Independent Variable

The variable that is being manipulated in the experiment such as sunlight to a plant

A researcher studies whether caffeine affects reaction time. Participants drink either coffee or water, and then their reaction time is measured.

• What is the independent variable (IV)?

• What is the dependent variable (DV)?

IV: Caffeine (coffee vs water)

DV: Reaction time

A study finds that stress leads to poor academic performance. The researcher suggests that lack of sleep explains this relationship. What is the mediator?

Lack of Sleep (explains why stress affects performance)

A researcher finds that exercise improves mood, but the effect is stronger for younger people than older people. What is the moderator?

Age (because it changes the strength of the relationship)

A study finds that students who drink more coffee get higher grades. However, these students also tend to study more. What is the confound?

Study time (because it could explain the relationship)

A researcher studies caffeine with three groups: 0 mg, 100 mg, 200 mg. What are these called?

levels of the independent variable

A researcher tests whether social media use affects anxiety. Participants are assigned to:

• No social media

• 1 hour per day

• 3 hours per day

Anxiety is measured after one week. The researcher also notes that personality (introvert vs extrovert) changes how strong the effect is. What is the IV, DV, levels, moderator.

IV: Social use

DV: anxiety

Levels: 0hr, 1 hr, 3 hr

Moderator = persoanlity

A study shows that exercise reduces stress. The researcher finds that improved sleep explains the effect, but the effect is stronger for women than men.

• Mediator = ?

• Moderator = ?

• Mediator = sleep

• Moderator = gender

Dependent Variable (DV)

The variable that is measured in a study and is expected to change as a result of the independent variable.

Mediator

A variable that explains why or how the independent variable affects the dependent variable.

Moderator:

A variable that changes the strength or direction of the relationship between the independent and dependent variables.

Confound:

A variable that influences both the independent and dependent variables, creating an alternative explanation for the results.

Level of a Variable:

The specific values or groups of an independent variable used in a study (e.g., 0 mg, 100 mg, 200 mg caffeine)

Covariation:

Two variables change together, meaning when one variable changes, the other also changes.

Temporal Precedence:

The cause must come before the effect in time

Internal Validity (No Alternative Explanations):

The study is designed so that no other variables (confounds) can explain the results, allowing a clear cause-and-effect conclusion.

A researcher finds that people who exercise more tend to have lower stress levels. Both variables were measured at the same time.Which rule for causation is missing?

Temporal precedence
(because we don’t know if exercise came before lower stress)

A study shows that as caffeine intake increases, anxiety also increases. Which rule is demonstrated?

Covariation
(both variables change together)

A researcher conducts an experiment where participants are randomly assigned to a sleep-deprived group or a well-rested group. All other factors are controlled. Which rule is strongest here?

Internal validity (no alternative explanations)
(confounds are controlled)

A study finds that students who study more get better grades, and studying clearly happens before exams. Which rule is satisfied?

Temporal precedence
(cause comes before effect)

A researcher finds a relationship between social media use and depression, but does not control for loneliness, which could explain both. Which rule is missing?

Internal validity (no alternative explanations)
(loneliness = confound)

A study shows that therapy reduces anxiety. Participants are randomly assigned, anxiety is measured after treatment, and other variables are controlled. Which THREE rules are satisfied?

• Covariation

• Temporal precedence

• Internal validity
  ✔ You can make a causal claim

A researcher finds that ice cream sales and crime rates increase together. Which rule is present?

Covariation

A study measures stress and sleep at the same time and finds a relationship, but cannot determine which causes the other. Which rule is violated?

Temporal precedence

True Experiment

A study in which researchers manipulate an independent variable and randomly assign participants to conditions, allowing for cause-and-effect conclusions

Quasi-Experiment

A study that compares groups without random assignment, so it has less control and weaker causal conclusions

Correlational Study

A study that measures the relationship between variables without manipulating them, so it cannot determine causation.

Between-Subjects Design:

A design where different participants are placed in different conditions, and each person experiences only one condition

Within-Subjects Design

A design where the same participants experience all conditions, allowing comparisons within the same group.

Longitudinal Design

A study that follows the same participants over time, measuring changes repeatedly.

A researcher randomly assigns participants to a caffeine group or a no-caffeine group and measures reaction time.What type of study is this?

True experiment

A researcher compares stress levels between people who chose to attend therapy and those who did not. What type of study is this?

