QUESTION 1

1. Which is true about designing A/B tests to extract maximum meaning?

   		A and B should have identical content except for the hypothesized elements
   		A and B should have different content except for the hypothesized elements
   		A should always be the control
   		A and B should have two levels each

10 points

QUESTION 2

1. A/B tests are

   		more similar to field experiments than lab experiments
   		more similar to lab experiments than field experiments
   		never field experiments or lab experiments
   		not truly experiments

10 points

QUESTION 3

1. Which of the following is NOT an A/B Testing tool?

   		AB Tasty
   		Google Experiments
   		Qubit
   		AB Lab

10 points

QUESTION 4

1. Which of the follow is NOT a type of A/B Test?

   		A/B/N Test
   		Optimize Test
   		Split Test
   		Bandit Test

10 points

QUESTION 5

1. Which is true of a bandit test?

   		It is an A/B Test but with an extra exploitation stage.
   		It shifts traffic in reaction to real-time performance.
   		It is an A/B Test with a hidden exploration stage.
   		It removes people from the exploitation stage.

10 points

QUESTION 6

1. Which A/B testing stage typically uses a larger portion of the potential audience?

   		exploration stage
   		Bandit stage
   		exploitation stage
   		experimental stage

10 points

QUESTION 7

1. What is the problem of "local maxima"?

   		A/B Tests fail to maximize the exploitation stage
   		A/B Tests fail to attract local participants
   		A/B Tests fail to test conditions that may have better outcomes
   		A/B Tests fail to test conditions that will optimize the company's local concerns

10 points

QUESTION 8

1. Which statement is false?

   		A/B Tests = Split Tests
   		A/B Tests are often run as part of a live marketing effort
   		A/B Tests are often automated
   		A/B Tests = real marketing firms' lab experiments

10 points

QUESTION 9

1. What is true?

   		Protect your A/B test from too much input from other departments in the company
   		A/B test for causality after getting non-significant regression results from non-experimental secondary data
   		A/B Testing is not a time to try crazy ideas
   		The value gained from A/B testing usually outweighs potentially frustrating customers