C8511 Research Skills in Psychology
C8511
THE UNIVERSITY OF SUSSEX
BSc First Year Examination 2012
RESEARCH SKILLS IN PSYCHOLOGY
SAMPLE PAPER with answers
INSTRUCTIONS
Do not write your name on this question paper
Do not tear off any part of this question paper
Do not, under any circumstances, remove this question paper, used or unused,
from the examination room. It must be left on your desk when you leave the
examination.
TIME ALLOWED: 2 HOURS
Answer ALL Questions
Write your answers ON THIS QUESTION PAPER
There are five sections to this paper: 1,2,3,4 and 5. Each section carries 20% of the
marks. Write your answers to the questions in sections 1, 2, 3 and 4 in the answer
boxes on page 15 at the end of the exam paper. Write the answers to section 5 in
the boxes provided within that section. You are advised to spend an equal amount
of time on each section.
C8511 Research Skills in Psychology
SECTION 1: BASIC CONCEPTS
In this section, a concept is given together with five alternative definitions, only one
of which is correct. Indicate which of the definitions is correct by writing the
appropriate letter (a, b, c, d or e) in the table on page 15 at the end of the exam
paper (2 marks per question).
1. The mean is:
(a) a summary of some data estimated by adding all the numbers, and dividing
by the number of numbers minus one.
(b) a summary of the data that is a measure of the population rather than the
sample.
(c) a summary of some data that is always half way between the maximum and
minimum value of the data.
(d) a summary of the data in terms of the most common value of the data.
(e) none of the above.
2. If data show "homogeneity of variance", it means that:
(a) they must be analysed with a Chi-Square test.
(b) scores in each group or condition show comparable amounts of variance.
(c) the data are normally distributed.
(d) they have been measured on an interval or ratio scale.
(e) none of the above.
3. The variance is always:
(a)
(b)
(c)
(d)
(e)
a measure of how noisy the data are, relative to a control.
the square of the standard deviation.
a measure of how many mistakes the subjects made.
a measure that changes if you add a constant to all of the data.
none of the above.
4. The null hypothesis is always:
(a)
(b)
(c)
(d)
(e)
proved to be incorrect by a significant result.
the hypothesis you do not believe before an experiment.
the simplest explanation for the data collected.
shown to be highly unlikely by a significant result.
none of the above.
2
C8511 Research Skills in Psychology
5. For the results of a parametric statistical test to be valid, the data should:
(a)
(b)
(c)
(d)
(e)
not show homogeneity of variance.
be measurements on a categorical scale
show homoscedasticity.
be roughly normally distributed.
be measurements on a rating scale.
6. A type two error:
(a)
(b)
(c)
(d)
(e)
is when one rejects the null hypothesis when it is in fact true.
is when one accepts the null hypothesis when it is false.
is always the result of bias in the sample.
is the error of using the wrong test.
is the error of using the same data twice.
7. A significant negative correlation between data sets implies:
(a)
(b)
(c)
(d)
(e)
that there is no relationship between the two sets of data.
that the relationship between two sets of data is not a simple linear one.
that one data set is related to the other at better than chance levels.
that the data consist mainly of negative numbers.
none of the above.
8. If a sample is unrepresentative, this implies:
(a) that not enough data were collected.
(b) that the data are not normally distributed.
(c) that one single measurement was not typical and therefore not useful.
(d) that this sample should not be used to make inferences about the population.
(e) none of the above.
9. If data are normally distributed:
(a)
(b)
(c)
(d)
(e)
the data are typical of the population.
the data consist of categorical data.
the probability distribution of the population is bell shaped.
the data are always positive.
the data are based on ranks.
10. If you perform a one-tailed statistical test, your hypothesis is:
(a)
(b)
(c)
(d)
(e)
that the experiment was conducted double blind.
that the difference between your groups will be in a specific direction.
that two different measurements are unpredictable from each other.
that the variance of two measurements does not differ significantly.
that the mean of two measurements does not differ significantly.
3
C8511 Research Skills in Psychology
SECTION 2: INTERPRETING SPSS OUTPUT
You are given some SPSS output from a study, and questions to answer about it.
There are two parts to this section, each with 10 questions (1 mark per question).
