PYC2606
EXAM PACK
FOR ASSISTANCE WITH THIS MODULE +27 67 171 1739
,Dear PYC2606 student
This tutorial letter provides feedback on Assignment 02. Please read it carefully.
1. FEEDBACK ON ASSIGNMENT 02
Question 1
What is the difference between the information provided in Table 3 and in Table 4 in the mini-
manual of the SBQ?
1) Table 3 shows the validity of the SBQ and Table 4 shows its reliability.
2) Both tables provide information about the validity of the SBQ.
3) Table 3 is about the SBQ’s internal inconsistency and Table 4 is about its test-retest
reliability.
4) Table 3 shows the reliability of the SBQ and Table 4 shows its validity.
Both tables provide information about the reliability of the SBQ. Table 3 shows the split-half
reliability. Split-half reliability is determined when you want to know to what extent all the items in
the questionnaire measures the same attribute (i.e. the internal consistency of the questionnaire).
To calculate this, the scores on two halves of the questionnaire are correlated. Table 4 shows the
test-retest reliability. Test-retest reliability is determined when you are interested in the
stability/consistency of the results over time, that is how consistent are the results over different
occasions. You administer the same questionnaire to the same group of people on two different
occasions. The two sets of scores are correlated.
QUESTION 2
What does Table 4 in the manual tell us about the reliability of the SBQ? Choose the most correct
answer.
1) The table shows that the SBQ was administered twice, and it indicates the total scores of
five respondents for each administration.
2) The table shows a poor correlation between the two sets of scores.
3) The table shows a poor correlation between the two sets of scores, and it is a negative
correlation.
4) The table shows a high correlation between the two sets of scores, implying that the
SBQ has test-retest reliability.
More than one of the answer options are true, but these options differ in terms of the value of the
information provided. The table shows that SBQ was administered twice, and it indicates the total
scores of five respondents for each administration. It will add value to consider the relationship
between the two sets of scores. We see that there is a high correlation between the two sets of
scores and it is a positive correlation (ascending values in the one set correspond with ascending
values in the other set). It adds even more value if we interpret this relationship in terms of the
reliability of the SBQ. The high correlation implies a high degree of test-retest reliability.
3
,QUESTION 3
Suppose the reliability coefficient indicating the test-retest reliability of the SBQ was 0.89. This
would indicate that …
1) results are stable over time.
2) results are consistent over forms.
3) items of the SBQ are inter-related.
4) two halves of the test are inter-related.
Test-retest reliability indicates stability or consistency of scores over time. The strength of the
relationship between the scores obtained on two administrations of the test is expressed in terms
of a correlation coefficient. The value of a correlation coefficient can range from -1.00 to +1.00.
The value of 0.89 indicates a strong, but not a perfect relationship. The results can be regarded
as stable over time. The other options refer to alternate forms and split-half reliability, that is not
test-retest reliability.
QUESTION 4
In Table 6, what does the correlation between the SBQ and the Verbal Ability Questionnaire
(VAQ) mean? Choose the most correct answer.
1) It indicates a high degree of discrimination between the measurements of the SBQ
and the VAQ.
2) There is a good relationship between the SBQ and the VAQ.
3) There is a poor relationship between the SBQ and the VAQ.
4) It means the VAQ should be grouped with the teacher rating rather than with the SBQ.
If the SBQ measures the construct it is supposed to measure (experience of bullying behaviour),
it has construct validity. One way to determine this, is to see if scores on the SBQ correlate
significantly with scores on another questionnaire that measures a similar construct (such as the
School and Classroom Climate Questionnaire or SCCQ). This is called convergent validity. On
the other hand, scores on SBQ should not correlate significantly with scores on a questionnaire
that is not theoretically related to the SBQ (such as the Verbal Ability Questionnaire (VAQ). This
is called discriminant validity.
The value in Table 6 for the correlation between the SBQ and the VAQ is 0.13. This indicates a
poor relationship between the questionnaire. But what does this mean? It means that there is a
high degree of discriminant validity and thus a high degree of discrimination between the two
questionnaires.
Despite the support in Table 6 for the construct validity of the SBQ, there is a serious problem
with the construct validity of the questionnaire. One of the factors of the experiences of bullying
(the realm of bullying) is not measured by the SBQ and the questionnaire therefore does not
include all the factors of the content domain.
4
, QUESTION 5
Which of the following is NOT a purpose of a manual?
1) To describe the aim and target population of the questionnaire.
2) To provide information on the reliability of the questionnaire.
3) To provide statistics so that items can be selected.
4) To provide guidelines for the interpretation of results.
The purpose of a manual is explained in the resource: Manual: purpose and structure in the
PYC2606 study guide.
QUESTION 6
This question is based on the discussion that you, as research psychologist, had with your
colleagues on the questionnaire. You need to order the statements from most correct to least
correct.
Select the correct statement regarding the validity and reliability of the SBQ.
Jaco: The SBQ is valid if it really measures an individual’s experience of bullying, and it is reliable
if it identifies bullies.
Lebo: The SBQ is valid if it really determines an individual’s experience of bullying, and it is reliable
if it provides consistent measures of an individual’s experience of bullying.
Sipho: The SBQ is valid when there is a high correlation between its even items and its odd items,
and it is reliable if it is used to assess learners in a school context.
You agree most with, second most with, and least with:
1) Sipho, Jaco, Lebo
2) Sipho, Lebo, Jaco
3) Lebo, Jaco, Sipho
4) Lebo, Sipho, Jaco
5) Jaco, Sipho, Lebo
6) Jaco, Lebo, Sipho
A questionnaire is valid if it actually measures what it is supposed to measure (in this case an
individual’s experience of bullying) and it is reliable if these measures are consistent. Lebo
provides a correct explanation for both validity and reliability, Jaco provides a correct explanation
for validity only, and Sipho has neither correct.
QUESTION 7
This question is based on the discussion that you, as research psychologist, had with your
colleagues on the questionnaire. You need to order the statements from most correct to least
correct.
What is the conclusion one could reach, based on the information in Table 3 and Table 4 in the
mini-manual of the SBQ?
Jaco: The SBQ has high test-retest reliability but its criterion-related validity is questionable.
Lebo: The items of the SBQ seem to measure the same thing, and the questionnaire is not
vulnerable to external influences.
Sipho: The information obtained from these two tables supports the validity of the SIQ.
5
