Data Cleaning – Quiz 4

Quiz Summary

0 of 3 Questions completed

Questions:

You have already completed the quiz before. Hence you can not start it again.

Quiz is loading…

You must sign in or sign up to start the quiz.

You must first complete the following:

Results

Quiz complete. Results are being recorded.

Results

0 of 3 Questions answered correctly

Your time:

You have reached 0 of 0 point(s), (0)

Question 1 of 3

1. Question

1. Suppose that you are estimating the average number of times that teachers are off-task in the dataset, but some teachers are missing classroom observation data. What is the best way to deal with this missing data?

Ignore it and calculate your estimate using data from non-missing cases
Correct Incorrect Correct answer

Impute the missing data by using outcomes from other teachers who look most similar to the teachers with missing data
Correct Incorrect Correct answer

Predict the missing data by training a random forest model on the non-missing data
Correct Incorrect Correct answer

Calculate and apply inverse probability weights to the non-missing observations
Correct Incorrect Correct answer

Calculate bounds on your estimate that captures the range of likely estimates under reasonable assumptions about the missing data
Correct Incorrect Correct answer

Depends on the data, context, and the judgment calls that you articulated in your pre-analysis plan
Correct Incorrect Correct answer

None of the above
Correct Incorrect Correct answer
Question 2 of 3

2. Question

Continuing from Quiz 3 (i.e. not reloading the Data Cleaning dataset, but still dropping the same duplicate observations as in Quiz 3), create a new classSize_wins variable, which is winsorized at the 5th & 95th percentiles. (Ignore missing values, i.e. if a value is missing in class_scan_1, then it should also be missing in classSize_wins).

2. Which of the following statements is true? (select all that apply)

The mean value of the original class size variable is greater than the mean value of the winsorized class size variable
Correct Incorrect Correct answer

The mean value of the original class size variable is less than the mean value of the winsorized class size variable
Correct Incorrect Correct answer

The mean value of the original class size variable is the same as the mean value of the winsorized class size variable
Correct Incorrect Correct answer

The median value of the original class size variable is greater than the mean value of the winsorized class size variable
Correct Incorrect Correct answer

The median value of the original class size variable is less than the mean value of the winsorized class size variable
Correct Incorrect Correct answer

The median value of the original class size variable is the same as the median value of the winsorized class size variable
Correct Incorrect Correct answer
Question 3 of 3

3. Question

3. What will happen if I run the command “assert class_scan_1 != .” on this dataset?

Stata will change all values in class_scan_1 to missing
Correct Incorrect Correct answer

Stata will impute all missing values in class_scan_1 to the average non-missing value for class_scan_1
Correct Incorrect Correct answer

Stata will return an error since the assertion is true
Correct Incorrect Correct answer

Stata will return an error since the assertion is false
Correct Incorrect Correct answer

Stata will not return an error since the assertion is true
Correct Incorrect Correct answer

Stata will not return an error since the assertion is false
Correct Incorrect Correct answer

None of the above
Correct Incorrect Correct answer

Data Cleaning – Quiz 4

Quiz Summary

Information

Results

Results

Categories

1. Question

2. Question

3. Question

Meeting the need for quantitative measurement in community-led development programs

Ensuring responsible AI adoption in African parliaments

Can AI strengthen foundational learning in African classrooms?

Governing AI: Takeaways from the 2026 AI for Good Global Summit

Good evidence as a starting point for more democratic technology

Relational strategies for working with parliaments in Africa

Benefits AI: Unlocking access to government social benefit programs

What does it take to be an AI-native organisation?

AI-driven support for bilingual education in Senegal

Where to test a model built for scaling

Related content

Quiz

Intro to Stata – Quiz 1

The Stata Interface (1) Quiz

Lesson 1

Quiz Summary

Information

Results

Results

Categories

1. Question

2. Question

3. Question

Meeting the need for quantitative measurement in community-led development programs

Ensuring responsible AI adoption in African parliaments

Can AI strengthen foundational learning in African classrooms?

Governing AI: Takeaways from the 2026 AI for Good Global Summit

Good evidence as a starting point for more democratic technology

Relational strategies for working with parliaments in Africa

Benefits AI: Unlocking access to government social benefit programs

What does it take to be an AI-native organisation?

AI-driven support for bilingual education in Senegal

Where to test a model built for scaling

Related content

Quiz

Intro to Stata – Quiz 1

The Stata Interface (1) Quiz

Lesson 1

Stay up-to-date with IDinsight