Enter your answers in the table on page 15 at the end of the exam paper.
PART 1. A psychologist hypothesises that "sadotoothpullerophobia" (fear of
dentists) develops because of bad childhood experiences. On the basis of an initial
interview, two groups of seven adults are identified: a group who report having had
bad childhood experiences of dentists, and a group who report no such
experiences. For each participant, their rating of their fear of the dentist (on a 100point scale) was recorded. Here is some of the SPSS output.
Test Statisticsa
DentistFear
Mann-Whitney U
8.000
Wilcoxon W
36.000
Z
-2.111
Asymp. Sig. (2-tailed)
Exact Sig. [2*(1-tailed Sig.)]
.035
.038b
4
C8511 Research Skills in Psychology
On the basis of this information, answer the following questions. Write your answers
in the appropriate boxes at the end of the exam paper.
1.
Which is the most appropriate statistical test to perform on these data?
(a) Wilcoxon matched-pairs test.
(b) Mann-Whitney test.
(c) Spearman's correlation test.
2.
The test results shown in the "Test Statistics" table are all:
(a) Statistically significant at p < .05.
(b) Statistically significant at p > .05.
(c) Not statistically significant at p < .05.
3.
On the basis of the description, what kind of hypothesis would be most
appropriate for this study?
(a) A one-tailed hypothesis.
(b) A two-tailed hypothesis.
(c) A neutral hypothesis.
4.
The variation in rating for the bad experiences group is:
(a) higher than for the good experiences group.
(b) the same as for the good experiences group.
(c) lower than for the good experiences group.
5. What is the standard deviation for the bad experiences group? 22.20
6. What is the standard deviation for the good experiences group? 31.68
7. What is the standard error of the mean for the bad experiences group? 8.39
8. What is the standard error of the mean for the good experiences group? 11.97
9. Using the data in the "Descriptives" table, complete the following boxplot (on the
next page) for the good experiences group.
C8511 Research Skills in Psychology
10. On the basis of these results, the researcher should conclude that:
(a) bad childhood experiences lead to greater fear of dentists in adulthood .
(b) bad childhood experiences lead to less fear of dentists in adulthood.
(c) bad childhood experiences are not significantly related to fear of dentists in
adulthood.
C8511 Research Skills in Psychology
PART 2.
A researcher is concerned that there might be a relationship between watching
"Celebrity Come Dancing" and cortical atrophy. The researcher obtains the brains
of 30 inmates from a residential home. He takes a standard-sized slice of cortex
from each brain and measures how many synapses it contains. He correlates this
measure with a record of how many episodes of "Celebrity Come Dancing" were
viewed by each inmate. Here is some of the SPSS output from this study.
Correlations
Number_of_viewings
Pearson Correlation
Number_of_viewings
1
-.772**
Sig. (2-tailed)
.000
N
Pearson Correlation
synapses
synapses
Sig. (2-tailed)
30
30
-.772**
1
.000
N
30
30
Model Summary and Parameter Estimates
Dependent Variable: synapses
Equation
Model Summary
R Square
Linear
.597
F
41.395
df1
Parameter Estimates
df2
1
The independent variable is Number_of_viewings.
Sig.
28
.000
Constant
3865.010
b1
-205.403
C8511 Research Skills in Psychology
1. A correlation test has been performed on these data. What does it tell us about
the relationship between the number of viewings of "Celebrity Come Dancing" and
the number of synapses?
(a) That there is a significant positive correlation between these two variables.
(b) That there is a non-significant positive correlation between these two variables.
(c) That there is a significant negative correlation between these two variables.
(d) That there is a non-significant negative correlation between these two variables.
2. How many degrees of freedom does this Pearson's correlation have?
(a) 30
(b) 29
(c) 28
(d) 27
3. Which of these equations correctly describes the regression line that SPSS
would fit to the scatterplot?
(a) Predicted Y = 3865.01 + - 205.40 * X
(b) Predicted Y = 3865.01 + 205.40 * X
(c) Predicted Y = 205.40 + 3865.01 * X
(d) Predicted Y = -205.40 + 3865.01 * X
4. What is the value of the intercept in the regression equation?
(a) -.772
(b) 3865.01
(c) -205.403
(d) .597
5. Approximately how much of the variability in number of synapses is accounted
for by its relationship with viewing "Celebrity Come Dancing"?
