1) Simpson's paradox describes the situation where a trend that appears when using summary statistics implies theoppositewhen the data is considered as a whole. In the lectures it was stated that this isn't so much a 'paradox' as it is a violation of an underlying assumption, which means the implication is false. What is the underlying assumption that gets violated?

Group of answer choices

1) You have the same number of data points

2) The data can be explained with a linear model

3) All else is equal when using the summary statistics

2) Data can be missing for a variety of reasons. Why is it important to understandwhythe data is missing?

Group of answer choices

1) You can never know why, this is a trick question.

2) It informs whether it is possible to 'fill in' the missing data and what approach you might use to do that.

3) It is important for the explanation of how the data was used, but not for processing the data itself.

3) We briefly introduced 3 types of missing data:

MCAR: Missing Completely at Random

MAR: Missing at Random

MNAR: Missing Not at Random

Based on the discussion from our Lecture, what might a better name for "Missing at Random" be (even if the resulting acronym is atrocious)?

Group of answer choices

1) Missing but with an underlying model that would explain it. (MBWAUMTWEI)

2) Forgotten Data (FD)

3) Missing by Accident. (MBA)