Quantitative Methods Coursera Quiz Answers

Quantitative Methods. In this post you will get Quantitative Methods Quiz Answers | 100% Correct Answers.

Quantitative Methods

N.B. We attempted our best to keep this site refreshed for our clients for nothing. You can likewise contribute by refreshing new inquiries or existing inquiry answer(s). There are numerous inquiries on our site, it is difficult for us to check them consistently. It will be extraordinary on the off chance that you can assist us with updating the site. Just let us know if you find any new questions through mail or comment . We will attempt to refresh the inquiry/answer ASAP.

Use “Ctrl+F” To Find Any Questions Answer. & For Mobile User You Just Need To Click On Three dots In Your Browser & You Will Get A “Find” Option There. Use These Option to Get Any Random Questions Answer.

Week- 1

Origins

1. Which example fits best with the concept of systematic observation?

Observing every fourth person to enter the mall
Observing everything you do in one day
Asking every fourth person to enter the mall about their favorite sport and recording this.

2. A hypothesis must be:

testable

observed
proven correct

3. What is the primary difference between a scientific theory and a scientific law?

A theory describes a pattern and a scientific law explains why something happens
A theory explains why something happens and a law describes a pattern

A theory does not necessarily have a large body of supporting data

4. In contrast to Plato, Aristotle asserts that:

sensory experience is prone to errors
only knowledge obtained through reasoning can lead to the truth
the physical world around us does provide knowledge

5. All swans that have been observed are white colored swans. Therefore one can conclude that all swans are white.

This is an argument based on a false premise

This is a form of inductive reasoning
This is a form of deductive reasoning

6. According to logical positivism, the sentence “God exists” is meaningful only if:

1 point

the sentence has meaning for the person who utters it
it is true by definition or can be verified through observation

it is believed to be true, even if we don’t know which observations can be used for verification

7. A student wants to do a research project on a mother’s love for her child. How would a radical empiricist react to this idea?

He or she would advise the student to develop a theory of love specific to this phenomena, i.e. the love of a mother for her child
A mother’s love for her child can only be understood by a fellow mother and therefore this project should not be undertaken by someone who hasn’t yet started a family
A mother’s love for her child cannot be subject to scientific analysis unless it can be shown to have a material, physical basis (e.g. brain activity associated with love)

8. The position that abstract concepts are merely words and that there is no independently accessible thing constituting the meaning of a word is known as

nominalism

idealism
realism

9. Which of these statements is true?

Positivists and interpretivists agree that science is empirical (studies produce data)
Constructivism and interpretivism are linked with qualitative data

both are true

10. If you prepared a study on the effects of text-messaging rather than talking on the phone on the quality of friendships, you would be conducting

fundamental and universalistic research
fundamental and particularistic research
applied research

Week- 2

Scientific Method

1. If in the testing phase our predictions are confirmed by the data, does this mean we have definitively proven the hypothesis?

It depends

2. If the data support our predictions, this leads us to conclude that

We need to develop new predictions that can be disconfirmed
Our predictions are confirmed, but we cannot say anything about the hypothesis
The hypothesis is provisionally supported

3. Heavey, Russell and Noelle (2012, p. 763) stated that: “How you feel may influence your facial expression, may be influenced by your facial expression, may be otherwise related to your facial expression, or none of the above, so a scientist’s observation of your facial expression (a third-person act) cannot be substituted for your own direct apprehension of your feelings (a first-person act)”. Here, the authors doubt the

Construct validity of studies using facial expressions

External validity of studies using facial expressions
Internal validity of studies using facial expressions

4. By combining data from various publicly available sources Harvard Law School student Tyler Vigen has found out that there’s a correlation between the number of movies Nicolas Cage appears in each year and the number of people who drown in their swimming-pools. The MOST logical conclusion is that

Correlation doesn’t imply causation
No causal inference can be made from observational data

Less people will drown in their swimming pool once Cage retires

5. Suppose a researcher hypothesizes a causal relationship between breastfeeding and children’s health at age 4 years exists and investigates this hypothesis by measuring health characteristics of a group of four year olds and by asking their mothers whether the child was breastfed or not. Suppose a relation is indeed found. The most obvious threat to internal validity in this situation is:

