220 research methods Flashcards
(121 cards)
1
Q
What is empirical knowledge based on?
A) Authority and tradition
B) Personal beliefs
C) Experience and observation
D) Logical reasoning
A
C) Experience and observation
If a scientist does a test to see how sleep changes memory and writes down what happens, this is called empirical knowledge because it comes from watching and learning from real experiments.
2
Q
What must an assertion (주장) have to be considered scientific?
A) Logical and empirical support
B) Agreement from experts
C) A strong hypothesis
D) A well-written explanation
A
A) Logical and empirical support
Example: If someone claims that crime rates increase during the summer, they need both logical reasoning (hot weather leads to more outdoor activity) and empirical data (crime statistics) to support the claim.
An assertion is a statement or claim that something is true. It’s when someone says something confidently, often without providing evidence right away to back it up.
For example:
“The sky is blue” is an assertion. It’s a statement that can be checked for truth.
3
Q
What is epistemology?
A) The science of knowing
B) The study of crime
C) A type of hypothesis
D) A method of observation
A
A) The science of knowing
Imagine you’re trying to figure out if it’s raining outside. You might use your eyes to look out the window (empirical evidence), or you might ask someone (testimony). Epistemology would study how you know it’s raining and whether you can trust your eyes or the person you asked.
4
Q
What does methodology focus on?
A) Creating laws
B) The process of finding out information
C) Making ethical decisions
D) Conducting legal trials
A
B) The process of finding out information
Example: If a researcher wants to study police behavior, they must choose the right methodology, like surveys or field observations, to collect data.
5
Q
Why are humans considered ‘naive observers’?
A) We rely only on traditions
B) We often form explanations based on limited observations
C) We never question authority
D) We always rely on logical reasoning
A
B) We often form explanations based on limited observations
Example: If a person sees a news report about one car theft in their neighborhood, they might assume crime is increasing, even though no data supports that conclusion.
6
Q
What is the purpose of a hypothesis in research?
A) To provide a definitive answer
B) To explain a possible relationship between variables
C) To replace traditional beliefs
D) To confirm agreement reality
A
B) To explain a possible relationship between variables
Example: A researcher might hypothesize that longer prison sentences reduce crime, then test this idea by analyzing crime rates before and after sentencing changes.
7
Q
What are the two types of reality?
A) Logical and scientific
B) Experiential and agreement
C) Empirical and hypothetical
D) Theoretical and methodological
A
B) Experiential and agreement
Example: Experiential reality is knowing fire is hot because you touched it; agreement reality is believing the Earth is round because scientists agree on it.
8
Q
What is agreement reality?
A) Knowledge we accept because of tradition or authority
B) Knowledge gained through direct experience
C) Knowledge that cannot be tested
D) Knowledge based only on opinion
A
A) Knowledge we accept because of tradition or authority
Example: Most people accept that gravity exists because scientists and textbooks confirm it, even if they haven’t personally tested it.
9
Q
How can tradition be a double-edged sword in knowledge?
A) It always provides the correct information
B) It prevents critical thinking
C) It passes down useful knowledge but can also spread incorrect beliefs
D) It relies only on empirical support
A
C) It passes down useful knowledge but can also spread incorrect beliefs
Example: Many cultures traditionally believed the Earth was flat, which was later proven incorrect by scientific observation.
10
Q
Why is critical thinking important when relying on authority for knowledge?
A) Experts are always correct
B) Authority figures cannot be questioned
C) Experts can be wrong, and sources should be evaluated
D) Agreement reality is always factual
A
C) Experts can be wrong, and sources should be evaluated
Example: A nutrition expert might say a certain diet is best, but if scientific research proves otherwise, critical thinking helps people evaluate the truth.
11
Q
What is the main cause of inaccurate observation in personal inquiry?
A) Overgeneralization
B) Selective observation
C) Sloppy observation and memory reconstruction
D) Political bias
A
C) Sloppy observation and memory reconstruction
Example: If a witness to a crime misremembers key details because they weren’t paying full attention, this is an example of inaccurate observation.
12
Q
How can researchers guard against inaccurate observations? Error #1
A) Relying on personal beliefs
B) Using scientific observation methods
C) Overgeneralizing findings
D) Ignoring contradictory data
A
B) Using scientific observation methods (Error #1)
Example: A researcher recording crime rates should use video surveillance or detailed notes instead of relying on memory alone.
13
Q
What is overgeneralization? Error #2
A) Ignoring information that contradicts beliefs
B) Assuming a small number of cases represent a broad pattern
C) Drawing conclusions based on logic
D) Repeating a study multiple times
A
B) Assuming a small number of cases represent a broad pattern
Guard against by: (Using appropriate sample, Replication -> repeat)
Example: If a person sees two car thefts in their neighborhood and assumes crime is increasing everywhere, they are overgeneralizing.
14
Q
How can overgeneralization be avoided in research?
A) Using a large and appropriate sample size
B) Only studying one example
C) Ignoring data that doesn’t fit
D) Relying on personal beliefs
A
A) Using a large and appropriate sample size
Example: A criminologist studying juvenile delinquency should survey a large group of youths rather than assuming all teens are delinquent based on a few cases.
15
Q
What is selective observation? (Error #3)
A) Focusing only on evidence that supports a belief
B) Making incorrect logical conclusions
C) Overgeneralizing from a small sample
D) Failing to observe important data
A
A) Focusing only on evidence that supports a belief
Noticing events that support our beliefs and ignoring others
Guard against by: (Specify #, type of observations)
Example: A person who believes crime is increasing might only notice news reports about violent incidents while ignoring reports showing crime rates are declining.
16
Q
How can researchers avoid selective observation?
A) Ignore contradictory evidence
B) Specify the number and type of observations before conducting research
C) Only use personal experiences as data
D) Overgeneralize findings
A
Example: If a researcher is studying police interactions, they should collect data from multiple officers and incidents instead of just focusing on cases that confirm their expectations.
Researchers can avoid selective observation by following a clear research plan, looking at all evidence (not just what supports their ideas), and using large, diverse samples.
17
Q
What is illogical reasoning? (Error #4)
A) Making conclusions that don’t logically follow from the evidence
B) Ignoring all forms of research
C) Overgeneralizing data
D) Selectively choosing observations
A
A) Making conclusions that don’t logically follow from the evidence
Example: If a person believes crime increases during a full moon just because they heard about a few crimes happening on those nights, they are using illogical reasoning.
18
Q
How can researchers guard against illogical reasoning?
A) Creating logical arguments and using sound reasoning
B) Ignoring contradicting information
C) Using small and biased samples
D) Overgeneralizing results
A
A) Creating logical arguments and using sound reasoning
Example: A study on the effects of social programs on crime should logically connect data to its conclusions rather than making assumptions without evidence.
19
Q
How can ideology and politics interfere with objective research? (Error #5)
A) They help researchers remain unbiased
B) They can shape conclusions based on beliefs rather than data
C) They prevent all errors in observation
D) They ensure research is always logical
A
B) They can shape conclusions based on beliefs rather than data
Example: If a researcher strongly believes in strict policing, they might ignore evidence showing that community policing reduces crime more effectively.
20
Q
What is the best way to prevent ideological and political bias in research?
A) Conducting research with an open mind and without bias
B) Only using sources that support personal beliefs
C) Overgeneralizing results to fit expectations
D) Ignoring evidence that contradicts pre-existing views
A
A) Conducting research with an open mind and without bias
Example: A fair study on gun control should consider all available data, not just information that supports one side of the debate.
21
Q
What does it mean for social science research to be “value free”?
A) It should reflect the values of the researcher
B) It is concerned with what should be, not what is
C) It focuses only on what is and why, without personal biases
D) It supports policy and decision-making
A
C) It focuses only on what is and why, without personal biases
Example: A criminologist studying the impact of community policing does not let their personal beliefs about policing influence the research findings.
22
Q
What is the difference between subjectivity and objectivity in research?
A) Subjectivity is unbiased, while objectivity is biased
B) Objectivity is desired in research, as it minimizes personal bias
C) Subjectivity focuses on patterns, while objectivity focuses on individual cases
D) Objectivity refers to what should be, and subjectivity focuses on what is
A
B) Objectivity is desired in research, as it minimizes personal bias
Subjectivity in research means letting personal opinions, feelings, or biases affect the results.
Objectivity in research means keeping your personal feelings out and sticking to the facts, so the results are fair and accurate.
Example: In studying crime rates, objectivity means relying on data and facts, not allowing personal views about crime to influence conclusions.
23
Q
Why is objectivity important in social science research?
A) It ensures the research is biased
B) It helps researchers maintain a neutral and scientific approach
C) It allows researchers to support a particular agenda
D) It is irrelevant in scientific inquiry
A
B) It helps researchers maintain a neutral and scientific approach
Example: A researcher studying racial bias in policing must avoid letting their personal opinions about the subject influence the research process or findings.
24
Q
What does it mean when social research is described as “probabilistic”? (확률적)
A) It focuses only on certainties
B) It aims to find patterns but acknowledges exceptions
C) It guarantees conclusions for all cases
D) It ignores exceptions in data
A
B) It aims to find patterns but acknowledges exceptions
Example: A study on criminal recidivism may show that many offenders reoffend, but some do not, highlighting the probabilistic nature of social research.
research in social sciences can show that certain things tend to happen, but it can’t guarantee exact outcomes every time.
25
What is a key characteristic of probabilistic social research?
A) It seeks exact truths without exceptions
B) It looks for patterns but acknowledges that there are always exceptions
C) It only looks at individual cases without drawing general conclusions
D) It avoids using data and focuses on personal experiences
B) It looks for patterns but acknowledges that there are always exceptions
Example: A study on the relationship between unemployment and crime might show a correlation but also recognize that some unemployed individuals do not commit crimes.
26
What is the focus of pure or basic research in social science?
A) To directly influence policy decisions
B) To explore, describe, and explain phenomena
C) To evaluate existing policies
D) To apply findings to real-world problems
B) To explore, describe, and explain phenomena
Example: A criminologist conducting basic research might study the relationship between neighborhood structure and crime without aiming to change specific policies.
27
What is the purpose of applied research in social science?
A) To explore theoretical concepts
B) To analyze existing data for academic interest
C) To evaluate policies and suggest real-world applications
D) To simply describe social phenomena
C) To evaluate policies and suggest real-world applications
Example: A study evaluating the effectiveness of rehabilitation programs in prisons is applied research because it aims to provide practical recommendations for policy.
28
What is the first step in the traditional model of science?
A) Data analysis
B) Observation
C) Theory
D) Reporting
C) Theory
Example: In a study on crime prevention, the first step is to develop a theory on how community policing might reduce crime.
29
What does operationalization in research involve? Science
A) Collecting raw data
B) Defining abstract concepts in measurable terms
C) Drawing conclusions based on data
D) Creating a hypothesis
B) Defining abstract concepts in measurable terms
Conceptualization = Defining what a concept means (broad idea).
Operationalization = Deciding how to measure that concept (making it specific and testable)
An example of operationalization could be: If a researcher is studying "happiness," they might define it by looking at things like how often people smile or how many positive emotions they report each day. This makes the idea of happiness easier to measure in a study.
30
What comes after theory in the traditional model of science?
A) Observation
B) Conceptualization
C) Data analysis
D) Reporting
B) Conceptualization
Conceptualization means clearly defining an idea so everyone understands what it means.
For example, after creating a theory about crime rates, a researcher would conceptualize it by deciding which factors to focus on, like education levels or unemployment rates, to better understand how they might affect crime.
31
In the traditional model of research, what is involved in "observation"? Science
A) Defining concepts in measurable terms
B) Selecting the population for the study
C) Gathering data through surveys, experiments, or fieldwork
D) Analyzing data to find patterns
C) Gathering data through surveys, experiments, or fieldwork
Example: In a criminology study, the researcher might observe criminal behavior in a certain community to gather data.
32
What is the purpose of "data analysis" in the traditional research model? Science
A) To test the hypothesis
B) To define the variables of interest
C) To organize and interpret the collected data
D) To write the research report
C) To organize and interpret the collected data
Example: After observing the crime rates, data analysis helps the researcher interpret whether there is a relationship between unemployment and crime rates.
33
What is the correct order of steps in a traditional research project?
A) Data analysis, population and sampling, operationalization
B) Conceptualization, choice of method, data analysis
C) Idea/theory, choice of method, reporting
D) Idea/theory, conceptualization, choice of method, observation, data analysis, reporting
D) Idea/theory, conceptualization, choice of method, observation, data analysis, reporting
Example: The process of studying how community-based policing reduces crime begins with an idea/theory, then moves through each step, from conceptualization to reporting the findings.
34
What does "conceptualization" involve in the traditional model of research? project
A) Defining specific measurable variables from a broad concept
B) Analyzing collected data for patterns
C) Collecting raw data from the sample group
D) Testing hypotheses through experiments
A) Defining specific measurable variables from a broad concept
For example, when studying how education affects crime, conceptualization might mean thinking of education as things like how many years someone has gone to school or how well they can read.
35
Why is "choice of method" an important step in the traditional research model? project
A) It helps determine how data will be analyzed
B) It defines how the results will be reported
C) It establishes the most suitable approach for gathering data
D) It helps define the population to study
C) It establishes the most suitable approach for gathering data
Example: A researcher studying crime rates might choose a survey method for gathering data from a large population or an observational method for more specific case studies.
36
What happens during "reporting" in a traditional research project?
A) The researcher's hypothesis is tested and proven
B) The data is analyzed and conclusions are drawn
C) The results are shared through publications, reports, or presentations
D) The study method is decided upon
C) The results are shared through publications, reports, or presentations
For example, after looking at the data on crime prevention programs, the researcher writes a report that explains what they found and how it could affect policies or decisions.
37
What is the primary difference between a theory and a hypothesis?
A) A theory is a testable statement, while a hypothesis is a systematic explanation
B) A theory explains observed facts, while a hypothesis predicts relationships between variables
C) A hypothesis is more general than a theory
D) A theory is always proven correct, while a hypothesis is always incorrect
B) A theory explains observed facts, while a hypothesis predicts relationships between variables
Example: A theory might explain why crime rates rise in certain areas, while a hypothesis would predict that increased unemployment in those areas leads to higher crime rates.
38
Can a hypothesis be “proven” through research?
A) Yes, a hypothesis can be conclusively proven
B) No, a hypothesis can only be tested and supported or refuted
C) Yes, hypotheses are always correct when tested
D) No, hypotheses are never testable
B) No, a hypothesis can only be tested and supported or refuted
For example, after testing the idea that more police officers reduce crime, researchers might find that it seems true, but they can't completely prove it because other factors could also explain the results.
39
In the research process, what is the relationship between theory and policy?
A) Theories guide policy creation, but policies do not influence research
B) Research guides theory, but policy has no role
C) Theory guides research, and research findings may inform policy decisions
D) Policy is the same as a hypothesis
C) Theory guides research, and research findings may inform policy decisions
For example, a theory about how well rehabilitation programs work can guide research, and the results from that research can help change laws or policies about how prisons are run.
40
What is the primary characteristic of deductive reasoning?
A) Moving from specific observations to general theories
B) Testing a theory to see if data support it
C) Creating a theory after observing patterns in data
D) Starting with data and developing a theory from it
B) Testing a theory to see if data support it
Inductive reasoning starts with specific observations and leads to a general theory.
Deductive reasoning starts with a general theory and tests it with specific data.
41
How does inductive reasoning differ from deductive reasoning?
A) Inductive reasoning moves from general to specific, while deductive reasoning moves from specific to general
B) Inductive reasoning moves from specific observations to general theories, while deductive reasoning moves from general to specific
C) Inductive reasoning tests theories, while deductive reasoning creates them
D) Inductive reasoning is used only in qualitative research
B) Inductive reasoning starts with specific observations and then builds a general theory from them. For example, noticing that crime rates go down in several cities with more police might lead to the theory that more police reduce crime.
Deductive reasoning starts with a general theory and tests it with specific observations. For example, starting with the idea that more police reduce crime, and then checking if crime rates are lower in cities with more police.
Example: A researcher studying patterns of criminal behavior might start with observations and then develop a general theory about what influences such behavior.
42
What is a key difference between quantitative and qualitative research?
A) Quantitative research is non-numerical, while qualitative research is numerical
B) Quantitative research is used to test hypotheses, while qualitative research explores patterns
C) Quantitative research is always based on deductive reasoning, while qualitative research uses inductive reasoning
D) Quantitative and qualitative research are the same
B) Quantitative research is used to test hypotheses, while qualitative research explores patterns
Quantitative research uses numbers and statistics to study things (e.g., surveys, experiments). Example: Measuring crime rates in different cities.
Qualitative research uses words and descriptions to understand things (e.g., interviews, observations). Example: Studying how people feel about crime in their neighborhood.
43
What is the difference between a construct and a variable?
A) A construct is an abstract idea, while a variable is a concrete representation of that idea
B) A construct is always measurable, while a variable is not
C) A variable is a theory, while a construct is a hypothesis
D) A variable is an idea in a study, while a construct is a characteristic
A) A construct is an abstract idea, while a variable is a concrete representation of that idea
A construct is a big, general idea, like happiness. A variable is a specific thing you can measure to show that idea, like how often someone smiles or how happy they say they feel.
For example, socioeconomic status is a broad idea (a construct), and to measure it, researchers might use specific things like income level or education level (the variables) as ways to understand it.
44
What is an example of an independent variable (IV)?
A) The outcome of a study
B) The variable that causes an effect or change
C) The characteristic that is measured
D) The group that is studied
B) The variable that causes an effect or change
Example: In a study examining how education affects crime rates, the independent variable would be education level, as it is the cause being tested.
45
What is the dependent variable (DV) in an experiment?
A) The predictor variable
B) The outcome or effect that changes in response to the independent variable
C) The method of data collection
D) The theory being tested
B) The outcome or effect that changes in response to the independent variable
The dependent variable (DV) is the result you're measuring to see if it was affected by the independent variable (IV).
In other words, you look at the DV to see if changes in the IV caused any differences.
For example:
IV: Amount of water given to plants
DV: Plant growth (how tall they get)
You change the amount of water (IV) and then measure the plant's growth (DV) to see if the water caused the growth to change.
DV changes because of the changes you make to the IV.
46
What is meant by "unit of analysis" in research?
A) The variable being measured in the study
B) The specific method used for data analysis
C) The people or phenomena being studied
D) The theoretical framework for the study
C) The people or phenomena (현상) being studied
Example: If studying the effects of community policing, the unit of analysis might be the individual officers, the communities, or the police departments themselves.
47
What is the ecological fallacy (오류)?
A) Making conclusions about groups based on individual data
B) Assuming that a conclusion about groups applies to individuals within the groups
C) Confusing causation with correlation
D) Using statistical analysis to draw conclusions about qualitative data
B) Assuming that a conclusion about groups applies to individuals within the groups
Example: Saying that "most people in low-income areas commit crimes" and assuming that every individual in those areas commits crimes is an example of the ecological fallacy.
48
What is the main difference between cross-sectional and longitudinal studies?
A) Cross-sectional studies follow participants over time, while longitudinal studies look at a phenomenon at a single point in time
B) Cross-sectional studies examine a phenomenon at one point in time, while longitudinal studies follow participants over time
C) Longitudinal studies are always more expensive than cross-sectional studies
D) Longitudinal studies only examine trends, while cross-sectional studies examine cause and effect
B) Cross-sectional studies examine a phenomenon at one point in time, while longitudinal studies follow participants over time
Example: A cross-sectional study might look at the relationship between poverty and crime at one moment in time, while a longitudinal study might track this relationship over several years.
49
.What is the main difference between retrospective and prospective studies?
A) Retrospective studies look at phenomena over time, while prospective studies examine them at a single point in time
B) Retrospective studies look at data from the past, while prospective studies look at data from the future
C) Retrospective studies are only used for experiments, while prospective studies are used for surveys
D) There is no difference between retrospective and prospective studies
B) Retrospective studies look at data from the past, while prospective studies look at data from the future
Example: A retrospective study might examine past crime data to understand trends, while a prospective study might follow participants into the future to observe crime patterns.
In prospective studies, researchers start by collecting data in the present or current time and then follow participants or events into the future to see how things develop.
While they don’t predict the future directly, they observe patterns and factors now that could influence or affect what happens later.
For example, if researchers track people’s habits today (like diet or exercise), they might study how those habits impact their health in the years to come.
50
How does the way a research problem is stated affect the study outcome?
A) It does not affect the study outcome at all
B) It influences the variables that will be studied and how results are interpreted
C) It only determines the sample size
D) It ensures that the study proves a hypothesis
B) It influences the variables that will be studied and how results are interpreted
If a researcher asks, “Why do juveniles commit crimes?” versus “What factors contribute to juvenile crime?”, the first question assumes that all juveniles commit crimes, while the second allows for an objective investigation.
51
2 types of Empirical Questions
1. Descriptive (provide information about a situation)
2. Causal (examine how one variable affects another)
Example:
Descriptive Question: What is the average recidivism rate for juveniles?
Causal Question: Does participation in a rehabilitation program reduce recidivism rates?
52
Which of the following is an example of a correlational relationship?
A) Increased study time leads to higher test scores
B) More ice cream sales occur when temperatures rise
C) Drinking coffee improves work performance
D) A new law reduces crime rates
B) More ice cream sales occur when temperatures rise
Example:
Just because ice cream sales and drowning incidents both increase in summer doesn’t mean ice cream causes drowning—it’s just a correlation.
A correlational relationship means two things are related, but one does not necessarily cause the other.
53
What is a key difference between correlation and causation?
A) Correlation proves causation
B) Correlation means two variables are related, while causation means one variable directly influences another
C) Causation and correlation always occur together
D) If two things happen together, one must have caused the other
B) Correlation means two variables are related, while causation means one variable directly influences another
Example:
Correlation: People who own more books tend to score higher on tests.
Causation: Studying more leads to higher test scores.
54
Which of the following are the three criteria for causality?
A) Variables are correlated, temporal precedence, no plausible alternative explanations
B) Variables are correlated, effect occurs before cause, presence of a third variable
C) No correlation, temporal precedence, multiple explanations for cause and effect
D) Cause and effect happen simultaneously, strong correlation, use of a large sample size
A) Variables are correlated, temporal precedence, no plausible alternative explanations (we have to make sure the result isn’t caused by something else)
If studying increases → grades increase, this shows correlation. If studying happens on Monday and the exam is on Tuesday, this meets temporal precedence. If no other factor (like tutoring) explains the higher grade, then there are no plausible alternative explanations, meaning studying causes better grades.
If all three are met, then we can say one variable causes the other.
55
What is the first requirement for a causal relationship to exist?
A) The independent variable (IV) must happen after the dependent variable (DV)
B) The two variables must be correlated
C) There must be at least three variables
D) The study must use a large sample
B) The two variables must be correlated
A study finds that exercise is correlated with weight loss. This is the first step in proving causation, but not enough by itself.
56
What is an example of temporal precedence?
A) Exercising and losing weight occur at the same time
B) A person studies first and then gets a good grade on the test
C) A person studies after getting their test results
D) Weight loss and exercise are unrelated
B) A person studies first and then gets a good grade on the test
Example:
If you eat a healthy diet first and then lose weight, the diet might be the cause. But if you lose weight before changing your diet, it’s not the cause.
57
Why is it important to rule out alternative explanations in research?
A) It ensures the study supports the researcher's opinion
B) It proves that the independent variable is the only factor affecting the dependent variable
C) It eliminates the possibility that a third variable is influencing the relationship
D) It makes the study more complex
C) It eliminates the possibility that a third variable is influencing the relationship
A study finds that kids who play violent video games are more aggressive. But if those kids also have aggressive parents, the parenting (third variable) might be the real cause.
58
What does conclusion validity assess?
A) Whether the relationship between variables reflects the real-world concept of interest
B) The extent to which findings can be generalized to other populations and settings
C) Whether a change in the independent variable (IV) is statistically correlated with a change in the dependent variable (DV)
D) The degree to which systematic errors or third variables impact the study
C) Whether a change in the independent variable (IV) is statistically correlated with a change in the dependent variable (DV)
Example: If a study finds that attending tutoring sessions (IV) is linked to higher exam scores (DV),
It checks if the relationship is real and not due to random chance or errors.
59
Why is sample size important for conclusion validity?
A) Larger sample sizes increase statistical power
B) Small sample sizes always produce more accurate results
C) Sample size is only important for external validity
D) The number of participants does not affect research outcomes
A) Larger sample sizes increase statistical power
Example: If a researcher studies DUI rates among only 50 high school students in BC, the results may not be statistically powerful enough. A larger sample size (e.g., 500 students) increases power, making the findings more reliable.
60
What does internal validity refer to?
A) The ability to determine if one variable causes another
B) The extent to which findings apply to different populations
C) The relationship between statistical power and sample size
D) How well a study avoids bias from small sample sizes
A) The ability to determine if one variable causes another
Example: A study finds that exercise leads to weight loss, but if diet is not controlled, the internal validity is weak because diet could be a third variable affecting the results.
Internal validity checks whether one variable (IV) truly affects another variable (DV) and also whether a third variable (confounding variable) could be influencing the outcome.
61
What is the primary threat to internal validity?
A) Having too large a sample
B) A third variable influencing the results
C) The inability to generalize findings to other populations
D) Measuring the wrong variables in a study
B) A third variable influencing the results
Example: A study claims video games cause aggression, but if parenting style is not accounted for, it may actually be a third variable influencing aggression levels.
62
What does external validity measure?
A) The ability to generalize research findings to different populations and settings
B) Whether one variable directly causes another variable to change
C) Whether the study measures what it claims to measure
D) The statistical power of a study based on sample size
A) The ability to generalize research findings to different populations and settings
External validity is about whether the results of a study apply to other people, places, or situations.
Example: If a study on police training only examines officers in one city, it may lack external validity because findings may not apply to officers in other cities or countries.
63
What does construct validity refer to?
A) Whether the variables in the study accurately represent real-world concepts
B) The degree to which findings can be generalized
C) Whether statistical power is high enough for valid conclusions
D) Whether sample size is large enough to detect significant differences
A) Whether the variables in the study accurately represent real-world concepts
is about whether a test or measure actually measures what it’s supposed to measure.
Example: If a study claims to measure stress but only asks about hours worked, it may have low construct validity because stress involves more factors like mental health, workload, and lifestyle.
64
What is the key difference between a priori and post hoc power analysis?
A) A priori determines the necessary sample size before data collection, while post hoc assesses power after data is collected
B) A priori is only used in qualitative research
C) Post hoc determines how variables should be measured
D) Post hoc calculates the sample size needed before conducting the study
A) A priori determines the necessary sample size before data collection, while post hoc assesses power after data is collected
A priori means you figure out how many people or data points you need before you start your study. It’s like planning ahead, so you don’t waste time or resources.
Post hoc is when you look at the data you’ve already collected and then check if you had enough participants to find meaningful results. It's like checking if your plan worked after the fact.
65
Which of the following are the four types of validity commonly used in research?
A) Content validity, construct validity, conclusion validity, and power validity
B) Construct validity, internal validity, external validity, and power validity
C) Content validity, construct validity, internal validity, and external validity
D) External validity, criterion-related validity, content validity, and conclusion validity
C) Conclusion validity, construct validity, internal validity, and external validity
66
What is the primary difference between a "conception" and a "construct"?
A) Conceptions are symbols used to represent mental images, while constructs are the mental images themselves.
B) Conceptions are mental images, while constructs are words or symbols used to represent these images.
C) Constructs are concrete objects, while conceptions are abstract ideas.
D) Constructs refer to actual measurements, while conceptions are theoretical ideas.
B) Conceptions are mental images, while constructs are words or symbols used to represent these images.
Example: A conception of "happiness" may involve feeling joy, smiling, and being at peace, while the construct would be the term "happiness" used to represent those feelings.
67
Which of the following is a key component of conceptualization?
A) Identifying hypotheses and testing variables
B) Identifying constructs, dimensions, and conceptual definitions
C) Creating operational definitions for constructs
D) Determining the sample size for research
B) Identifying constructs, dimensions, and conceptual definitions
Example: In researching "violent crime," you might identify constructs like "aggravated assault," break it down into dimensions (e.g., "premeditation"), and define it as "the intent to harm another individual with prior thought."
68
What is an operational definition?
A) A set of rules for collecting data in the field
B) A measure of the quality of the data
C) A detailed description of how a construct will be measured in practice
D) A theoretical explanation of how variables relate
C) A detailed description of how a construct will be measured in practice
Operationalization is about how you measure that concept in the real world.
Example: For the construct "academic performance," an operational definition might be "midterm exam score" or "average grade in a course."
69
Which of the following is an example of an ordinal level of measurement?
A) Gender
B) A ranking of the top 5 football teams in a league
C) Blood alcohol content
D) Age in years
B) A ranking of the top 5 football teams in a league
Example: Ranking teams based on performance (1st, 2nd, 3rd, etc.) represents an ordinal scale because the positions are ordered, but the distance between ranks isn’t necessarily equal.
70
What does "reliability" in measurement refer to?
A) The accuracy of the measurement
B) The consistency of the measurement when repeated
C) The ability of a measure to reflect true scores
D) The ease of applying the measurement in different contexts
B) The consistency of the measurement when repeated
Example: If you measure someone's height several times with the same ruler and get the same result each time, your measurement is reliable.
71
Which of the following is an example of criterion-related validity?
A) Comparing your measurement of "stress" with a widely accepted stress test
B) Checking if a measure agrees with related constructs
C) Testing if a measurement captures all aspects of a concept
D) Evaluating if a measure is meaningful in the context of its definition
A) Comparing your measurement of "stress" with a widely accepted stress test
Criterion-related validity is just checking if a measurement actually makes sense and matches what it should. (fact checking)
If you're measuring how good someone is at math, you could check if their math test score matches their final grade in the math class.
If the test score and final grade are similar, it means your measure is valid!
72
Which of the following is a key aspect of "construct validity"?
A) The measure aligns with external criteria
B) The measure accurately reflects the theoretical construct
C) The measure covers the full range of the concept
D) The measure is consistent across different raters
B) The measure accurately reflects the theoretical construct
checks if the measurement really captures the idea or concept you're trying to measure. It's about making sure your test or tool truly reflects the thing you're studying.
For example, if you're trying to measure "happiness," construct validity would ask if your survey really measures happiness, or if it's measuring something else,
73
What is "face validity"?
A) The degree to which a test measures what it is supposed to measure
B) The consistency of a test over time
C) The common agreement on the meaning of a concept
D) The comparison of a test's results with an external criterion
C) The common agreement on the meaning of a concept
Face validity is how much a test looks like it measures what it’s supposed to measure. It’s based on common sense or judgment, not actual scientific proof.
Example: If a questionnaire on anxiety seems to reflect common understanding of anxiety (e.g., worry, nervousness), it has face validity.
74
What is an example of a measurement at the ratio level?
A) Gender
B) Ranking of countries by population
C) Age in years
D) Likert scale ratings (1-5)
C) Age in years
Age in years is a ratio because:
It has a true zero point—zero years means birth.
The difference between numbers makes sense—10 years is 5 years more than 5 years.
So, you can say things like "A 10-year-old is twice as old as a 5-year-old" because the scale has a true zero (birth) and equal intervals.
75
What does "mutually exclusive" attributes mean in measurement?
A) The categories allow for overlapping classifications
B) Each observation fits into one and only one category
C) The categories can be ranked from low to high
D) Categories are defined by an external criterion
B) Each observation fits into one and only one category
Example: If you classify people’s income into three groups (e.g., low, medium, high), each person should belong to only one of these categories.
76
What is the main purpose of conceptualization in research?
A) To define the research process
B) To specify precisely what we mean when we use particular terms
C) To establish the reliability of measurements
D) To determine the validity of a construct
B) To specify precisely what we mean when we use particular terms
77
Which of the following is an example of a dimension of a construct?
A) Indicators
B) Pre-meditation in aggravated assault
C) Conceptual definition
D) Research about violent crime
B) Pre-meditation in aggravated assault
Example: In studying violent crime, one dimension could be pre-meditation, which helps differentiate the severity of an offense.
78
What does an indicator do in relation to a dimension?
A) It assigns a conceptual definition
B) It specifies how to measure a construct
C) It indicates the presence or absence of a dimension
D) It is a type of hypothesis
C) It indicates the presence or absence of a dimension
An indicator helps show if a dimension is present or not.
For example, if the dimension of pre-meditation is being studied in aggravated assault, an indicator could be asking, "Did the person plan the attack?" If the answer is yes, it shows the dimension (pre-meditation) is present. If the answer is no, the dimension is absent.
So, an indicator helps us see if the dimension exists.
79
Which of the following is an example of an operational definition?
A) Defining happiness as emotional well-being
B) Defining age as years since birth
C) Using pre-meditation as a dimension of aggravated assault
D) Using a scale of 1 to 10 to measure victim harm
B) Defining age as years since birth
Example: In an operational definition, “age” is measured as the number of years since birth.
80
What must attributes of variables be in research?
A) Consistent
B) Exhaustive and mutually exclusive
C) The same for all studies
D) Broad in scope
B) Exhaustive and mutually exclusive
Example: Family income categories must be mutually exclusive, so a person can only fit into one income bracket (e.g., less than $25,000, $25,001-$50,000).
81
Which of the following is an example of a nominal level of measurement? just a label
A) Age
B) Gender
C) Blood alcohol level
D) Temperature
B) Gender
nominal level of measurement is the simplest level, where data is categorized into different groups without any order or ranking.
Example: Gender is a nominal variable because it categorizes individuals without any inherent order.
82
Which level of measurement involves rank-ordered attributes with no information about the distance between values?
A) Nominal
B) Ordinal
C) Interval
D) Ratio
B) Ordinal
Example: A race ranking (1st, 2nd, 3rd) is ordinal, as it shows order but doesn’t specify how much better one rank is than another.
83
What is a ratio level of measurement characterized by?
A) No true zero point
B) Rank ordering without distances between values
C) Equal intervals between values and a true zero point
D) Qualitative categories
C) Equal intervals between values and a true zero point
Example: Age is measured on a ratio scale because it has equal intervals and a true zero point (birth).
84
What is the observed score in measurement?
A) The sum of random errors and systematic errors
B) The difference between random and systematic errors
C) The true score plus random error
D) The true score plus both systematic and random errors
D) The true score plus both systematic and random errors
Example: If a test score is 85, the observed score includes the true score (e.g., the student’s knowledge) and any errors in measurement.
85
Which of the following is an example of random error?
A) A person’s inability to recall information due to a test-taking distraction
B) Using the wrong formula in an experiment
C) A misinterpretation of a construct’s definition
D) Bias in the way questions are framed
A) A person’s inability to recall information due to a test-taking distraction
Example: A student’s performance might suffer due to distractions during a test, which introduces random error.
86
What does the test-retest method measure in terms of reliability?
A) Consistency between multiple raters
B) Consistency over time when the same measurement is taken repeatedly
C) The accuracy of a measurement technique
D) The degree of systematic error in a study
B) Consistency over time when the same measurement is taken repeatedly
Example: If a student takes the same math test twice and scores similarly each time, the test shows high reliability.
87
Which of the following is a measure of inter-rater reliability?
A) Checking if two researchers give the same rating to the same behavior
B) Repeating the same test with the same group of people
C) Using multiple measurement tools for the same construct
D) Testing for validity by comparing scores across different studies
A) Checking if two researchers give the same rating to the same behavior
Inter-rater reliability means checking if different people (or researchers) agree on their ratings or observations of something.
For example:
Two researchers watch the same person and rate their behavior, like how aggressive the person is.
If both researchers give the same rating (say, "high aggression"), then the inter-rater reliability is good.
If they give different ratings (one says "high," the other says "low"), then the inter-rater reliability is low.
It’s all about making sure everyone sees and rates things in the same way.
88
What is the role of multiple measures in research?
A) To test if the measurements are reliable
B) To compare a measure with alternative methods for assessing the same construct
C) To check the content validity of a single measure
D) To increase the sample size
B) To compare a measure with alternative methods for assessing the same construct
Example: To measure “aggression,” using both observational and self-report methods provides a more comprehensive measure of the construct.
89
What does criterion-related validity assess?
A) How well a measure reflects the underlying construct
B) The ability to predict outcomes based on external criteria
C) The range of aspects a measure covers
D) The consistency of measurements over time
B) The ability to predict outcomes based on external criteria
Example: If a new job performance measure accurately predicts future job success, it has high criterion-related validity.
90
Which of the following is a characteristic of discriminant validity?
A) A measure predicts outcomes in a related area
B) A measure correlates with scores on a different but related construct
C) A measure can distinguish between different constructs
D) A measure correlates with multiple variables
C) A measure can distinguish between different constructs
Example: A depression measure should not strongly correlate with a measure of anxiety, as they are distinct constructs.
91
What does convergent validity refer to?
A) The degree to which a measure aligns with an external criterion
B) The extent to which a measure covers the range of meanings of a construct
C) The ability of a measure to predict scores on another accepted measure of the same construct
D) The measure’s ability to distinguish between different constructs
C) The ability of a measure to predict scores on another accepted measure of the same construct
If you're measuring student motivation, you develop a new survey. To check convergent validity, you compare it to an existing motivation survey. If both surveys give similar results, it shows your new survey is accurately measuring motivation, demonstrating convergent validity.
92
Which of the following is true about interval measures?
A) They have a true zero point.
B) The distance between attributes has meaning, but there is no true zero point.
C) They can only be used for categorical data.
D) They represent rank-ordered values.
B) The distance between attributes has meaning, but there is no true zero point.
An interval measure is something where we can measure the difference between two things, but zero doesn't mean "nothing".
For example, temperature in Celsius: If it's 10°C and then 20°C, the difference is 10 degrees. The difference makes sense, but 0°C doesn't mean there's no temperature—it’s just another point on the scale.
It’s about how we can measure the distance between points, but zero doesn’t mean nothing.
93
What is the purpose of a pretest in an experiment?
a) To measure the independent variable before exposure
b) To measure the dependent variable before exposure
c) To introduce bias into the study
d) To determine the study’s conclusion before testing
b) To measure the dependent variable before exposure
"Pretest is the before test—it measures what people think or do before the experiment starts."
A researcher wants to study if a tutoring program improves math scores. They test students before the program starts. That test is the pretest.
94
In a posttest, when is the dependent variable measured?
a) Before exposure to the independent variable
b) After exposure to the independent variable
c) During exposure to the independent variable
d) It is not measured in a posttest
b) After exposure to the independent variable
After students complete the tutoring program, their math scores are measured again. This is the posttest.
95
What is the main difference between an experimental group and a control group?
a) The experimental group is randomly assigned, and the control group is not
b) The experimental group receives the independent variable, while the control group does not
c) The control group is tested first, and the experimental group is tested later
d) The experimental group is always larger than the control group
b) The experimental group receives the independent variable, while the control group does not
A study tests if caffeine improves memory. One group drinks coffee (experimental group), and the other drinks water (control group).
96
What is the Hawthorne effect?
a) When participants drop out of a study before it ends
b) When participants change their behavior because they know they are being observed
c) When researchers unknowingly influence participants’ responses
d) When participants guess the purpose of the study and act accordingly
b) When participants change their behavior because they know they are being observed
Workers in a factory work harder because they know they are being watched, not because of any real workplace improvements.
97
in a double-blind experiment, who is unaware of group assignments?
a) Only the participants
b) Only the researchers
c) Both the researchers and the participants
d) No one
c) Both the researchers and the participants
study where neither the researcher nor the participants know who is in the experimental group and who is in the control group. This prevents bias in the results.
Group assignment refers to who gets the independent variable (IV) and who does not.
Experimental group = Gets the IV (e.g., a new drug).
Control group = Does NOT get the IV (e.g., a placebo).
Since both the researchers and participants don’t know the assignments, they can’t influence the results on purpose or by accident.
98
Why is random assignment important in an experiment?
a) It ensures groups are equal at pretest
b) It guarantees a significant result
c) It eliminates all threats to internal validity
d) It replaces the need for a control group
a) It ensures groups are equal at pretest
A study on exercise and weight loss randomly assigns some people to a gym program and some to no exercise to make the groups similar.
99
What is a requirement for a “true” experiment?
a) Participants must volunteer
b) The researcher must control the independent variable
c) The researcher should allow self-selection into groups
d) The study must take place in a laboratory
b) The researcher must control the independent variable
A drug trial where the researcher controls who gets the medication and who gets a placebo is a true experiment.
100
What is the “gold standard” for experimental design?
a) Quasi-experimental studies
b) Experimental designs
c) Case studies
d) Cross-sectional surveys
b) Experimental designs
Controls the independent variable (IV) – The researcher decides who gets the treatment and who does not.
Uses random assignment – Participants are randomly placed in either the experimental group (gets the IV) or the control group (does not get the IV).
Ensures internal validity – It rules out other possible explanations for the results.
By following these steps, experimental designs eliminate biases and confounding variables, making them the best method for proving causation.
101
If events occur during an experiment that might influence the results, what type of threat to validity is this?
a) Maturation
b) Testing
c) History
d) Instrumentation
c) History
History can be considered a type of third variable that influences the result of an experiment, but it's more about external events (not part of your study) that might cause changes in the dependent variable (DV)
A study tests stress levels before and after an exam, but a campus fire drill happens between tests, raising stress levels.
102
What is an example of maturation (성숙) as a threat to internal validity?
a) Participants dropping out of a study
b) Participants naturally changing over time
c) Participants influencing each other
d) Participants purposely trying to skew results
b) Participants naturally changing over time
A study follows children’s reading skills for 3 years. Improvement might be due to natural growth, not the teaching method.
103
Which threat occurs when participants improve their posttest scores because they took a pretest?
a) Instrumentation
b) Testing
c) Statistical Regression
d) Selection Bias
b) Testing
pretest can act as a practice run or give participants foreknowledge about the questions or task, leading them to perform better on the posttest, not necessarily because of the actual treatment (the workshop). so this whole thing is "testing"
A study measures public speaking anxiety. Participants answer questions before and after a workshop, but the first test helps them prepare for the second.
104
If extreme scores move closer to the average on a second test, what is this called?
a) Selection bias
b) Statistical regression
c) Causal time order
d) Diffusion of treatment
b) Statistical regression
Statistical regression means that when someone has a very high or low score on the first test, they’re likely to score closer to the average on the second test. This happens naturally, and it’s not because of any special treatment or practice.
In a basketball shooting study, players who made very few or very many shots in the first test often score closer to average in the second test.
105
If some participants drop out before a study is finished, this is a threat known as:
a) Selection bias
b) Mortality (Attrition)
c) Testing effects
d) Diffusion of treatment
b) Mortality (Attrition)
A weight-loss study lasts 6 months, but 20 participants quit because they don’t see results.
ppl who stayed (might have been more motivated, had better initial results, or were less overweight to begin with. Because of this, they might have experienced more noticeable changes, which can give the false impression that the weight-loss method is more effective than it really is.)
This happens when some participants leave or drop out of the study before it’s finished. Their absence can affect the study results, because the final group might not represent the original participants, which can create bias.
106
What is diffusion of treatment?
a) Participants in different groups sharing information about the study
b) The effect of maturation on results
c) Participants dropping out of the study
d) A control group becoming demoralized
a) Participants in different groups sharing information about the study and mess up result
Diffusion of treatment happens when participants in the experimental group share what they are learning or experiencing with those in the control group. This can lead to the control group inadvertently getting some of the same treatment or benefits as the experimental group, which can mess up the results.
107
What happens in compensatory rivalry?
a) Control group participants try harder to “keep up” with the experimental group
b) Participants guess the study’s purpose
c) The researcher gives special treatment to the control group
d) The control group gives up out of frustration
a) Control group participants try harder to “keep up” with the experimental group
In compensatory rivalry, the control group works extra hard because they know they didn’t get the treatment. They try to "prove" they can still do well without it.
If one basketball team gets new shoes, the other team plays harder to prove they can still win.
108
Which method helps minimize threats to validity?
a) Ignoring possible threats
b) Random assignment
c) Using only a pretest
d) Allowing participants to choose their own groups
b) Random assignment
Random assignment helps make sure groups are similar before the experiment starts. This way, any differences in results are more likely caused by the independent variable (IV) and not something else.
In a diet study, researchers randomly assign some participants to a vegan diet and some to a regular diet to ensure fairness.
109
Which of the following correctly represents the sequence of a PSA study with a pretest and posttest?
a) Pretest -> Posttest -> 2 hours of TV with PSA
c) 2 hours of TV with PSA -> Pretest -> Posttest
b) Pretest -> 2 hours of TV with PSA -> Posttest
d) Posttest -> 2 hours of TV with PSA -> Pretest
b) Pretest -> 2 hours of TV with PSA -> Posttest
A researcher measures students’ attitudes about texting while driving, has them watch a PSA, then measures their attitudes again
110
What is the purpose of a control group in an experiment?
a) To receive a different version of the independent variable
c) To ensure the dependent variable is measured correctly
b) To serve as a comparison group that does not receive the independent variable
d) To guarantee the independent variable affects the dependent variable
b) To serve as a comparison group that does not receive the independent variable
A researcher tests if exercise improves memory. The experimental group exercises, while the control group does not.
111
Why is random assignment important in an experiment?
a) It ensures the same participants are in both the experimental and control groups
c) It eliminates the need for a control group
b) It helps ensure groups are equivalent before the study begins
d) It guarantees the independent variable causes changes in the dependent variable
b) It helps ensure groups are equivalent before the study begins
In a study on sleep and test scores, participants are randomly assigned to get either 4 hours or 8 hours of sleep before a test.
112
Which of the following is NOT a requirement for a "true" experiment?
a) Researcher controls the independent variable
c) Random assignment of participants
b) Participants choose their own groups
d) Variables are correlated
b) Participants choose their own groups
A true experiment must have random assignment and researcher control over the independent variable.
113
What is the main purpose of an experimental design?
a) To find the strongest correlation between two variables
c) To determine cause-and-effect relationships
b) To eliminate any possible bias from participants
d) To ensure that only one variable changes during the study
c) To determine cause-and-effect relationships
A researcher tests if drinking coffee improves memory by having one group drink coffee and another not drink coffee.
114
If participants in the control group feel left out and stop trying, which threat to internal validity is present?
a) Compensatory rivalry
c) Diffusion of treatment
b) Demoralization
d) Maturation
b) Demoralization Demoralization happens when control group participants feel left out because they didn’t get the treatment. This can make them lose motivation and stop putting in effort, which affects the results.
In a study on tutoring effects, students who didn’t get tutoring stop trying because they feel discouraged.
115
Which of the following is an example of "statistical regression" as a threat to internal validity?
a) People who score extremely high or low on a test tend to move toward the average on a second test
c) Participants drop out of a study before it is completed
b) People try harder when they know they are in an experiment
d) A major world event affects participants' responses
a) People who score extremely high or low on a test tend to move toward the average on a second test
A group of students scored very low on a math test. On the second test, most scored closer to average, even without extra studying.
116
How does a testing threat affect internal validity?
a) Participants become better at a test simply because they took it before
b) The measuring tool used in the study changes over time
c) Participants drop out of the study early
d) The control group is influenced by the experimental group
a) Participants become better at a test simply because they took it before
Students take a math test twice—the second time, they score higher just because they remember the questions, not because they learned more.
117
What is an instrumentation threat in a study?
a) The measuring tool or method changes between pretest and posttest
b) Participants change over time due to natural growth
c) The study loses participants before completion
d) The control group tries harder to keep up with the experimental group
a) The measuring tool or method changes between pretest and posttest
An instrumentation threat occurs when the measuring tool or method used to collect data changes between the pretest and posttest. This can cause the results to be affected by the change in measurement, rather than by the treatment or independent variable (IV).
Imagine a study measuring participants' anxiety levels using a questionnaire. If the questions on the posttest are slightly different from those on the pretest (e.g., some questions are worded differently or new questions are added), it could lead to differences in how participants' anxiety levels are measured. This could make it seem like there was a change in anxiety when, in fact, the change was caused by the different way the data was collected.
118
What is an example of selection bias in an experiment?
a) Groups are different at the start, affecting results
b) Participants drop out before the study is finished
c) Participants feel discouraged and give up
d) Participants improve naturally over time
a) Groups are different at the start, affecting results
groups being compared in an experiment are not equal at the start. This can affect the results because any differences found between the groups might be due to their initial differences rather than the independent variable (IV).
A study tests a new workout program. One group consists of athletes, while the other group consists of people who never exercise. If the athlete group shows better results, it may be because they were already fitter, not because of the workout program itself.
119
How can compensatory treatment threaten an experiment?
a) Researchers give extra help to the control group, affecting results
b) Participants drop out of the study
c) Participants perform better just by taking the test a second time
d) Participants’ extreme scores move closer to average
a) Researchers give extra help to the control group, affecting results
when researchers feel bad that the control group is not receiving the experimental treatment, so they provide extra help or resources to "compensate." This can threaten the experiment's validity because the control group may improve in ways unrelated to the actual independent variable.
A study tests a new therapy, but therapists feel bad for the control group and give them extra support, making it hard to tell if the therapy worked.
120
What does causal time order mean in an experiment?
a) The dependent variable must be measured before the independent variable is changed
b) The independent variable must come before the dependent variable
c) The dependent variable must affect the independent variable
d) The independent and dependent variables must happen at the same time
b) The independent variable must come before the dependent variable
the independent variable (IV) must come first, and the dependent variable (DV) must follow. This ensures that any change in the DV is actually caused by the IV, not the other way around.
121
What is demoralization in an experiment?
a) Participants in the experimental group perform worse because they don’t feel like they’re getting a fair chance
b) Participants in the control group get discouraged because they are not receiving the treatment
c) Participants drop out of the study because they find it too difficult
d) Participants share information about the study with each other
b) Participants in the control group get discouraged because they are not receiving the treatment
In a weight-loss study, participants in the control group might feel demoralized because they are not receiving the new weight-loss treatment like the experimental group. This feeling of unfairness could cause them to give up or not try as hard.
This is a threat to internal validity because the control group might perform worse simply due to feeling discouraged, not because the treatment (or lack of it) directly caused the difference.
