What happens to the following sample size calculation if you increase the value for ES: n =

((1.96 + .84)/2)2?Answer The sample size goes down.

The sample size stays the same.

The sample size goes up.

Impossible to say given the information.

The reason for this is because the difference between the man of treatment group and the mean

of control group increases.

Question 2

What is the standard deviation in the following calculation (30-20)/10 = 1? Answer = 10

30

20

1

This is the amount of variation or dispersion of the figure from the average.

Question 3

Which of the following statements about Type 1 and Type 2 error is false? Answer: They are

both a form of chance error.

They are both represented using Greek letters.

They are both a form of systematic error.

Ideally you should try to keep both as low as possible in your study.

Question 4

Which is not a reason for making your sample size as large as possible? Answer: Reducing Type

1 error

Reducing Systematic error

Reducing Chance error

Reducing Type 2 error

A larger sample size reduces the level of various errors except chance errors. It therefore

increases the level of credibility of a given sample.

QUIZ 2

Question 5

What happens to the following sample size calculation if you increase the size of the population

from which the sample is drawn: n = ((1.96 + .84)/2)2? Answer: The sample size goes down.

The sample size stays the same.

The sample size goes up.

Impossible to say given the information.

Increase in population requires the sample size to be increased as well to match the high

population to ensure that the results are realistic.

Question 6

Given a Type 2 error rate of .10, what is the Power? Answer: 10%

90%

1.10

Unable to calculate given the information.

Power is the probability of rejecting null hypothesis when one is required to do so especially to

avoid type II error.

Question 7

Given a Type 1 error rate of .10, what is the Power? Answer: 15%

1.15

90%

Unable to calculate given the information.

Question 8

Given a Type 2 error rate of .15, what is the Power? Answer: 15%

1.15

85%

Unable to calculate given the information.

Question 9

Which of the following is not an acceptable level for a Type 1 error in a study? Answer: .05

.20

QUIZ 3

.01

5%

Question 10

Which of the following parts of a sample size calculation are usually educated guesses? Answer:

Z1 – α/2

ES

Z1 – β

None of the above

Question 11

Which of the following is true about Power?

Answer: A study conducted with insufficient Power has a high chance of a Type 1 error.

Whenever you read of a study where they were unable to reject the null hypothesis you

should check whether it had enough Power.

It is related to the Type 1 error rate you set for your study.

Given a constant sample size, if you pre-specify a higher type 1 error, the statistical power will

decrease.

Question 12

Which of the following is the correct definition of Power?

Answer: It is the likelihood of an investigator to reject a null hypothesis that is false and

should be rejected.

It is the likelihood of an investigator to fail to reject a null hypothesis that is false and should

be rejected.

It is the likelihood of an investigator to reject a null hypothesis that is true and should not be

rejected.

It is the likelihood of an investigator to fail to reject a null hypothesis that is true and should

not be rejected.

Question 13

Which of the following is true about sample size?

Answer: The sample size you calculate will always be sufficient to conduct your statistical tests

Events like questions left unanswered in questionnaires and dropouts from a study can

reduce the available sample size.

QUIZ 4

The size of the effect you are trying to observe, whether a difference in means or an association

between variables is not important when computing sample size

A sample size of 30 or greater is always sufficient

Question 14

Which of the following is a true statement about hypothesis testing?

Answer: You conduct hypothesis testing to prove your null hypothesis.

You conduct hypothesis testing to prove your alternative hypothesis.

You conduct hypothesis testing to eliminate the effect of chance on your solution.

You conduct hypothesis testing to test the significance of a proposed relationship between

variables.

Question 15

Which of the following is true about Sample Size calculations?

Answer: It does not depend on the type of statistical test you plan to use

It should not be calculated using software

Some of the values used in calculating it are estimates

It can be computed after performing the test to see if you had sufficient sample size

Question 16

Which of the following is an example of a Type 1 error?

Answer: Rejecting a false null hypothesis.

Rejecting a true null hypothesis.

Failing to reject a false null hypothesis.

Failing to reject a true null hypothesis.

Question 17

Which of the following is an example of a Type 2 error? (include on all quizzes)

Answer: Rejecting a false null hypothesis.

Rejecting a true null hypothesis.

Failing to reject a false null hypothesis.

Failing to reject a true null hypothesis.

QUIZ 5

Question 18

Which of the following is true of the statement: The men in this sample are taller than the

women?

Answer: It is a directional null hypothesis.

It is a directional alternative hypothesis.

It is a two-tailed alternative hypothesis.

It is a one-tailed null hypothesis.

Question 19

Which is the correct null hypothesis based on this statement: People with diabetes have higher

systolic blood pressure than people without diabetes?

Answer: People with diabetes have lower systolic blood pressure than people without diabetes.

People with diabetes have equal systolic blood pressure when compared to people without

diabetes.

People with diabetes have a systolic blood pressure equal to or lower than people without

diabetes.

None of these is a null hypothesis.

Question 20

Which of the following is a true statement about a null hypothesis?

Answer: It is the hypothesis you are trying to prove.

It is always written as a question.

It is a statement of no association between variables or no difference between groups.

It is not related to the alternative hypothesis.

.

References

Ader, J., & Hand, D. (2007). Advising on research methods: A consultant’s companion. Huizen,

The Netherlands: Johannes van Kessel Publishing