Page 1 of 19
Adventist University of the Philippines
College of Arts and Humanities
Psychology Department
PSYCHOLOGICAL STATISTICS
Laboratory Exercises
SY 2023-2024
RHALF JAYSON F. GUANCO, PhD, RPsy, RPm
Course Facilitator
Page 2 of 19
Lab #1 – Descriptive Statistics
PART 1 – MALE
Work these exercises using Excel, SPSS or Jamovi.
Students in my undergraduate psychological statistics class, First Semester, 2021, were asked to
rate how fearful they were of the course (psystatophobia), using a scale from 0 (absolutely no fear) to 10
(extreme sympathetic arousal and crippling emotions). Here are the data for the male students:
PsyStatopha
Frequency
5 1
7 2
10 1
Total 4
a. Gender = Male
For these 4 scores, compute the mean, median, mode, range, sample variance, and sample
standard deviation. Compare the mean to the median and then comment on the shape of the distribution.
Y (Y-M) (Y-M)2
5 -2.25 5.0625
7 -0.25 .0625
7 -0.25 .0625
10 2.75 7.5625
LEARNING POINT: WHAT IS YOUR ANSWER?:
1. Sum =
2. Mean =
3. Median =
4. Mode =
5. Sum of squared deviations from the mean =
6. Sample variance =
7. Sample standard deviation =
8. Comment on the shape of the distribution =
PART 1 – FEMALE
Here are the data for the female students in that same class:
Page 3 of 19
PsyStatopha
Frequency
5 3
6 4
7 2
8 3
9 2
Total 14
a. Gender = Female
For these 14 scores, compute the mean, median, mode, range, sample variance, and sample
standard deviation.
Y (Y-M) (Y-M)2
1 5 -1.786 3.190
2 5 -1.786 3.190
3 5 -1.786 3.190
4 6 -0.786 .618
5 6 -0.786 .618
6 6 -0.786 .618
7 6 -0.786 .618
8 7 0.21 .044
9 7 0.21 .044
10 8 1.214 1.474
11 8 1.214 1.474
12 8 1.214 1.474
13 9 2.214 4.902
14 9 2.214 4.902
LEARNING POINT: WHAT IS YOUR ANSWER?:
9. Sum =
10. Mean =
11. Median =
12. Mode =
13. Sum of squared deviations from the mean =
14. Sample variance =
15. Sample standard deviation =
16. Comment on the shape of the distribution =
Page 4 of 19
Lab #2 – Linear Correlation Analysis
We are interested in relating quality of teaching to quality of research by AUP professors. Sample
includes 20 CAH teachers who have been evaluated over a ten-year period. These ratings are averaged to
create an overall quality rating as an instructor (rating_1) and the overall quality of the course (rating_2)
for each professor. We also obtain the number of articles published in the ten year period (num_pub) and
the number of times these articles have been cited (cites).
SPSS Instruction: Click AnalyzeCorrelate Bivariate. Move all variables over into the Variables box.
Makes sure Pearson, Two-tailed, and Flag significant are checked. Click Options check Means and
Standard Deviations. Click OK.
Overall Quality Overall
Teache Number of Number of times cited by
Rating as Instructor Course
r Publications other authors
(rating_1) Quality
1 3 5 10 11
2 4 5 11 2
3 2 4 10 3
4 5 5 10 4
5 5 4 4 5
6 5 5 8 3
7 4 5 8 8
8 3 4 8 9
9 4 5 8 45
10 5 4 8 2
11 5 5 9 3
12 3 4 7 21
13 4 5 7 2
14 2 4 7 3
15 4 5 7 44
16 3 5 8 3
17 2 4 5 2
Page 5 of 19
18 4 4 5 2
19 5 4 5 2
20 5 5 5 10
21 5 4 5 11
22 5 5 7 11
23 5 4 9 34
24 5 5 10 11
25 5 3 10 12
26 5 3 10 34
27 5 3 11 7
28 5 4 8 6
29 5 5 10 11
30 5 5 10 11
LEARNING POINT:
WHAT IS THE ANSWER?:
PART 1:
Mean Standard Deviation
1. Overall Quality Rating
as an Instructor
2. Overall Course Quality
3. Number of Publications
4. Number of times cited
by other authors
PART 2:
PROVIDE YOUR ANSWERS FOR THE FOLLOWING QUESTIONS:
a) What is the null hypothesis between rating_1 and rating_2?
b) What is the p-value for the correlation between rating_1 and rating_2?
c) Is the relationship between the number of citations and number of publications significant?
d) Is the relationship between number of citations and instructor quality significant?
e) Is the relationship between the number of articles published and the overall quality of the
instructor significant?
