SG 9

Question 1

• A claim or statement about the value of a single population characteristic or the values of several population characteristics.

Answer 1

Hypothesis

Question 2

One way of summarizing and testing the evidence for a hypothesis is through a _______

Answer 2

significance test

Question 3

Also called hypothesis test.
- A method that uses sample data to decide between two competing hypotheses about a population characteristic.
- It helps researchers decide if the observed difference is so large that it justifies the conclusion that the sample is different from the population in terms of the attribute of interest

Answer 3

Significance test

Question 4

null hypothesis vs alternative hypothesis

Answer 4

• Null hypothesis. It asserts that there is “no difference” between the sample value and the population value
• Alternate hypothesis. Contradicts null hypothesis (i.e. the sample value is different from the population value)

The NH and the AH must be mutually exclusive and exhaustive.

Question 5

type 1 vs type 2 error

Answer 5

• type 1. the error committed when we decide to reject the NH when in reality, it is true (Reject Ho, but NH is TRUE)
• type 2. the error committed when we decide no the reject the null hypothesis when in reality, it is false (Accept Ho, but NH is FALSE)

Question 6

alpha vs beta error

Answer 6

An alpha error would be if the suspect is convicted when he is innocent while a beta error would be if the suspect is cleared when he is really guilty. We would rather free a guilty person than imprison an innocent one. In other words, if we reject the null hypothesis, we are confident about our decision.

Question 7

Also called the rejection region. This is the area under the sampling distribution that includes all unlikely sample outcomes.

Answer 7

Critical Region

Question 8

The proportion of the area included in the critical region. The probability of rejecting NH as untrue. We commonly use 0.05, 0.01 and 0.10 for significance level.

Answer 8

Significance Level (α)

Question 9

The appropriate statistic to use when looking for the population parameter is the minimum error estimator.

Answer 9

test statistic

Question 10

A value computed from the sample data and used as a “decision-maker” for the statistical test.

Answer 10

test statistic

Question 11

when do we reject the null hypothesis?

Answer 11

one-tailed or two-tailed test
alpha is greater than or equal to p-value
when the test statistic falls in the critical region

Question 12

___ means that the probability that we are making an error is low, no higher than 5% or 1%. It is unlikely due to random chance.

Answer 12

significant

Question 13

Like the z-distribution, it is mound-shaped and symmetrical about the mean

Answer 13

t-distribution

Question 14

As the sample size n (or df) increases, the t-distribution approaches the standard normal (z) distribution. (t or f)

Answer 14

t

Question 15

number of values that are free to vary after certain restriction have been imposed

Answer 15

degrees of freedom

Question 16

one-tailed vs two-tailed

Answer 16

A two-tailed test is performed when the difference between the sample and the population cannot be predicted

one-tailed test is done when the direction of the difference can be predicted.

Question 17

________ do not influence the selection of cases for each set while __________ are where the selection of cases for the first set completely determines which cases make up the samples of the second set

Answer 17

Independent samples
dependent samples

Question 18

If the selection of the case does not influence the cases in the other sample

Answer 18

independent

Question 19

If the selection of the cases from the first population completely determines which cases make up the sample from the second population

Answer 19

dependent