PYC3704/202/1/2021
Psychological Research: Early Completion
Programme (ECP).
Department of Psychology
• Feedback to Assignment 02
,Question 1
In statistical hypothesis testing, the - - - - - is used to determine the -----------which is to be compared to the
chosen --------- to make an inference regarding the status of the hypotheses.
1. p-value; level of significance; test statistic
2. test statistic; p-value; level of significance
3. p-value; test statistic; level of significance
4. test statistic; level of significance; p-value
Answer: The correct answer is option 2. To test a hypothesis, you first calculate an appropriate test
statistic, and this is then used to determine the p-value (using statistical tables or a computer program).
After that, this p-value is compared with a level of significance (α), chosen by the researcher, which
represents the maximum risk which the researcher is willing to take that the observed effect is due to
chance and not a reflection of an actual relationship between variables in the population.
2
, PYC3704/202
Question 2
Two samples may be regarded as dependent when - -.
1. each measurement in one sample is correlated with a measurement in the other sample
2. there is a systematic relationship between the measurements in one sample and the other
3. they were drawn from the same population
4. they are both totally random
Answer: Option 2 is correct and is a definition of dependent samples, where the measurements form
matched pairs. Option 1 is not really valid as a definition of dependence. Correlations are usually
calculated from two measurements (that is, two variables) in the same sample, not from different samples.
If you find a significant relationship, it implies that one type of measurement may be dependent on the
other type of measurement, but it is not really a dependency between two separate samples of data. It is
possible to correlate measurements from two samples if they are paired off in matched pairs of some kind
and finding a significant correlation would then probably imply dependence of some kind. This could imply
that the samples were discovered to be dependent, but it is not how ‘dependent samples’ are defined.
Being drawn from the same population does not imply dependence, so Option 3 is not correct.
Randomness of the samples is not relevant and is in any case likely to imply a lack of dependence, so
Option 4 is also not correct.
Question 3
Suppose H0: = 100 is tested against H1: μ 100 with α = 0.05. If the t-statistic is found to be -3.20 and the
two-tailed p-value is 0.04, what decision regarding the statistical hypothesis can be taken?
1. Reject H0 and accept H1
2. Do not reject H1
2. Reject H1 and accept H0
4. Do not reject H0
Answer: Option 1 is the correct answer. The p-value is 0.04 and α = 0.05, so p-value < α gives a
significant result. The H0 can be rejected in favour of the H1. Note that the p-value provided is two-tailed
and the test is non-directional, so no adjustment of the p-value is needed. If the p-value which was provided
was one-tailed, it would have been necessary to multiply this one-tailed p-value by 2 to get a two-tailed p-
value before comparing it to the level of significance (see p. 81 in the PYC3704 Guide).
Question 4
The following list contains a number of situations where a researcher may consider using a variation of
the t-test:
(a) To compare two group means
(b) To determine whether a relationship exists between two categorical (nominal scale) variables
(c) To compare a group mean with a constant value
(d) To determine whether a relationship exists between two continuous quantitative variables
Two of the statements above are true. Choose the correct set of true statements from the list below:
1. (a) and (c)
2. (a) and (b)
3. (b) and (d)
4. (c) and (d)
Answer: Option 1 is correct. A t-test for a two-groups design can be used to compare two group or
3
Psychological Research: Early Completion
Programme (ECP).
Department of Psychology
• Feedback to Assignment 02
,Question 1
In statistical hypothesis testing, the - - - - - is used to determine the -----------which is to be compared to the
chosen --------- to make an inference regarding the status of the hypotheses.
1. p-value; level of significance; test statistic
2. test statistic; p-value; level of significance
3. p-value; test statistic; level of significance
4. test statistic; level of significance; p-value
Answer: The correct answer is option 2. To test a hypothesis, you first calculate an appropriate test
statistic, and this is then used to determine the p-value (using statistical tables or a computer program).
After that, this p-value is compared with a level of significance (α), chosen by the researcher, which
represents the maximum risk which the researcher is willing to take that the observed effect is due to
chance and not a reflection of an actual relationship between variables in the population.
2
, PYC3704/202
Question 2
Two samples may be regarded as dependent when - -.
1. each measurement in one sample is correlated with a measurement in the other sample
2. there is a systematic relationship between the measurements in one sample and the other
3. they were drawn from the same population
4. they are both totally random
Answer: Option 2 is correct and is a definition of dependent samples, where the measurements form
matched pairs. Option 1 is not really valid as a definition of dependence. Correlations are usually
calculated from two measurements (that is, two variables) in the same sample, not from different samples.
If you find a significant relationship, it implies that one type of measurement may be dependent on the
other type of measurement, but it is not really a dependency between two separate samples of data. It is
possible to correlate measurements from two samples if they are paired off in matched pairs of some kind
and finding a significant correlation would then probably imply dependence of some kind. This could imply
that the samples were discovered to be dependent, but it is not how ‘dependent samples’ are defined.
Being drawn from the same population does not imply dependence, so Option 3 is not correct.
Randomness of the samples is not relevant and is in any case likely to imply a lack of dependence, so
Option 4 is also not correct.
Question 3
Suppose H0: = 100 is tested against H1: μ 100 with α = 0.05. If the t-statistic is found to be -3.20 and the
two-tailed p-value is 0.04, what decision regarding the statistical hypothesis can be taken?
1. Reject H0 and accept H1
2. Do not reject H1
2. Reject H1 and accept H0
4. Do not reject H0
Answer: Option 1 is the correct answer. The p-value is 0.04 and α = 0.05, so p-value < α gives a
significant result. The H0 can be rejected in favour of the H1. Note that the p-value provided is two-tailed
and the test is non-directional, so no adjustment of the p-value is needed. If the p-value which was provided
was one-tailed, it would have been necessary to multiply this one-tailed p-value by 2 to get a two-tailed p-
value before comparing it to the level of significance (see p. 81 in the PYC3704 Guide).
Question 4
The following list contains a number of situations where a researcher may consider using a variation of
the t-test:
(a) To compare two group means
(b) To determine whether a relationship exists between two categorical (nominal scale) variables
(c) To compare a group mean with a constant value
(d) To determine whether a relationship exists between two continuous quantitative variables
Two of the statements above are true. Choose the correct set of true statements from the list below:
1. (a) and (c)
2. (a) and (b)
3. (b) and (d)
4. (c) and (d)
Answer: Option 1 is correct. A t-test for a two-groups design can be used to compare two group or
3
