Clarification on sample question: SAS Statistical Business Analysis Using SAS 9: Regression and Mode

[Siuli]

Hi,

For the course "SAS Statistical Business Analysis Using SAS 9: Regression and Modeling Exam" I have below clarifications on the sample questions provided by SAS:

1. Question 1: As the probability is less than the default significance level and as the analysts is examining whether assets in portfolio A are more risky than those of portfolio B, the alternate hypothesis as per my understanding was A>B and hence my answer was option A (asset in A is more risky than asset in B). But the correct answer given was option C (the portfolios differs significantly with respect to risk). Kindly explain what was wrong with my answer

2. Question 2: For pairwise comparison to control EER the correct answer given was option B. When I have gone through the E training it was mentioned for Tukey method that it is a popular multiple comparison test that controls the EER. However it was also mentioned for Dunnett's method that "it controls the EER to be no greater than α when all treatments are compared to the control group, it accounts for the correlation that exists between the comparisons, and you can conduct one-sided tests of hypothesis against the control group". Given that both Tukey and Dunnett's method control EER and either one could be the correct option. Please can someone explain why does option B for Tukey method was provided in the answer

3. Question 10: For the ROC curve please explain why the correct answer was option B

[ballardw]

---

@Siuli wrote:

Hi,

For the course "SAS Statistical Business Analysis Using SAS 9: Regression and Modeling Exam" I have below clarifications on the sample questions provided by SAS:

1. Question 1: As the probability is less than the default significance level and as the analysts is examining whether assets in portfolio A are more risky than those of portfolio B, the alternate hypothesis as per my understanding was A>B and hence my answer was option A (asset in A is more risky than asset in B). But the correct answer given was option C (the portfolios differs significantly with respect to risk). Kindly explain what was wrong with my answer

2. Question 2: For pairwise comparison to control EER the correct answer given was option B. When I have gone through the E training it was mentioned for Tukey method that it is a popular multiple comparison test that controls the EER. However it was also mentioned for Dunnett's method that "it controls the EER to be no greater than α when all treatments are compared to the control group, it accounts for the correlation that exists between the comparisons, and you can conduct one-sided tests of hypothesis against the control group". Given that both Tukey and Dunnett's method control EER and either one could be the correct option. Please can someone explain why does option B for Tukey method was provided in the answer

3. Question 10: For the ROC curve please explain why the correct answer was option B

---

Show the results that you get from the analysis. Not all of us would have the same datasets or output having taken the classes years ago. So we need to see the actual results that the decision is to be made from. If possible, indicate the actual values you were considering in selecting your answer as "probability" often appears in more than one place in some procedure output.

[Siuli]

Hi,

Please find the attached document with sample questions and refer to the question number mentioned in my previous email. This is the sample questions I have got from SAS website.

Thanks,

Siuli