(a) 40%
(b) 60%
(c) 77%
(d) 41%
6. If a person had watched 5 episodes of " Celebrity Come Dancing",
approximately how many synapses would you predict them to have?
(a) 2,838
(b) 9,230
(c) 1,360
7. If a person had watched 10 episodes of " Celebrity Come Dancing",
approximately how many synapses would you predict them to have?
(a) 2,416
(b) 4,620
(c) 1,811
8. If a person had watched 15 episodes of " Celebrity Come Dancing",
approximately how many synapses would you predict them to have?
(a) 1,200
(b) 1,049
(c) 784
C8511 Research Skills in Psychology
9. Which of the regression lines on the graph is the correct one for predicting the
number of synapses from the number of episodes of "Celebrity Come Dancing"
watched?
(a) Line A.
(b) Line B.
(c) Neither line A nor line B.
10. What should the researcher conclude from these results about the relationship
between viewing "Celebrity Come Dancing" and the number of synapses present?
(a) The more episodes that were watched, the fewer the synapses in the tissue
sample.
(b) The more episodes that were watched, the greater the number of synapses in
the tissue sample.
(c) Watching "Celebrity Come Dancing" produces a reduction in the number of
syapses in the cortex.
(d) Watching "Celebrity Come Dancing" produces an increase in the number of
synapses in the cortex.
C8511 Research Skills in Psychology
SECTION 3: WHICH TEST?
In this section you will be given a brief description of a study and some data; you
have to choose the appropriate test. Unless stated otherwise, assume the data are
normally distributed and show homogeneity of variance. There are 10 questions,
each worth 2 marks. For each question write the letter corresponding to the correct
test (i.e. A for Wilcoxon, B for Friedman, etc.) in the table on page 15 at the end of
this exam paper. (Do not write the name of the test itself in the table: if you do so, it
will not be counted as an answer).
A. Wilcoxon.
B. Friedman.
C. Mann-Whitney.
D. Kruskal-Wallis.
E. Spearman’s rho.
F. Pearson’s r.
G. Chi-Squared.
1.
A researcher is interested in whether there is a relationship between daily
temperature and the amount of time that students study. She measures the
temperature each day for six months, and the mean number of hours spent in the
library by a group of students. What test is required to test the hypothesis that
study time is related to temperature? F
2.
A study was performed to examine the effects of allergies on mood. One
group of participants were allergy-free; another group suffered from severe
hayfever; a third group suffered from eczema; and a fourth group had gluten
intolerance. A therapist rated the mood of each participant on a 100-point scale.
Which statistical test should the researchers use to see if allergies affect mood? D
3.
A study was performed to investigate the effects of alcohol on people's
impulsivity. Three groups of participants were compared. One group had water;
one group had 1 pint of beer; and the third group had one pint of vodka. Each
subject's impulsivity was assessed by a questionnaire that yielded a score out of
50. Which statistical test should the researchers use to test if alcohol affects
impulsivity? D
4.
A researcher is interested in comparing the effectiveness of four different
scuba diving courses. He assembles a boat-full of divers (twenty from each
course), and takes them to a nearby barrier reef. Each diver makes one dive, in
which he attempts to stay safely below the water for 40 minutes. The researcher
then measures the number of divers from each course who successfully return to
the surface. Which test should the researcher use in order to see if there is a
significant difference between the effectiveness of the different training courses? G
5.
