8- Hypothesis Testing

Question 1

what is a hypothesis test?

Answer 1

a statistical method that rules out chance (sampling error) as a possible explanation for the results from a research study

Question 2

4 steps to the hypothesis test

Answer 2

1) state the hypotheses and select the alpha level
2) locate the critical region
3) compute the test statistic
4) make a decision

Question 3

hypothesis testing is an _________ process

Answer 3

hypothesis testing is an inferential process

Question 4

type 1 error

Answer 4

occurs when a researcher rejects a null hypothesis that is actually true, treatment has NO AFFECT

Question 5

the alpha level for a hypothesis test is the ……..

Answer 5

the alpha level for a hypothesis test is the probability that the test will lead to a type 1 error (0.5= 5% of making type 1 error)

Question 6

type 2 error

Answer 6

researcher fails to reject a null hypothesis that is really false, HAS AN AFFECT

Question 7

a type __ error is not as serious as a type ___ error.

Answer 7

a type 2 error is not as serious as a type 1 error.

Question 8

critical region for an alpha level of 0.05 = _____ and _____

Answer 8

critical region for an alpha level of 0.05 = -1.96 and +1.96

Question 9

critical region for an alpha level of 0.01 = ____ and ____

Answer 9

critical region for an alpha level of 0.01 = -2.58 and +2.58

Question 10

critical region for an alpha level of 0.001 = ____ and ____

Answer 10

critical region for an alpha level of 0.001 = -3.30 and +3.30

Question 11

higher variability can _____ the chances of finding a significant treatment effect

Answer 11

higher variability can reduce the chances of finding a significant treatment effect

Question 12

increasing the number of scores in the sample produces a _______ standard error and a ______ value for the z-scores

Answer 12

increasing the number of scores in the sample produces a smaller standard error and a larger value for the z-scores

Question 13

the values in the sample must consist of _______ ________.

Answer 13

the values in the sample must consist of independent observations. (occurrence of 1st event has no effect on 2nd)

Question 14

directional tests is also known as ____-______ ______.

Answer 14

directional tests is also known as one-tailed tests.

Question 15

what is “effects size” purpose?

Answer 15

effect size is intended to provide a measurement of the absolute magnitude of a treatment effect, independent of the size of the sample(s) being used

Question 16

what is a way to measure effect size of the mean difference?

Answer 16

cohen’s d

Question 17

a small effect of cohen’s d= ___

Answer 17

a small effect of cohen’s d= 0.2

Question 18

a medium effect of cohen’s d= ___

Answer 18

a medium effect of cohen’s d= 0.5

Question 19

a large effect of cohen’s d= ___

Answer 19

a large effect of cohen’s d= 0.8+

Question 20

power:

Answer 20

power is the probability that the test will correctly reject a FALSE null hypothesis

Question 21

as the _____ _____ increases, the probability of rejecting H0 also increases, which means that the power of the test increases.

Answer 21

as the EFFECT SIZE increases, the probability of rejecting H0 also increases, which means that the power of the test increases.

Question 22

reducing the _____ _____ for a hypothesis test also reduces the power of the test.

Answer 22

reducing the alpha level for a hypothesis test also reduces the power of the test.

Question 23

a _____ difference between sample and population mean produces a _____ z-score.

Answer 23

a larger difference between sample and population mean produces a larger z-score.

Question 24

a _____ standard deviation produces a ______ standard error, which produces a ______ z-score.

Answer 24

a larger standard deviation produces a larger standard error, which produces a smaller z-score.

Question 25

________ the number of scores, produces a ______ standard error, which produces a ______ z-score.

Answer 25

increasing the number of scores, produces a smaller standard error, which produces a larger z-score.