Research Methodology Vocab

Critical Thinking

the process of using logic, analysis, and reasoning to evaluate information and make sound judgments

Confirmation Bias

when researchers look solely for evidence that supports their ideas and ignores other contradictory information

Hindsight Bias

After learning the outcome, we tend to believe that we would have foreseen the results

Overconfidence

We tend to know more than we do

Illusory Correlation

Cognitive bias where people incorrectly perceive a relationship between two unrelated or weakly related variables

Peer Reviewers

Scientific experts who evaluate a research article’s theory, originality, and accuracy

Theory

explains behaviors or events by offering ideas that organize observations

Hypothesis

expresses a relationship between 2 variables

Null Hypothesis

A default statistical statement that assumes there is no effect, no difference, or no relationship between variables

Falsifiable

The possibility that an idea, hypothesis, or theory can be disproven by observation or experiment

Operational Definition

explain what you mean in your hypothesis, how variables will be measured, and helps with replication

Replication

repeating the essence of a research study to see whether the basic finding can be reproduced

Case Study

An in-depth picture of one or a few subjects usually unique/rare phenomenon

• descriptive research, tells a story

• documentaries, interviews, etc

• findings CANNOT be applied to all cases

Naturalistic Observation

watching subjects in their natural environment

• no manipulation

• no cause and effect

Hawthorne Effect

people being watched act differently when knowing that they are being watched

Correlation

expresses a relationship between two variables, does NOT prove causation

the measure of the extent to which two factors vary together, and thus how well either factor predicts the other

Experimenter bias

An error where a scientist’s personal expectations or desires unconsciously influence the outcome of a study

Social-desirability bias

bias from people’s responding in ways they presume a researched expects or wishes

Self-report bias

bias when people report their behavior ineffectively

Sampling bias

a flaw sampling process that produces an unrepresentative sample

Wording effects

small changes in order/wording of questions can create drastic effects

Population

the group from which your participants were drawn from

Sample

must be representative of the population you want to study

Representative sample

a small group that accurately mirrors the key traits and characteristics of a larger population

Random sample/selection

process of choosing the research participants from population, occurs before assignment

Convenience sampling

collecting research from a group that is readily available

Correlational coefficients

on a scale of -1 to 1, with 0 being no correlation

• relationship gets weaker as you get closer to zero!!

Variables

anything that can vary and is feasible and ethical to measure

Scatterplot

a graphed cluster of dots, each of which represent the values of two variables

Regression towards mean

the tendency for extreme or unusual scores or events to fall back towards the average

Independent variable

whatever is being manipuated in the experiment

dependent variable

whatever is being measured in the experiment

experimental group

exposed to the independent variable

control group

group that is not exposed to the independent variable

random assignment

each participant has equal chance of being placed into any group

single blind study

research participants are ignorant about whether they have received the treatment or a placebo

double blind study

both the research participants and research staff are ignorant about whether research participants receive treatment/placebo

placebo

a fake treatment

Placebo effect

participants’ expectations that the “treatment” will cause the hypothesized effect

Confounding variables

anything that could cause a change in a dependent variable that is not the independent variable

Experimental bias

not a “conscious” act, when a researcher’s unconscious expectations or flawed study designs skew the results of an experiment

Validity

the extent to which a test or experiment measures or predicts what it’s supposed to

Non-Experimental Method

AKA descriptive, to observe and record behavior

• done through case studies, surveys, observations

• no control of variables, single causes may be misleading

Correlational

to detect naturally occurring relationships and to assess how well one variable predicts the other

• computing statistical association, sometimes among survey responses

• cannot specify cause and effect

Experimental

to explore cause and effect

• manipulating one/more factors + uses random assignment to eliminate preexisting differences among subjects

• maniputes independent variables

• sometimes not possible; results may not generalize to other contexts

Institutional Review Boards

A group that reviews experiments to ensure they are ethical

Voluntary participation

you cannot be forced to do an experiment

Protect from harm

minimal risk to physical and mental health

Informed Consent

you must be aware of what’s happening in the experiment and sign off

Informed Assent

consent for people under 18 from their guardians

Confidentiality

keep information private

Debriefing

Scientists have to inform you of the results

use of deception

the deception must have a reason and you’re told about it after the experiment

role of confederates

an actor or member of research that acts to be a regular participant in an experiment

can’t cause harm, must be told about them after an experiment

Descriptive Statistics

short summaries that describe sets of data

Percentile Rank

the percentage of scores that are less than a given score

Standard deviation

the average variance of scores from the mean

Inferential statistics

can the finding be applied to the larger population from which the sample was selected? related to statistical significance

Meta-analysis

combining the results of multiple studies to create a more accurate result

Statistically significant

how likely it is that a result occurred by chance

Effect size

the strength of the relationship between two variables

• the larger the effect size, the more one variable can be explained by the other