SASInstitute SAS Predictive Modeling Using SAS Enterprise Miner 14 Sample Questions:

1. A multilayer perceptron neural network is using three interval inputs to model one interval target (outcome). The neural network has ten hidden units and one hidden layer. How many weights, including biases are being estimated?
You may use a calculator for this question. On the certification exam, an on-screen calculator is provided for you.
Select one:
Response:

A) 50
B) 51
C) 41
D) 40

2. What is the number of missing values for the TLSum variable in the sample generated by SAS Enterprise Miner?
Response:

A) 0
B) 20-39
C) 1-19
D) 40 or more

3. Perform these tasks in SAS Enterprise Miner:
- Use the Regression node to build another regression model with TARGET as the dependent variable and all other input variables as independent variables (main effects only).
- Configure the regression model to use Stepwise for Selection Model and Validation Error for Selection Criteri a. Do not change any other property for the regression model.
For the validation data, in what range does cumulative percent captured response at the 60th percentile lie?
Response:

A) 0-24.99
B) 50-74.99
C) 75 or more
D) 25-49.99

4. For the variable TLCnt24, apply a Max Normal transformation. What transformation was selected by SAS Enterprise Miner?
Response:

A) Exponential
B) Log
C) Square Root
D) Square

5. What percentage of observations in the test data has TARGET=1?
Response:

A) 16.8874
B) 16.5924
C) 83.3333
D) 16.6627

Solutions: