Hypothesis Testing

Question 1

what is the Null hypothesis?

Answer 1

The null hypothesis, H0: a statement that is assumed to be true until proven otherwise

Question 2

What is a type 1 error

Answer 2

Cost - acted in error

Question 3

type 2 error

Answer 3

opportunity cost - didn’t act when we should have

Question 4

why do we hypothesis test?

Answer 4

The test statistic is used to make the statistical decision and is a function of a sample of size n

Since SIGMA is typically unknown, use the test statistic (ie T)

T is then compared to a ‘critical value’ to decide if the sample mean is ‘too far’ from U.

Question 5

Higher significance level implies?

Answer 5

implies lower probability of type-I error

Question 6

Hypothesis Testing and Confidence Intervals

Answer 6

Confidence intervals are another way to confirm the result of an hypothesis test.

The interval explicitly shows the region where you’re likely to find the true parameter value

If the confidence interval doesn’t include H0, then an hypothesis test will reject H0.