Page 6 of 19
Lab #3 – Multiple Regression
Page 7 of 19
Achievement Ability Motivation Interest
1 2 1 2
2 2 3 1
2 2 3 3
3 4 3 2
3 3 4 3
4 3 2 2
1 2 1 2
2 2 3 1
2 2 3 3
3 4 3 2
3 3 4 3
4 3 2 2
1 2 1 2
2 2 3 1
2 2 3 3
3 4 3 2
3 3 4 3
4 3 2 2
1 2 1 2
2 2 3 1
2 2 3 3
3 4 3 2
3 3 4 3
4 3 2 2
1 2 1 2
2 2 3 1
2 2 3 3
3 4 3 2
3 3 4 3
4 3 2 2
1 2 1 2
2 2 3 1
2 2 3 3
3 4 3 2
3 3 4 3
4 3 2 2
Problem: Dr. Marquez, a professor in AUP Department of Psychology, wanted to understand the best
predictors of school achievement. How will you help Dr. Marquez analyse the given data?
LEARNING POINT:
PROVIDE YOUR ANSWERS TO THE FOLLOWING QUESTIONS:
Page 8 of 19
Part 1:
Descriptive Statistics
Mean Std. Deviation N
Achievement
Ability
Motivation
Interest
Part 2:
1. What is your null hypothesis?
2. How many predictors entered the stepwise multiple regression?
3. What is/are the best predictor/s of school achievement according to the data?
4. What is the variance of the specific predictor/s of school achievement?
5. What is the direction of relationship between ability and school achievement?
Lab #4 – Independent Sample T-test/Uncorrelated Sample T-test
Page 9 of 19
The t-test is the name of a statistical technique which examines whether the two groups of scores have
significantly different means – in other words, how likely is it that there could be a difference between the
two groups as big as the one obtained if there is no difference in reality in the population?
The data are from an imaginary study involving the emotionality of children from lone-parent and two-
parent families. The independent variable is family type which has two levels – the lone-parent type and
the two-parent type. The dependent variable is emotionality on a standard psychological measure – the
higher the score on this test, the more emotional is the child. The data are listed in Table 14.8.
PROBLEM: Is emotionality was found to be higher for the children of two-parent families?
SPSS Data
Family Emotion
2 12
2 18
2 14
2 10
2 19
2 8
2 15
2 11
2 10
2 13
2 15
2 16
1 6
1 9
1 4
1 13
1 14
1 9
1 8
1 12
1 11
1 9
Page 10 of 19
LEARNING POINT:
PART 1:
Group Statistics
Family N Mean Std. Deviation Std. Error
Mean
1.0
Emotion
2.0
PART 2:
ANSWER THE FOLLOWING QUESTIONS:
1. What is your null hypothesis?
2. What is your alternative hypothesis?
3. What is the t-score based from the SPSS output?
4. What is the P-value?
5. Is the t-score statistically significant?
6. What kind of family has greater emotionality?
Page 11 of 19
Lab #5 – Paired Sample t-test/Related t-test/Correlated t-test
In paired sample t-test or related measures designs, or correlated scores designs, the researcher wishes to
know whether the means of the two conditions differ from each other.
The data are taken from an imaginary study which looked at the relationship between the age of an infant
and the amount of eye contact it makes with its mother. The infants were six months old and nine months
old at the time of testing – age is the independent variable. The dependent variable is the number of one-
minute segments during which the infant made any eye contact with its mother over a ten-minute session.
The null hypothesis is that there is no relation between age and eye contact. The data are given in the
Table, which includes the difference between the six-month and nine-month scores. Is the difference
statistically significant?
Data
6 Months (X1) 9 months (X2)
Baby 1 3 7
Baby 2 5 6
Baby 3 5 3
Baby 4 4 8
Baby 5 3 5
Baby 6 7 9
Baby 7 8 7
Baby 8 7 9
Page 12 of 19
LEARNING POINT:
Part 1:
Paired Samples Statistics
Mean N Std. Deviation Std. Error
Mean
@6MonthsX1
Pair 1
@9monthsX2
Part 2:
Answer the following questions:
1. Looking at the mean score, is eye contact slightly higher at nine than at six months?
2. Is the difference statistically significant?
3. What is your t-score based from the SPSS output?
4. What is the 95% confidence interval of difference in the lower bound and upper bound?
5. Will you confirm the null hypothesis stating that there is no relationship between age and eye
contact?
Page 13 of 19
Lab #6 – One Way ANOVA
The analysis of variance (ANOVA) can do this but in addition can extend the comparison to three or
more groups of scores. Analysis of variance takes many forms but is primarily used to analyse the results
of experiments. This can be used whenever we wish to compare two or more groups in terms of their
mean scores on a dependent variable. The scores must be independent (uncorrelated or unrelated). In
other words, each respondent contributes just one score to the statistical analysis. The analysis of variance
with just two conditions or sets of scores is relatively easy to interpret. You merely have to examine the
difference between the means of the two conditions. It is not so easy where you have three or more
groups. Your analysis may not be complete until you have employed a multiple comparisons procedure
using Scheffé test or Tukey test.
Dependent: Depression
Group 1 Group 2 Group 3
Hormone Hormone Placebo
1 2 Control
9 4 3
12 2 6
8 5 3
SPSS Data
Conditio
n Emotion
1 9
1 12
1 8
2 4
2 2
2 5
3 3
3 6
3 3
PROBLEM: Roger wanted to understand if the treatment conditions have a significant effect on the
depressive symptoms of adolescents. Please calculate the F-ratio and discover if there is a significant
effect of the independent variable drug treatment on the dependent variable depression among
adolescents?