Selection effect
Maturation effect
Selection by maturation effect

6. Testing effects due to practice/learning from exposure to repeated testing can be eliminated by

Randomization

Including groups that are exposed to a pre-test and groups that aren’t
Using tests with high construct validity

7. In a famous study by psychologist John Bargh subjects had to create a sentence from scrambled words. When these words related to being old, participants walked more slowly when they left the laboratory. In a recent replication study, Doyen, Klein, Pichon and Cleeremans (2012) found that participants walked more slowly only when they were tested by experimenters who expected this effect. This seems to point to

The impact of demand characteristics
An experimenter expectancy effect

The need to misguide participants

8. A researcher is interested in the effect of the perceived freedom of speech on social cohesion in small communities. She investigates small communities in China – which has a low perceived freedom of speech – and Malaysia – which has a relatively high perceived freedom of speech. The study runs for ten years. The study started two years before China relaxed its policy of restricting couples to have only one child. This policy change represents a

History threat to internal validity
Mortality threat to internal validity
Temporal ambiguity threat to internal validity

9. Willingness to take risks is assumed to be an important component of entrepreneurship. We hypothesize that willingness to take risks causes people to start and run a business. Here,

Willingness to take risks is the dependent variable

Entrepeneurship is the dependent variable
Willingness to take risks is the outcome variable

10. Suppose an observational study indicates a positive relation between weekly ice cream consumption and murder rates. Which of the following are possible lurking variables?

Weapon possession and population size
Season of the year and heat waves

Neither of the two options

Peer-graded Assignment: Scientific Method – Writing Assignment (Creative)

Project Title *
Give your project a descriptive title

Scientific Method – Writing Assignment (Creative)

Click here to download answer file

Week- 3

Research Designs

1. The main advantage of randomized controlled trials (RCT) is that

they provide the best support for causality

treatments can be compared against each other and a control group
they are rigorous and objective

2. A researcher presents both male and female managers from several companies with application materials (CV and application letter) from a student applying for a job opening. Half the managers were given the application with a male name attached, and half were given the exact same application with a female name attached. Results showed that managers were less likely to offer the female applicant a job (gender bias). This corresponds to

an interaction effect between the applicant’s and the manager’s gender
a main effect of the manager’s gender

a main effect of the applicant’s gender

3. Which of the following illustrates the use of a within-subjects design?

One group of students is given a compliment before an exam and a second group is criticized before taking the exam.
Students of three different age levels are given the same test.
Students take two comparable tests. They take the first without preparation; before the second test they meditate for ten minutes.

4. An educational psychologist examined whether students will perform best if online education is combined with classroom learning. Students were randomly assigned to three conditions. In this study, these three conditions would be

online education, classroom learning and a combination of both

student grades, experimental condition and course content
online education, classroom learning and highly motivated vs. poorly motivated students

5. Those in favor of field experiments argue that this type of research is perhaps less tightly controlled, but that more realism implies greater relevance. They also question the generalizability of laboratory experiments. This critique can be summarized as

doubt on the internal validity of laboratory experiments
concerns about self-selection of participants into lab experiments

doubt on the ecological validity of laboratory experiments

6. A researcher notices that highly educated participants are more likely to refuse an unpleasant experimental treatment after being randomly assigned to the treatment condition. Therefore, he is concerned about the comparability of the treatment and control group. In this case, the researcher should BEST

rerun the study with some form of restricted randomization
do a randomization check
stop worrying because randomization never fails

7. Which of the following designs allows the researcher to compare the size of the increase or decrease in scores in the experimental and control condition?

a simple within subjects design

the two-group pre-test/post-test design
the two-group post-test only randomized experiment

