If a research collecting data stops sample collection at 50 observations versus 100 observations, how would the 95% confidence interval around the parameter estimate differ?

Question 1 options:

	The confidence interval forn = 50 would be narrower than the confidence interval forn = 100.
	The difference in sample size would not have any of the above effects.
	A sample ofn = 50 would cause the researcher to have more confidence in their esimates than would a sample ofn = 100.
	The confidence interval forn = 50 would be wider than the confidence interval forn = 100.

Question 2

Assume you have fit a regression model and then constructed a 95% confidence interval for the estimate of B1.If the confidence interval does not include 0, what does this mean?

Question 2 options:

	It means that the confidence interval could be 0.
	It means that the true value of B1 is 95% likely to be 0.
	It suggests we should adopt the complex model.
	It suggests we should retain the empty model

Question 3

What is the range of possible values within which we could be 95% confident that the true population mean would lie?

Question 3 options:

	The sample mean plus or minus one standard error.
	The sample mean plus or minus two standard deviations.
	The population (DGP) mean plus or minus one standard error.
	The population (DGP) mean plus or minus two standard errors.

Question 4

What are you doing when you are bootstrapping?

Question 4 options:

	Breaking the relationship between variables by shuffling to make a sample distribution
	Resampling from data already collected
	Making up a distribution to sample from
	Collecting many samples of data from the population

Question 5

If you were to make a bootstrapped sampling distribution of means and a simulated sampling distribution of means for the same variable (assuming the estimated standard mean, standard deviation, and normality), how would the two distributions compare?

Question 5 options:

	They would be very different in center, but similar in shape and spread.
	They would be different in center, shape, and spread
	They would be similar in center, but very different in shape and spread.
	They would be similar in center, shape, and spread.

Question 6

Imagine that a researcher who collected salary data by gender for college teachers also collected similar data from 100 elementary school teachers and found that among elementary school teachers, salaries varied less than they did among college teachers. If we estimate the mean salary in each data frame, which would have the wider 95% confidence interval measured in dollars? Which confidence interval would be wider if measured in number of standard errors?

Question 6 options:

	Elementary teachers' salary would have the wider 95% confidence interval, whether measured in dollars or in number of standard errors.
	College teacher's salary would have the wider 95% confidence interval if measure in dollars. The confidence intervals would be the same if measured in number of standard errors.
	Elementary teachers' salary would have the wider 95% confidence interval if measured in dollars. The confidence intervals would be the same if measured in number of standard errors.
	College teachers' salary woul dhave the wider 95% confidence interval, whether measured in dollars or in number of standard errors.

Question 7

A model usingAge to predictSalary can be specified as Salary1=b0+b1Age1+e1. Which of the following is a correct interpretation of the 95% confidence interval for B1in this model?

Question 7 options:

	We are 5% confident that the true slope is not within this confidence interval.
	We are 95% confident that the confidence interval for b1will be the same for any sample size larger than the current sample.
	All of the above are correct.
	We are 95% confident that the true slope of the DGP will be equal to b1.

Question 8

Given the model below, if you want to determine how much expectedSalary changes based onAge, around which parameter estimate would you construct a confidence interval?

Salary1=b0+b1Age1+e1.

Question 8 options:

	b0
	b1
	Age1
	e1

Question 9

Given the model below, how would you determine if the true population parameter (B1) is equal to your parameter estimate (b1)?

Salary1=b0+b1Age1+e1.

Question 9 options:

	Calculate a confidence interval
	Construct a sampling distribution
	Run lm() in R
	You can't determine the true population parameter from any of these actions

Question 10

Which of the following information can we obtain from the output below?

Call: lm(formula = Salary ~ Age, data = SalaryGender) Coefficients: (Intercept) Age -9.305 1.319

Question 10 options:

	Estimates of b0 and b1
	Confidence interval for b1
	Significance of the model
	Mean and standard deviation ofSalary

Question 11

Age.model <- lm(Salary ~ Age, data = SalaryGender) confint(Age.model)

Using the code above, we created a model to predictSalary usingAge as the explanatory variable. We then constructed 95% confidence intervals around the parameter estimates. The output is pictured below.

 2.5 % 97.5 % (Intercept) -33.30870 14.699700 Age 0.83179 1.805966

If we repeated this study and found a smaller standard error, what would be different about the confidence interval for B1?

Question 11 options:

	It's likely that the 95% confidence interval for b1would be wider.
	The confidence interval would stay the same as long as the confidence level is the same.
	There is no way to tell because standard error is not related to confidence intervals.
	It's likely that the 95% confidence interval for b1would be narrower.

Question 12

If you bootstrap a sampling distribution of means based on your sample of data, what will be the mean of the bootstrapped distribution?

Question 12 options:

	0
	The mean of your sample
	The true mean of the population
	Whatever you decide for it to be

Question 13

How can sampling distributions help us interpret our data?

Question 13 options:

	Sampling distributions allow us to see if our sample data came from the population.
	Sampling distributions eliminate sampling variation from the sample data.
	Sampling distributions give us a way to assess whether a relationship between two variables we've observed in our data is likely to have occurred just by chance.
	Sampling distributions give us a way to assess whether a relationship between two variables we've observed in our data is causal or correlational.