In response to claims that A-levels are easier now than they were 20 years
ago, a group of current sixth-formers are given two English exams, one a copy of
the 1980 A-level paper, and the other a copy of the 2005 A-level paper. Each
student provides a mark for each exam, out of 100. Their scores for the 1980 paper
are heavily skewed. Which statistical test should be used to test the hypothesis that
English exams used to be harder than they are nowadays? A
5
C8511 Research Skills in Psychology
6. Researchers wants to find out if there is a relationship between length of
service in academia and levels of obsession. The obsession level of each of fifty
lecturers was measured by questionnaire. The length of time that each lecturer
had been in the university was also recorded. After collecting these data, it was
found that the scores were somewhat skewed towards the "highly obsessive"
end of the scale. Which test should be used to measure the strength of the
relationship between obsession and length of time in employment? E
7. Anecdotal evidence suggests that many comedians' choice of career can be
traced to their childhood experiences of using comedy in order to avoid being
bullied at school. 200 comedians and 300 member of the public were interviewed
and asked whether or not this use of comedy was true of them personally. What
test should be used to test the hypothesis that bullying encourages children to
follow a career in comedy? G
8. Ten children are each given four different toys to play with, and are asked to
rate each toy in terms of how much they liked it. Which test would you use to
assess whether the four toys are liked equally? B
9. Three hundred bird watchers are given the choice between a telescope and
a pair of cheap binoculars. 182 prefer the telescope. Which test would you use to
determine whether or not this is a statistically significant difference in preference?
G
10. 200 drivers' performance was rated by a professional driving instructor
under three conditions: while they drove for 30 minutes without distraction, while
they drove for 30 minutes using a hands-free mobile phone, and while they drove
for 30 minutes and listened to the radio. What test would you use to determine
whether distraction affected driving performance? B
6
C8511 Research Skills in Psychology
SECTION 4
In the following questions you are given some details of an experiment, the
results of a number of statistical tests, and a set of conclusions. Only ONE of
these tests is appropriate, and only ONE in each set of conclusions is correct.
Thus only TWO of the statements are correct in each of the following questions.
Indicate which two are correct by writing the appropriate letters in the table on
page 15 at the end of this exam paper (4 marks per question: 2 for identifying the
correct statistics, and 2 for identifying the correct interpretation).
1. An experimenter develops a method that may help the memory of people with
brain damage. It is thought that these people have problems because when they
make a mistake in recall, they cannot remember whether the mistake or the real
answer was correct. Therefore they are given strong clues to the answer, to stop
them ever making mistakes and hopefully improving their memory (this method is
known as errorless learning). To test the effectiveness of this method, the
experimenter asked ten head injury patients to learn the names of 20 of their
carers. Ten of the names were learnt using errorless learning, and ten using
simple trial and error. The data are not normally distributed.
Patient
A
B
C
D
E
F
G
H
I
J
Mean:
S.D.:
A: Number of names learnt using
trial and error
7
7
6
6
5
6
3
7
5
6
5.8
1.23
B: Number of names learnt using
errorless learning
4
7
6
6
3
3
4
3
4
5
4.5
1.43
Statistical tests:
(a)
(b)
(c)
(d)
Mann Whitney test: U (10, 10) = 25, p = .05.
Wilcoxon test: z = -2.05, p = .04.
Pearson's correlation of A and B: r (8) =.25, p = .48.
Spearman's correlation of A and B: rs (10) = .21, p = .56.
Conclusions:
(e) the number of names learnt by trial and error is related to the number
of names learnt with errorless learning.
(f) Memory for names is unaffected by the type of learning.
(g) Memory for names is significantly better if errorless learning is used.
(h) Memory for names is significantly better if trial and error learning is
used.
7
C8511 Research Skills in Psychology
2. An experimenter is interested in whether users of the drug MDMA ("Ecstasy")
are higher sensation-seekers than non-users. 12 Ecstasy users and 12 nonusers rated themselves for sensation-seeking (7 = "highly sensation-seeking")
Participant:
1
2
3
4
5
6
7
8
9
10
11
12
Mean:
S.D.:
(a)
(b)
(c)
(d)
A: Ecstasy user
7
6
7
7
7
6
6
7
6
5
7
5
6.33
.78
B: Non-user
3
7
5
4
6
5
4
2
1
1
7
6
4.25
2.14
Pearson's correlation between A and B: r (10) = .16, p = .61.
Spearman's correlation between A and B: rs (12) = .12, p = .70.
Mann-Whitney test: U (12, 12) = 28, p = .009.
Wilcoxon test: z = 2.51, p = .01.
Conclusions:
(e) Ecstasy users' sensation-seeking scores are more variable than those of
non-users.
(f) Ecstasy users rate themselves to be significantly higher in sensationseeking than non-users.
(g) Ecstasy users rate themselves to be significantly lower in sensation-seeking
than non-users.
