SASInstitute Statistical Business Analyst A00-240 Questions & Answers

• Question 1:

  After performing an ANOVA test, an analyst has determined that a significant effect exists due to income. The analyst wants to compare each Income to all others and wants to control for experimentwise error. Which GLM procedure statement would provide the most appropriate output?

  A. lsmeans Income / pdiff=control adjust=dunnett;

  B. lsmeans Income / pdiff=control adjust=t;

  C. lsmeans Income / pdiff=all adjust=tukey;

  D. lsmeans Income / pdiff=all adjust=t;

  Correct Answer: A

  Reference: https://rpubs.com/JsoLab/Stat01_L02

• Question 2:

  This question will ask you to provide a missing option.

  A business analyst is investigating the differences in sales figures across 8 sales regions. The analyst is interested in viewing the regression equation parameter estimates for each of the design variables.

  Which option completes the program to produce the regression equation parameter estimates?

  

  A. Solve

  B. Estimate

  C. Solution

  D. Est

  Correct Answer: C

  Reference: https://documentation.sas.com/?docsetId=statuganddocsetTarget=statug_ods_examples06.htmanddocsetVersion=14.3andlocale=en

• Question 3:

  This question will ask you to provide a segment of missing code.

  The following code is used to create missing value indicator variables for input variables, fred1 to fred7.

  

  Which segment of code would complete the task?

  A. Option A

  B. Option B

  C. Option C

  D. Option D

  Correct Answer: C

• Question 4:

  This question will ask you to provide a missing option. Given the following SAS program:

  

  What option must be added to the program to obtain a data set containing Spearman statistics?

  A. OUTCORR=estimates

  B. OUTS=estimates

  C. OUT=estimates

  D. OUTPUT=estimates

  Correct Answer: D

• Question 5:

  What does the Pearson product moment correlation coefficient measure?

  A. nonlinear and nonmonotonic association between two variables

  B. linear and monotonic association between two variables

  C. linear and nonmonotonic association between two variables

  D. nonlinear and monotonic association between two variables

  Correct Answer: B

  Reference: http://d-scholarship.pitt.edu/8056/1/Chokns_etd2010.pdf

• Question 6:

  An analyst knows that the categorical predictor, zip_code, is an important predictor of a binary target. However, zip_code has too many levels to be a feasible predictor in a model. The analyst uses PROC CLUSTER to implement Greenacre's method to reduce the number of categorical levels.

  What is the correct application of Greenacre's method in this situation?

  A. Clustering the levels using the target proportion for each zip_code as input.

  B. Clustering the levels using the zip_code values as input.

  C. Clustering the levels using the number of cases in each zip_code as input.

  D. Clustering the levels using dummy coded zip_code levels as inputs.

  Correct Answer: A

  Reference: https://support.sas.com/resources/papers/proceedings/proceedings/sugi31/079-31.pdf

• Question 7:

  Refer to the confusion matrix:

  

  Calculate the accuracy and error rate (0 - negative outcome, 1 - positive outcome)

  A. Accuracy = 58/102, Error Rate = 23/48

  B. Accuracy = 83/102, Error Rate = 67/102

  C. Accuracy = 25/150, Error Rate = 44/150

  D. Accuracy = 83/150, Error Rate = 67/150

  Correct Answer: A

• Question 8:

  Which statistic is based on the maximum vertical distance between the primary event EDF and the secondary event EDF?

  A. KS

  B. SBC

  C. Max EDF

  D. Brier Score

  Correct Answer: A

  Reference: https://support.sas.com/documentation/onlinedoc/ets/132/severity.pdf

• Question 9:

  Refer to the exhibit:

  

  On the Gains Chart, what is the correct interpretation of the horizontal reference line?

  A. the proportion of cases that cannot be classified

  B. the probability of a false negative

  C. the probability of a false positive

  D. the prior event rate

  Correct Answer: B

• Question 10:

  What is a benefit to performing data cleansing (imputation, transformations, etc.) on data after partitioning the data for honest assessment as opposed to performing the data cleansing prior to partitioning the data?

  A. It makes inference on the model possible.

  B. It is computationally easier and requires less time.

  C. It omits the training (and test) data sets from the benefits of the cleansing methods.

  D. It allows for the determination of the effectiveness of the cleansing method.

  Correct Answer: D