8. If participants are not measured twice (e.g. only a post-test)

testing (sensitization) is not an issue
regression to the mean and testing (reactivity) are not issues

regression to the mean is not an issue

9. Cameron, Erkal, Gangadharan, and Meng (2013) studied the causal relationship between growing up without siblings and altruism by comparing a group of participants born just before and just after the introduction of China’s One-Child Policy in 1979. This is an example of

a Randomized Controlled Trial (RCT)
a ‘natural’ experiment
an experimental study

10. A cohort design is a panel study

where the same individuals respond to a survey at several points in time
where the same individuals are interviewed at several points in time
where a group of individuals with a common characteristic are followed up longitudinally

11. Mincome was an experimental Canadian basic income project that was held in Dauphin, Manitoba during the 1970s. The project allowed every family in this town to receive a minimum cash benefit, thereby essentially eliminating poverty. Forget (2013) has evaluated the long-term effect of this guaranteed income program on people’s health (hospitalization rates) by comparing residents from Dauphin with a matched comparison group of residents from similar areas. This study can be characterized as

a summative evaluation study with a quasi-experimental design
a formative evaluation study with a quasi-experimental design
a summative evaluation study with an experimental design

Peer-graded Assignment: Research Designs – Writing Assignment (Evaluative)

Project Title *
Give your project a descriptive title

Research Designs – Writing Assignment (Evaluative)

Click here to download the answer file

Week- 4

Measurement

1. Operationalization refers to

an attribute, characteristic, or behavior that is in principle measurable
the specification of an abstract concept into a measurement procedure
any observation that can take different values

2. Measurement is

the way in which variables are categorized
the numerical representation of empirical relations
assigning numbers

3. A researcher asks people to name their favorite music genre (rock, rap, etc…). This question measures music genre preference at

the interval level
the ordinal level
the nominal level

4. Markowitz and Hancock (2014) compared publications of the social psychologist Diederik Stapel in which proof of fraud was established to articles by the same author which showed no evidence of fraud. One of the things these researchers did was to count the number of words related to emotional actions, states and processes in the two types of publications. Such a word frequency variable is

1 point

a continuous ratio variable
a discrete ratio variable
a categorical variable

5. I. measures of the same trait using different methods show agreement

II. different traits assessed by the same method do not agree

I indicates convergent validity, II indicates discriminant validity
I indicates convergent validity, II indicates criterion validity
I indicates discriminant validity, II indicates convergent validity

6. The degree of agreement between raters when using a particular rating instrument is called

intra-observer consistency
rater reliability
inter-rater reliability

7. “38% of the managers would not hire a mother for any role in their organization”. This statement MOST likely implies that a sample of managers has

filled out a questionnaire on their attitudes towards working mums
filled out a survey including a question if they would recruit a mum for a position in their business
taken a test on their knowledge of employee rights

8. Likert items should be monotone, meaning that respondents

cannot be unsure about their response to the item
are consistently more likely to agree with the item if they possess the property to a greater degree
cannot have both negative and positive reactions to the item

9. Consistently concealing your true opinion by using the midpoint of the scale

1 point

introduces a generosity error and is called bias towards the middle
introduces random error and is called acquiescence
introduces systematic error and is called bias towards the middle

10. Hair cortisol (a hormone made by the adrenal glands) levels are being used as a chronic stress measure. This illustrate the use of

physical measures
trace measures
observational measures

Peer-graded Assignment: Measurement – Writing Assignment (Creative)

Project Title *
Give your project a descriptive title

Measurement – Writing Assignment (Creative)

Click here to download the answer file

week- 5

Sampling

1. In directed imagery tasks participants listen to a particular scenario and are instructed to picture the situation, the people, and the events as clearly and as vividly as they can. A researcher could ask participants how realistic they found such scenarios in order to check

the external validity of the task
whether the use of an experimental setting that does not mirror reality precisely was justified
whether reactivity to the laboratory setting occurred

2. Strata are

distinct subsets in the population defined by a stratification variable
all the elements in a population that can be individually identified
all the elements in a sampling frame

3. Opinion polls attempt to measure public opinion. Poll results can accurately reflect the attitudes in the population if

the sample is large enough and based on self-selection
the poll is based on probability sampling
the sample is large enough and consists of volunteer respondents