(h) There is no significant difference between Ecstasy users and non-users in
terms of sensation-seeking.
8
C8511 Research Skills in Psychology
3. A researcher is interested in the effects of watching TV on the number of
synapses in the human frontal cortex. Brain slices were obtained from 30
pensioners who had died in an old people's home: purely by chance, 10 of these
people had been incarcerated in a home that had Sky TV, 10 had been
imprisoned in a home that had access only to terrestrial TV stations, and 10 had
been condemned to eke out their miserable last days in a home that had no
access to TV at all. The number of synapses per millimetre of cortex was
recorded for each person. The data are not normally distributed.
Pensioner no.
1
2
3
4
5
6
7
8
9
10
Mean:
S.D.:
A: Sky TV
170
180
150
150
190
170
180
112
111
115
153.80
30.39
B: Terrestrial TV
190
130
120
180
190
110
120
160
120
150
147.00
31.29
C: No TV
114
95
68
79
100
115
98
77
82
111
93.00
16.72
Statistical tests:
(a) Kruskal-Wallis test: Χ2 (2) = 16.45, p < .001.
(b) Spearman's correlation between A and B: rs (10) = .17, .p = .65.
(c) Pearson's correlation between A and C: r (8) = .12, p = .74.
(d) Friedman's test: Χ2 (2) = 12.46, p = .002.
Conclusions:
(e) The more TV that is watched, the fewer the synapses in human
frontal cortex.
(f) Pensioners who have fewer synapses in their frontal cortex prefer to
watch Sky TV.
(g) There is no significant difference between the three groups of
pensioners in terms of how many synapses they had in their frontal cortex.
(h) The nature of the pensioners' television viewing experiences has
significantly affected the number of synapses in their frontal cortex.
9
C8511 Research Skills in Psychology
4. A researcher is interested in the effects of four different types of speed limit sign
on drivers' behaviour. At a known accident black spot, each of four different signs is
erected for one month. During that time, the number of drivers exceeding the speed
limit is recorded.
Type of sign
Sign 1
Sign 2
Sign 3
Sign 4
Number of drivers exceeding the speed limit
4000
3,420
2,221
6,544
Statistical tests:
(a) Pearson's correlation between sign and number of speeders: r (2) = .46,
p = .54
(b) Spearman's correlation between sign and number of speeders: rs (3)= .20,
p = .80
(c) Chi-square goodness of fit test: Χ2 (3) = 2462.68, p < .001.
(d) Wilcoxon test: z = 1.83, p = .07.
Conclusions:
(e) The type of sign significantly affects how many drivers speed past it.
(f) The type of sign has no effect on how many drivers speed past it.
(g) There is a significant correlation between the type of sign and drivers'
speeding behaviour.
(h) There is no significant correlation between the type of sign and drivers'
speeding behaviour.
10
C8511 Research Skills in Psychology
5. A researcher is interested in the effectiveness of two different methods of
punishing teenage children's antisocial behaviour. Method A consisted of locking
the child in a small dark room for ten minutes every time they behaved antisocially.
Method B involved depriving the child of their MP3 player for ten minutes. Each
child received a week of each treatment. (Treatment order was counterbalanced).
The dependent variable was the number of antisocial acts committed in the week
after each punishment regime had ended. The data lack homogeneity of variance.
Subject A: Number of anti-social acts
committed after being punished
by imprisonment
1
10
2
15
3
20
4
17
5
13
6
19
7
17
8
15
9
14
10
21
Mean: 16.10
S.D.:
3.38
B: Number of anti-social acts
committed after being
punished by loss of MP3
player
0
3
5
4
6
8
4
3
6
7
4.60
2.32
Statistical tests:
(a) Pearson's correlation between A and B: r (8) = .66, p = .04.
(b) Spearman's correlation between A and B: rho = .51, p = .14.
(c) Wilcoxon test: z = 2.81, p = .005.
(d) Mann-Whitney test: U (10,10) = 17, p = .02.
Conclusions:
(e) The two methods differ significantly in their effectiveness in preventing
antisocial behaviour by children.
(f) Children who behaved badly under method A also did so under method B.
(g) Depriving children of personal freedom causes them to miss their MP3 player.
(h) Children who are punished by having their MP3 player taken away, are more
likely to misbehave subsequently than children who are punished by having
their liberty curtailed.
11
C8511 Research Skills in Psychology
SECTION 5:
1. It is hypothesised that visualisation techniques combined with football
training might improve footballers' performance more than football training
alone. This was assessed by measuring the number of goals scored in a
season of training matches, after participants had either (a) trained for 5
hours a week on a running track and 5 hours a week in the gym; or (b) done
this training plus five hours a week of visualising themselves scoring goals.
The table below shows the number of goals that were scored by each player
in the following season, together with the means, standard deviations, and
the result of the Mann-Whitney test used to compare the scores.
Participant number
1
2
3
4
5
6
7
8
Mean (SD)
Training alone
3
9
14
17
12
11
19
11
12.00 (4.93)
Training + visualisation
9
7
6
15
5
6
12
13
9.12 (3.76)
U = 21 p = .25
(a) graph these data in a form appropriate for inclusion in a lab report (5 marks).
Draw your graph here:
C8511 Research Skills in Psychology
(b) Describe the data in a form appropriate for inclusion in the results section of a
lab report (5 marks).
Write your results section here
A Mann-Whitney test revealed that combining visualisation techniques and
football training did not improve footballers' performance more than football
training alone, U (8, 8) = 21.00, p > .05). Footballers in the visualisation plus
training condition scored a mean of 12.00 goals in a season (SD = 4.93),
whereas footballers in the training-only condition scored only 9.12 goals (SD
= 3.76).
[N.B. This is a one-tailed test - we were predicting that footballers given
visualisation plus training would be better at scoring goals than footballers
given only training, not just different. So if the test had been significant, we
would have had to conclude merely that visualisation plus training offered no
benefits over training alone].
C8511 Research Skills in Psychology
2. A researcher's hypothesis is that the ability to perform well on a computer
driving game is a good measure of a person's ability to drive fast on a real driving
track. The table below shows eight participants’ best scores in a racing game (a
higher score meaning that they performed better), and their average lap time at a
racetrack. Also shown is the value of the correlation coefficient r between the two
scores.
Participant
Racing game score
1
2
3
4
5
6
7
8
20
50
30
60
88
10
12
50
Racing track lap time
(seconds)
30
66
28
75
90
10
50
80
r = 0.87 p = .005
(a) Graph the data in a form appropriate for inclusion in a lab report (5 marks).
13
C8511 Research Skills in Psychology
(b) Describe the data in a form appropriate for inclusion in the results section of a
lab report (assuming no graph in the results section) (5 marks).
Write your results section here:
There was a strong positive correlation between participants' best scores on a
racing game and their average lap time at a race-track, r (6) = .87, p = .005. The
higher a participant's racing game score, the longer their lap time. These results
run contrary to the original hypothesis. Although the ability to perform well on a
computer driving game is a good measure of a person's ability to drive on a real
driving track, it is in the opposite direction to what was predicted originally: people
who perform well on the game actually perform worse (drive more slowly) on the
race track.
C8511 Research Skills in Psychology
Answer sheet for sections 1, 2, 3 and 4:
Section 1
Answer
Section 2
PART 1
Answer
Section 2
PART 2
Answer
Section 3
Answer
Q1
E
Q1
B
Q1
C
Q1
F
Q2
B
Q2
A
Q2
C
Q2
D
Q3
B
Q3
A
Q3
A
Q3
D
Q4
D
Q4
C
Q4
B
Q4
G
Q5
D
Q5
22.20
Q5
B
Q5
A
Q6
B
Q6
31.68
Q6
A
Q6
E
Q7
C
Q7
8.39
Q7
C
Q7
G
Q8
D
Q8
11.97
Q8
C
Q8
B
Q9
C
Q9
Q9
B
Q9
G
Q10
B
Q10
SEE
BOXPLOT
A
Q10
A
Q10
B
Section 4 answers
Q1
statistics: B
interpretation: H
Q2
statistics: C
interpretation: F
Q3
statistics: A
interpretation: H
Q4
statistics: C
interpretation: E
Q5
statistics: C
interpretation: E
End of paper