Sampling for Surveys-Quiz 3

JavaScript isn't enabled in your browser, so this file can't be opened. Enable and reload.

Email *

1. Which of the following statements is true about margin of error? (Choose all that apply) *

1 point

The margin of error is equal to the width of the confidence interval

The margin of error is equal to ½ the width of the confidence interval

As sample size goes up, margin of error goes up

As sample size goes up, margin of error goes down

To estimate sample size, you start by setting a target margin of error and work backwards

To estimate sample size, you start by setting a target standard deviation and work backwards

None of the above

Required

2. Which of the following statements is true about the standard error? (Choose all that apply) *

1 point

The standard error is the most common margin of error

As variance in the underlying data increases, standard error increases

As variance in the underlying data increases, standard error decreases

As sample size increases, standard error increases

As sample size decreases, standard error increases

SRS is always the most efficient sampling design (i.e. leads to the smallest standard error)

SRS is not necessarily the most efficient sampling design (i.e. leads to the smallest standard error).

None of the above

Required

3. At which value of the population parameter is the variance in a binary variable maximized? *

1 point

0.25

0.33

0.5

None of the above

4. Suppose that you wanted to estimate the fraction of children who have a learning disability in this population. How many children should you sample such that your estimate has a margin of error of +/- 4 percentage points, assuming a 95% confidence interval? Assume SRS, and use a conservative assumption about the standard deviation calculation. Round up to the nearest integer. *

1 point

5. Now double the sample size from your previous answer. What is the approximate margin of error now, assuming a 95% CI? Report your answer in terms of percentage points, and round to the nearest 0.1 (only enter the number, not "+/-" or "p.p."). *

1 point

6. In Q4 we made an assumption about the prevalence of learning disabilities to make our sd calculation conservative. Let’s make a less conservative assumption: suppose that we expect the prevalence of learning disabilities in the population to be 10%. Now how many children should you sample such that your estimate has a margin of error of +/- 4 percentage points, assuming a 95% confidence interval? Round up to the nearest integer. *

1 point

7. Suppose that you wanted to estimate the average test score of students in your population. How many children should you sample such that your estimate has a margin of error of +/- 0.05 standard deviations, assuming a 95% CI? Still assume SRS, and round up to the nearest integer. *

1 point

8. Suppose that you wanted to estimate average test score, with a margin of error of +/- 0.5 points on the test, assuming a 95% CI. Assume that test scores will be similarly distributed to baseline test scores for students in the EG DIB dataset (variable total_bl). How many children should you sample? Still assume SRS, and round up to the nearest integer. *

1 point

Submit

Clear form

Never submit passwords through Google Forms.

This form was created inside of Idinsight.org. Report Abuse

Forms