4. Systematic sampling may be used instead of simple random sampling if

the sample size is large
we are unaware of a pattern in the list of elements
the list of elements is ordered randomly

5. The loss in precision is usually far outweighed by the reduced cost. This applies to

stratified sampling
random sampling
cluster sampling

6. A researcher approaches the first visitor entering a mall and asks if he or she is willing to participate in a study on aging and depression. He approaches the next visitor, followed by the next, and so on. This is

convenience sampling
quota sampling
purposive sampling

7. As the size of a random sample increases, the amount of sampling error

remains the same
decreases
increases

8. Using the same sample frame, a random sample of 500 voters were interviewed by telephone and a second random sample of 500 voters answered the same set of questions by filling out a web survey. A systematic difference in polls results can be due to

an incomplete or inaccurate sampling frame
differences in non-sampling error between the two samples
the amount of sampling error between the two samples

9. To decide the optimal sample size, one needs to consider

the variability in the population
the variability in the population and the margin of error that one is willing to accept
the size of the population

Peer-graded Assignment: Sampling – Writing assignment (Evaluative)

Project Title *
Give your project a descriptive title

Sampling – Writing assignment (Evaluative)

Click here to download the answer file

Week- 6

Practice, Ethics & Integrity

1. The method section of a research report

summarizes the data collection procedure and the planned statistical analyses
provides information on the measurement materials
describes in full every detail of the research design and analyses

2. In the codebook the researcher

provides all statistical and data manipulation information
specifies the programs that will recognize the data file format
specifies what variables were entered into the data file and defines the numeric codes for each variable

3. Research integrity encompasses

adherence to rules made by the scientific community
good documentation and researchers’ striving for excellence
protecting the welfare of participants but also the integrity of the scientific process

4. A recent study in which Facebook users’ moods were manipulated has raised ethical concerns. In defense of the researchers someone states that the effect of the manipulation was minimal and that therefore very little harm was done. This statement pertains to

the ethical principle of justice
the ethical principle of beneficence
the ethical principle of respect

5. A researcher continues to believe in an effect regardless of strong evidence to the contrary. In addition, he refuses to respond to critique. This is an example of

a violation of the principle of objectivity
self-plagiarism
a conflict of interests

6. Suppose you have conducted an experiment on 20 subjects. The results are disappointing in that the hypothesized difference between conditions is not significant (a p value of .08). Given this unfavorable result you decide to run 20 more subjects. This is a questionable research practice because

the decision to collect more data should not be conditional upon obtaining a (non-) significant finding
the hypothesized difference does not follow from a substantial theory
you should have used a power calculation to decide on the number of participants needed

7. Published articles should ideally be

chosen only if they show confirmatory results
subjected to peer review
revised multiple times

8. Proposed solutions to publication bias include

publishing in open access journals
preregistration and pre-acceptance of the hypothesis and research setup
making the data and analyses publicly available

Peer-graded Assignment: Practice, Ethics & Integrity – Writing assignment (Creative)

Project Title *
Give your project a descriptive title

Practice, Ethics & Integrity – Writing assignment (Creative)

Click here to download the answer file

Week- 7

Practice Exam 1 – immediate feedback

1. This is a practice exam, to prepare yourself for the final exam. You can take this exam as many times as you like, the score will not count towards your final grade. To pass the exam you need a score of 70% (21 out of 30 questions correct).

In the real exam, please make sure your internet connection is good and don’t forget to save your answers from time to time. You can take the final exam only once every 30 days, so make sure you are well prepared!

This practice final exam consists of 30 multiple-choice questions about the research described below. Each question has three answer options, of which only one is correct or most appropriate. If you feel a correct answer option is not provided, then choose the best fitting option.

Please follow the honor code and do not communicate or confer with others taking this exam.

Flipping the classroom
A lecturer at the University of Amsterdam (UvA) wants to investigate the effectiveness of an instructional method called ‘Flipping the Classroom’ (FtC). FtC means that students prepare for class by watching short video lectures online. Subsequently, in the face-to-face, live lectures the subject matter is treated more in-depth, by using interactive assignments, so students will learn more.

The teacher investigates this method with premaster students and regular bachelor students studying Communication Science, who are taking the course Statistics-II together. Under the guise of extra support, four days before each lecture, the premaster students get access to the video recordings of last year’s lecture. They are asked to study these recordings carefully. In the live lecture (for all students) the lecturer only explains the most difficult material, and leaves a lot of time for questions. After this lecture, the premaster students don’t have any access to the recordings anymore. The regular students get access to the recording of the live lecture they attended during four days after the lecture. At the end of the course, all students take the same exam at the same time.

The effectiveness of the ‘standard’ versus the FtC instructional method will be investigated by comparing exam scores (study performance, score range: 1 – 10, interval variable) of the two groups. During the exam a questionnaire is used to measure self-confidence and study motivation (both interval variables with a score range of 10 – 50) and age, gender and the math score obtained in secondary school (on final exams).

Disclaimer: this research is completely made up!

Question 1:
This research is

correlational
experimental
quasi-experimental

2. A manipulation check could consist of checking if

the lecture videos were indeed studied
the number of men and women in each group was about the same
the mean self-confidence scores were about the same in the two groups

3. The independent variable is

study performance
instructional method
type of student (premaster/regular)

4. The most obvious threat to internal validity is

maturation
selection
instrumentation

5. If self-confidence is significantly lower for premaster students, then self-confidence is a

constant
confounder
independent variable

6. The dependent variable is

study performance
self-confidence
instructional method

7. This research has the following design:

static group comparison
randomized pretest posttest design
pretest posttest non-equivalent control group

8. The external validity of this study benefits from the fact that

all students study Communication Science
both male and female students participated
Neither

9. The sample is (most likely) a

quota sample
purposive sample
convenience sample

10. Suppose the effect of the instructional method and gender on study performance was investigated factorially, then how many main effects can be investigated?

11. If a researcher maintains that the not-directly observable trait of study motivation can be useful in scientific claims, then this researcher is not a

logical-positivist (like Schlick)
scientific realist (like Galileo)
empirical constructivist (like Van Fraassen)

12. Suppose that FtC does not result in better study performance, but does result in higher study motivation. As a consequence, the researcher changes the research question and hypothesis and presents the study as a study on the effect of FtC on study motivation. This is called

harking
p-hacking
cherry picking

13. This study has the following design:

within
between
within and between

14. The only threat to internal validity which could not provide an alternative explanation for the expected results in this study is

dropout
history
testing (sensitization)

15. A control variable in this study is

study performance
study motivation
instructional method

16. The ecological validity in this study is fairly good, because it was performed

on actual students
in a natural educational setting
both

17. A randomization-check could consist of checking if

the video lectures were really studied afterwards
study performance on the exam was about the same in the two groups
mean age in the two groups was approximately the same

18. Suppose that study performance is mainly determined by reading skill instead of understanding of the course material. This is bad for the

internal validity
construct validity
both

19. Instructional method is a

control variable
experimental variable
individual differences variable

20. In this study random sampling can only be carried out in practice when the population exists of

students
people who follow an education
UvA-students who are enrolled in 2014-2015

21. Considering the benefits (knowledge about the effectiveness of FtC) and disadvantages (possible lowering of study performance of one group of students) falls under the ethical aspect of

respect
beneficence
justice

22. If a researcher holds that it is impossible to know or measure how much self-confidence someone really has, then this is an objection of

an ontological nature
an epistemological nature
neither

23. a. ‘Studying material beforehand will lead to better study performance’

b. ‘My live lectures seem more useful when students are well prepared’

c. The mean result for Statistics-II will be higher for students who were instructed via FtC, than the mean of students who received regular instruction’

The three statements above consecutively belong the following phases of the empirical cycle:

deduction – induction – observation
deduction – observation – induction
induction – observation – deduction

24. If a student responds with ‘totally disagree’ to all items on the study motivation-scale, not considering the content of the items, we call this

acquiescence
social desirability bias
‘bad participant’-behavior

25. Suppose that the research hypothesis is confirmed by the results. Our confidence in the effectiveness of FtC is strengthened most by

replication
peer-review
meta-analysis

26. The researcher wants to know whether students’ motivation is measured validly. The scores on the study motivation scale are compared with the scores on the Amsterdam Study Motivation Scale (ASMS), a widely used tool during enrollment for the study of all students. The correlation between study motivation measured in the present study and the ASMS-score concerns

predictive validity
‘concurrent’ validity
convergent validity

27. Self-confidence is a

formative variable
experimental variable
individual-differences variable

28. The measurement level of the variable instructional method is

interval
ordinal
nominal

29. Suppose the researcher finds the following descriptive statistics for the variable study motivation:

Descriptive Statistic Value
number of participants 126
number of missing values 0
minimum value -1
maximum value 50
mean 30.7
standard deviation 12.3
The most probable error is

a data-entry error
a computational error
misspecification of missing values

30. Suppose we find a mean study performance score of 6.28 (84 students, sd = 0.85) in the regular group and a mean of 6.61 in the FtC group (42 students, sd = 1.66). A higher score indicates a better performance. If you consider only the direction of the difference between the groups (don’t worry about the size or significance of the difference) then the results

cannot be said to agree or disagree with the expectations
agree with the researcher’s expectations
disagree with the researcher’s expectations

Practice Exam 2 – feedback in screencasts

1. The described research study is

correlational
experimental
quasi-experimental

2. The lecturer could have performed a manipulation-check by checking if

the students opened and read the emails
engagement was the same between groups at the end of the course
engagement was the same between groups at the beginning of the course

3. The independent variable is

engagement
type of feedback
type of student (premaster/bachelor)

4. The research design aims to prevent a threat to internal validity caused by

maturation
selection
both

5. Suppose the engagement questionnaire is very unreliable. As a result, an estimate of the following type of validity will be low

construct validity
ecological validity
confirmative validity

6. The dependent variable is

engagement
type of feedback
type of student (premaster/bachelor)

7. This research has the following design

randomized two group design
randomized pretest posttest design
pretest posttest non-equivalent control group design

8. The external validity could have been improved by using

random multi-stage cluster sampling
stratified quota sampling
neither

9. If the sample would have been twice as large, then the margin of error would have been

larger
smaller
unaffected

10. If the lecturer does not document the study in enough detail, then this compromizes

transparency
logical consistency
empirical testability

11. The lecturer holds that the property engagement really exists, independent of human thought, and that knowledge about students’ engagement is best acquired through measurement, for example by using a questionnaire. The lecturer is not

a rationalist
an idealist
both

12. Suppose the expected effect occurs only for premaster students. The lecturer reports the result of this group of participants alone. We call this

harking
data snooping
cherry picking

13. Suppose the lecturer decides to add the variable sex to the described research design as an independent variable. The design is then called

factorial
within-subjects
within-between subjects

14. Possible threats to internal validity, against which the described research design does not protect, are

mortality
history
both

15. Suppose that in the population of women, the variation in engagement scores is greater than in the population of men. Suppose we take a sample of men and a sample of women of equal size. Compared with the men, the precision of the estimation of mean engagement for women is expected to be

greater
smaller
the same

16. The lecturer could have approached the research question qualitatively by assessing engagement using

a structured interview
an open interview
neither

17. The lecturer could have performed a randomization-check by checking if

the comparative feedback was accurate
engagement was the same between groups at the end of the course
engagement was the same between groups at the beginning of the course

18. Suppose the exam grade does not give a good indication of knowledge of statistics. This is firstly a problem for the

external validity of the study
construct validity of the exam
internal validity of the research hypothesis

19. In fundamental research the most important type of validity is

internal validity
external validity
ecological validity

20. The most obvious threat to external validity in this study is

history
selection
reactivity (setting)

21. What ethical aspect is definitely violated in this study?

justice
respect
beneficence

22. Suppose the lecturer does not find the expected result. She decides not to reject the hypothesis yet, but to reject the assumption of valid and reliable measurement of engagement instead. This approach was critically discussed by

Kuhn
Quine
Popper

23. The choice to measure engagement with a questionnaire (instead of, for example, by using observation) is associated with the following phase in the empirical cycle

testing
induction
deduction

24. If an item from the engagement questionnaire is considered to be applicable by highly engaged students but also by highly unengaged students, then this item is not

monotone
polytomous
dichotomous

25. Suppose the research hypothesis is not confirmed by the results and the lecturer decides not to publish the research for that reason. This is an example of

publication bias
replication failure
the file-drawer problem

26. If the engagement questionnaire is very unreliable, then the next time any particular student completes the questionnaire the new engagement score is expected to differ from the original score

by a small degree
by a large degree
not at all

27. Type of student (premaster/bachelor) is a

monotone variable
experimental variable
individual-differences variable

28. The measurement level of the variable educational degree is

ordinal
interval
nominal

29. Consider the following results for the variable sex:

Descriptive Statistics Value
Number of respondents 115
Number of missing values 4
Minimum value 1
Maximum value 3
Indicate what the most likely error is

a (re)coding error
a data entry error
missing values were misspecified

30. The benefit of a syntax-file, amongst other things, is documentation of

all (statistical) operations performed on the data
all the materials used in the research study
both

Peer-graded Assignment: Final Writing Assignment – (Evaluative)

Project Title *
Give your project a descriptive title

Final Writing Assignment – (Evaluative)

Click here to download the answer file

Week- 8

Final Exam

1. This is the final exam which will contribute significantly to your final grade. Please make sure you have a good internet connection and don’t forget to save your answers from time to time. You can take this exam only once every 30 days, so please make sure you are well prepared!

To pass the exam you need a score of 70% (21 out of 30 questions correct). You can take this exam only once a month, so make sure you are well prepared!

This final exam consists of 30 multiple-choice questions about the research described below. Each question has three answer options, of which only one is correct or most appropriate. If you feel a correct answer option is not provided, then choose the best fitting option.

Please follow the honor code and do not communicate or confer with others taking this exam.

English vs. Dutch
The Communication Sciences department at the University of Amsterdam is considering offering the existing Dutch bachelor program in English. Some teachers fear that this will cause the educational quality of the program to deteriorate. They point to studies that show that students who study abroad need more time to complete a program. A researcher who is interested in the relationship between language skills and academic achievement, decides to use this opportunity to explore the general hypothesis that education in a foreign language has a negative influence on academic achievement.

The researcher approaches the lecturers of the first two courses in the first semester, ‘Introduction’ and ‘History’. She persuades the lecturers to deliver the lectures and seminars (group meetings) twice, once in Dutch and once in English. At the start of the semester, students choose if they wanted to follow both courses either in English, or in Dutch. Students are also asked for permission to use their academic results for research purposes.

To assess the effect of the language of instruction on academic achievement, the researcher measures students’ knowledge of the material twice, once with an exam at the start of the course and once at the end. These are all different, old exams that have previously shown high psychometric quality.

Besides academic performance (average exam grade on the final exam, range 1-10), students are asked to fill out a separate online survey to indicate their age (in years), gender (male / female), secondary education final exam score in English (grade, range 1-10) and overall satisfaction with the courses ‘Introduction’ and ‘History’ (mean sum score of 4 Likert items, range 4-20).

Disclaimer: This research is completely fabricated!

1 The described study is

correlational
experimental
quasi-experimental

2. The researcher could have conducted a manipulation-check by checking if the

mean final exam grade in English was similar between groups
mean performance on the first exam was the same between groups
discussions in the English speaking group were really conducted in English

3. The independent variable is

gender
language of instruction
final exam score in English

4. The described research design is especially useful to assess threats to internal validity by

maturation
selection
neither

5.
Question 5
If the reliability of the overall satisfaction questions is very high, then their validity will be

high
low
not necessarily high or low

6. The dependent variable in this study is

age
academic achievement
overall satisfaction (with the courses)

7. The design of this study is called a

Solomon pretest posttest design
randomized pretest posttest design
pretest posttest non-equivalent control group design

8. External validity could have been enhanced by using a

quota sample
random sample
convenience sample

9. If we don’t take into account the average exam grade at the start of the course, the described research design may be called

within (subjects)
between (subjects)
within-between (subjects)

10. The variable most appropriate to be used as a control variable is

age
overall satisfaction
final exam grade in English

11. The described research design is, in terms of epistemologic approach, most compatible with

realism
empiricism
neither

12. The best randomization check the researcher could have performed would be to check whether

the average final exam grade in English was similar between groups
academic achievement was the same between groups at the start of the study
both

13. Suppose the researcher decides to add gender to the described design as an independent variable. The effects that can be analyzed are

one main effect and one interaction effect
two main effects and one interaction effect
two main effects and two interaction effects

14. The internal validity of the described research design is threatened most strongly by

testing
selection
instrumentation

15. Suppose the research hypothesis is not confirmed, and for that reason the study is not accepted for publication by scientific journals. This is an example of

publication bias
falsification error
replication failure

16. Overall satisfaction (with the courses) is

a constructive variable
an experimental variable
an individual difference variable

17. The measurement level of the variable ‘language of instruction’ is

interval
ordinal
nominal

18. a. “Research shows that students who study abroad need more time to complete their studies”

b. “Teaching a foreign language will lead to lower academic performance than education in the native language”

c. “The average final exam grade for the courses ‘Introduction’ and ‘History’ will be lower in the group that was taught in English than in the group was taught in Dutch”

The previous three statements a, b and c respectively belong to the following stages of the empirical cycle

observation – induction – deduction
deduction – induction – observation
deduction – observation – induction

19. Suppose the items in the online questionnaire really do give a good indication of student satisfaction with the courses. In that case, we say the questionnaire has high

construct validity
predictive validity
ecological validity

20. If students behave differently because they are aware of their participation in a study, we call this

a Pygmalion effect
demand characteristics
“bad participant” behavior

21. Suppose the Ethics Committee evaluates the described research and decides that the benefits do not outweigh the costs. Which ethical aspect do they regard to be violated?

respect
justice
beneficence

22. If a researcher believes that the nature of reality is not independent of our thinking, then this is primarily an objection of

an epistemological nature
an ontological nature
both

23. The measurement level of variables like exam grade and final exam grade in English is highly debated, generally researchers will accept that these variables approximate the

ratio level, but strictly speaking are measured at the interval level
interval level, but strictly speaking are measured at the ordinal level
ordinal level, but strictly speaking are measured at the nominal level

24. Suppose the researcher finds: a) that there are relatively more women in the English group than in the Dutch group and b) that on average women perform equally well in the final examinations. In this case, we call gender

a confounding variable
a lurking variable
neither

25. One method to evaluate the validity of a measurement instrument like exam grade or the overall course satisfaction items is the

purposive validation approach
multi-stage clustering approach
multi-trait multi-method matrix approach

26. Suppose you have determined – through psychometric analysis – that the final exam of the course “Introduction” has high construct validity. On the basis of this information, you can say that the reliability of this exam

cannot be determined
is probably low
is probably high

27. The ecological validity of this study is high because the

instruments measure what they are intended to measure
research setting resembles a natural educational setting
sample (almost all first year students Communication Sciences) is large

28. Suppose the researcher had initially planned to use the results of the final exams as well as the resits (retake exam if the final exam was not passed). However, she notices immediately after the final exams that the results are in line with the expectations. The researcher decides to offer the data for publication immediately and no longer waits for the results of the resits. This is called

harking
data snooping
cherry picking

29. A codebook includes a description of

what the variables and variable values in the data file mean
the (statistical) operations that are performed on the data
both

30. Suppose that there is no difference between the two groups in the mean grade for the exams at the start of the semester. Now look at the following table that shows the mean grade for the final exams for both groups.

Results for mean final exam grade:

Language of instruction N missing mean sd
English 79 3 6.56 1.27
Dutch 119 4 6.11 2.14
Look only at the direction of the difference between these means (not the size or significance). The direction of the difference is