Uncertainty and Hypothesis Testing

Question 1

Estimand

Answer 1

the unobserved quantity that we are trying to learn about

Question 2

Estimator

Answer 2

The procedure we apply to data to generate a numerical result

Question 3

Estimate

Answer 3

The numerical result arising from the application of the estimator

Question 4

Sample mean

Answer 4

an example estimator

Question 5

Bias

Answer 5

Differences between the estimate and the estimand that arise for systematic reasons

Question 6

Noise

Answer 6

Differences between the estimate and the estimand that arise due to idiosyncratic facts

Question 7

Descriptive inference

Answer 7

A non-representative sample, unit non-response, misreporting

Question 8

Quantifying precision

Answer 8

Either use the standard error or the confidence interval because both are related to the sampling distribution

Question 9

Sampling distribution

Answer 9

the probability distribution of a statistic that is obtained through repeated sampling of a specific population

Question 10

Standard Error

Answer 10

the standard deviation of the sampling distribution

Question 11

How to conduct hypothesis testing

Answer 11

State the hypothesis that you want to refute (null hypothesis). Then pick a significance threshold, also known as the probability that you observe when the null hypothesis is true. After, compute the probability that you observe a value at least as extreme as the one you observed when the null was true. Lastly, if the p-value is less than a significance threshold (0.05) for example, then can reject the null.

Question 12

Alternate hypothesis

Answer 12

The hypothesis we test against the null

Question 13

Test statistic

Answer 13

A function of the observed data that can be used to test the null hypothesis

Question 14

Reference distribution

Answer 14

The probability of the test statistic under the null