, such as variable distribution or outliers.
- Use the IMPUTE node to impute missing values and create missing value indicators
- Reduce the levels of a categorical variable
- Use the FILTER node to remove cases
Prepare data to be submitted to a predictive model - Select a portion of a data set using the SAMPLE node
- Partition data with the PARTITION Node
- Use the VARIABLE SELECTION node to identify important variables to be included in a predictive model.
- Use the PARTIAL LEAST SQUARES node to identify important variables to be included in a predictive model.
- Use a DECISION TREE or REGRESSION nodes to identify important variables to be included in a predictive model.

Building Predictive Models - 35-40%

Describe key predictive modeling terms and concepts - Data partitioning: training, validation, test data sets
- Observations (cases), independent (input) variables, dependent (target) variables
- Measurement scales: Interval, ordinal, nominal (categorical), binary variables
- Prediction types: decisions, rankings, estimates
- Dimensionality, redundancy, irrelevancy
- Decision trees, neural networks, regression models
- Model optimization, overfitting, underfitting, model selection
- Describe ensemble models
Build predictive models using decision trees - Explain how decision trees identify split points
- Build decision trees in interactive mode
- Change splitting rules
- Explain how missing values can be handled by decision trees
- Assess probability using a decision tree
- Prune decision trees
- Adjust properties of the DECISION TREE node, including: subtree method, Number of Branches, Leaf Size, Significance Level, Surrogate Rules, Bonferroni Adjustment
- Interpret results of the decision tree node, including: trees, leaf statistics, treemaps, score rankings overlay, fit statistics, output, variable importance, subtree assessment plots
- Explore model output (exported) data sets
Build predictive models using regression - Explain the relationship between target variable and regression technique
- Explain linear regression
- Explain logistic regression (Logit link function, maximum likelihood)
- Explain the impact of missing values on regression models
- Select inputs for regression models using forward, backward, stepwise selection techniques
- Adjust thresholds for including variables in a model
- Interpret a logistic regression model using log odds
- Interpret the results of a REGRESSION node (Output, Fit Statistics, Score Ranking Overlay charts)
- Use fit statistics and iteration plots to select the optimum regression model for different decision types
- Add polynomial regression terms to regression models.
- Determine when to add polynomial terms to linear regression models.
Build predictive models using neural networks - Theory of neural networks (Hidden units, Tanh function, bias vs intercept, variable standardization)
- Build a neural network model
- Use regression models to select inputs for a neural network
- Explain how neural networks optimize their model (stopped training)
- Recognize overfit neural network models.
- Interpret the results of a NEURAL NETWORK node, including: Output, Fit Statistics, Iteration Plots, and Score Rankings Overlay charts

Predictive Model Assessment and Implementation - 25-30%

Use the correct fit statistic for different prediction types - Misclassification
- Average Square Error
- Profit/Loss
- Other standard model fit statistics
Use decision processing to adjust for oversampling (separate sampling) - Explain reasons for oversampling data
- Adjust prior probabilities
Use profit/loss information to assess model performance - Build a profit/loss matrix
- Add a profit/loss matrix to a predictive model
- Determine an appropriate value to use for expected profit/loss for primary outcome
- Optimize models based on expected profit/loss
Compare models with the MODEL COMPARISON node - Model assessment statistics
- ROC Chart
- Score Rankings Chart, including (cumulative) % response chart, (cumulative) Lift chart, gains chart.
- Total expected profit
- Effect of oversampling
Score data sets within Enterprise Miner - Configure a data set to be scored in Enterprise Miner
- Use the SCORE node to score new data
- Save scored data to an external location with the SAVE DATA node
- Export SAS score code

Pattern Analysis - 10-15%

Identify clusters of similar data with the CLUSTER and SEGMENT PROFILE nodes - Select variables to use to define the clusters
- Standardize variable scales
- Explore clusters with results output and plots
- Compare distribution of variables within clusters
Perform association and sequence analysis (market basket analysis) - Explain association concepts (Support, confidence, expected confidence, lift, difference between association and sequence rules)
- Create a data set for association analysis
- Interpret the results and graphs of the ASSOCIATION node.

The SAS has created this credential to assess the knowledge and understanding of a candidate in the area as above via the certification exam. The SAS Predictive Modeler (A00-255) Certification exam contains a high value in the market being the brand value of the SAS attached with it. It is highly recommended to a candidate to do a thorough study and also get a hand full of the practice to clear SAS Predictive Modeling Using SAS Enterprise Miner 14 exam without any hiccups.

Rating: 4.8 / 5 (92 votes)