Quasi-experiment

A researcher measures hours of sleep and anxiety levels without changing anything.

Correlational study

Participants are split into three groups, each group experiences a different noise level.What design is this?

Between-subjects design

The same participants complete tasks under three different lighting conditions.

Within-subjects design

A researcher measures the same group of students’ stress levels every year for 4 years.

Longitudinal design

A researcher studies whether exercise causes weight loss by assigning participants to exercise or no-exercise groups randomly.Why can this study make a causal claim?

Because it is a true experiment with random assignment

A study finds that people who drink more coffee have higher GPA, but does not control for study time. What type of study is this AND why can’t it show causation?

Correlational study; confounds (like study time) are not controlled

A researcher tests memory using the same participants in all conditions to reduce individual differences. What design is this and why use it?

Within-subjects; controls for individual differences

A researcher compares two classrooms (one uses tablets, one does not) but cannot randomly assign students.

Quasi-experiment

Correlation

A measure of the relationship between two variable

Positive correlation:

both variables move in the same direction
(e.g., more studying → higher grades)

Negative correlation:

variables move in opposite directions
(e.g., more stress → lower sleep)

Median

The middle value in a set of ordered numbers.

Mode

The most frequently occurring value in a dataset.

Alpha (p-value)

The cutoff for statistical significance, usually .05 or .01, representing the probability results occurred by chance.

Type I Error

Rejecting the null hypothesis when it is actually true- False positive

Type II Error

Failing to reject the null hypothesis when it is actually false- false negative

Null Hypothesis

The assumption that there is no real relationship or difference between variables.

Reliability

The consistency of a measurement, meaning it produces the same results across time, items, or raters.

Validity:

The extent to which a measure or study accurately measures what it is supposed to measure.

Internal Validity

The extent to which a study supports a clear cause-and-effect relationship by ruling out alternative explanations (confounds).

External Validity

The extent to which the results of a study can be generalized to other people, settings, or situations

Face Validity:

The extent to which a measure appears (on the surface) to measure what it is supposed to measure.

Statistical Validity:

The extent to which the statistical conclusions are accurate, meaning the results are not due to chance and the analysis is appropriate.

A test gives the same results every time but does not measure what it is supposed to measure. What does it have?

Reliability (but not validity)

A scale accurately measures depression levels. What does it have?

Validity

A study has many confounding variables that could explain the results. What is low?

Internal validity

A study’s results apply to real-world settings and different populations. What type of validity is this?

external validity

A study only works in a lab and cannot be generalized. What is low?

external validity

A survey “looks like” it measures anxiety but hasn’t been tested scientifically. What type of validity is this?

Face validity

A study finds results that are statistically significant and unlikely due to chance. What type of validity is this?

Statistical validity

A study finds results that are statistically significant and unlikely due to chance. What type of validity is this?

Statistical validity

A study has a very high p-value and results may be due to chance. What is weak?

Statistical validity

A measure is consistent but inaccurate. What does it have and lack?

Has reliability, lacks validity

A study shows causation but only in a lab setting. What is high and what is low?

High internal validity, low external validity

A study has a significant p-value but many confounds. What is high and what is low?

High statistical validity, low internal validity

Placebo Group:

A control group that receives an inactive or fake treatment designed to mimic the real treatment, allowing researchers to control for expectancy effects and determine whether changes in the dependent variable are due to the independent variable rather than participants’ beliefs, thereby improving internal validity

Confederate

A person who appears to be a participant but is actually working with the researcher to intentionally influence or create a specific social situation, often used in studies involving behavior or social interaction, and typically requires deception and later debriefing.

Random Assignment:

The process of placing participants into experimental conditions by chance, ensuring that groups are equivalent at the start of the study and reducing confounding variables, which strengthens internal validity and supports causal conclusions.

Random Sampling:

The process of selecting participants randomly from a larger population, increasing the likelihood that the sample represents the population and improving external validity and generalizability of the results.

Survey Response Rate

The percentage of individuals who complete a survey out of those who were invited, where a low response rate can introduce bias and reduce how well the results represent the population, weakening external validity

PsycINFO AND Search

A search strategy that returns results containing all specified terms, which narrows the number of results and increases relevance by focusing only on studies that include every keyword.

PsycINFO OR Search

A search strategy that returns results containing any of the specified terms, which broadens the number of results and is useful for exploring a wider range of related topics.