Page 14 of 19
Part 1:
Descriptives
Emotion
N Mean Std. Deviation Std. Error
1.0
2.0
3.0
Total
Part 2:
Answer the following questions:
1. What is the F-ratio?
2. Is the F-ratio statistically significant at the .05 level?
3. What is the p-value?
4. Which group has greater depression scores?
5. Is the Tukey HSD significant at the .05 level?
Page 15 of 19
Lab #7 –Two-way or factorial ANOVA for unrelated/ uncorrelated scores
The one-way analysis of variance deals with a single independent variable which can have two or more
levels. However, analysis of variance copes with several independent variables in a research design.
These are known as multi-factorial ANOVAs. The number of ‘ways’ is the number of independent
variables. of variance There is only one dependent variable no matter how many ‘ways’ in each analysis.
If you have two or more dependent variables, each of these will normally entail a separate analysis of
variance (MANOVA).
We will attempt to analyse the sleep and alcohol experiment. It is described as a 2 x 3 analysis of variance
because one independent variable has two values and the other has three values (Table 25.11). The effect
of the independent variables alcohol and sleep deprivation on the dependent variable of people’s
comprehension of complex video material expressed in terms of the number of mistakes made on a test of
understanding of the video material will be explored. In a sense, one could regard this experiment
conceptually as two separate experiments, one studying the effects of sleep deprivation and the other
studying the effects of alcohol. The effects of each of the two independent variables are called the main
effects. Additionally, the analysis normally looks for interactions which are basically findings that cannot
be explained on the basis of the distinctive effects of alcohol level and sleep deprivation acting separately.
Interactions are about the effects of specific combinations of variables. The interaction consists of any
variation in the scores which is left after we have taken away the ‘error’ and main effects for the gender
and iron supplements sub-experiments.
Page 16 of 19
SPSS Data
Alcohol Sleep Errors
1 1 16
1 1 12
1 1 17
1 2 18
1 2 16
1 2 25
1 3 22
1 3 24
1 3 32
2 1 11
2 1 9
2 1 12
2 2 13
2 2 8
2 2 11
2 3 12
2 3 14
2 3 12
LEARNING POINT:
Part 1: Estimated Marginal Means
1. Alcohol
Dependent Variable: Errors
Alcohol Mean Std. Error 95% Confidence Interval
Lower Bound Upper Bound
1.0
2.0
2. Sleep
Dependent Variable: Errors
Sleep Mean Std. Error 95% Confidence Interval
Lower Bound Upper Bound
4 hrs
12 hrs
24 hrs
Page 17 of 19
Part 2:
Answer the following questions:
1. What is the F-ratio in sleep?
2. Is the F-ratio in sleep statistically significant at the .05 level?
3. What is the F-ratio in alcohol?
4. Is the F-ratio in alcohol statistically significant at the .05 level?
5. What is the p-value in alcohol?
6. What is the p-value in sleep?
7. Is the interaction in sleep and alcohol significant based on the result?
8. Four hours of sleep deprivation gave an average of how many errors?
9. Consuming alcohol led to an average of how many errors?
10. Does Levene’s test show homogeneity in the variances?
Page 18 of 19
Lab #8 – Reliability Analysis
Statistics plays a critical role in determining the adequacy of psychological scales and measures.
Typically, but not always, in psychology, measures are composed of several distinct components that are
added together to yield a total score on the measure. Thus, many attitude and personality tests are
comprised of a large number of questionnaire items that are aggregated to produce a total score on some
aspect of attitude or personality. Internal consistency is the extent to which all of the items constituting a
measure are measuring much the same thing. If they are measuring similar things, each item should
correlate with the other items in the measure. It is generally accepted that a value of alpha of about .7 or
larger indicates that a scale has satisfactory reliability.
SPSS DATA: COVID-19 Vaccine Hesitancy Questionnaire (6-point likert scale)
Person Item 1 Item 2 Item 3 Item 4
1 1 3 5 6
2 2 1 1 2
3 1 1 1 1
4 5 2 4 2
Page 19 of 19
5 6 4 3 2
6 5 4 5 6
7 4 5 3 2
8 2 1 2 1
9 1 2 1 1
10 1 1 2 2
PART 1:
Item-Total Statistics
Scale Mean if Scale Variance Corrected Item- Squared Cronbach's
Item Deleted if Item Deleted Total Correlation Multiple Alpha if Item
Correlation Deleted
Item1 7.600 18.933 ? .626 ?
Item2 8.000 19.556 ? .563 ?
Item3 7.700 17.789 ? .843 ?
Item4 7.900 18.767 ? .801 ?
PART 2:
Answer the Following Questions:
1. What is the Cronbach’s Alpha of the COVID-19 Vaccine Hesitancy Questionnaire?
2. What is the degree of internal consistency of the COVID-19 Vaccine Hesitancy Questionnaire?
3. Is the COVID-19 Vaccine Hesitancy Questionnaire reliable?
