Psychology Unit 0: Research Methods and Data Interpretation

Peer Reviewers

scientific experts who evaluate a research article's theory, originality, and accuracy

Theory

an explanation using principles that organizes observations and predicts behaviors/events

Hypothesis

a good theory produces testable predictions

Falsifiability

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

Operational definition

carefully worded statement of the exact procedures used in a research study and how exactly the variables are measured

Replication

repeat original observations with different participants

Case Study

non-experimental technique in which one individual or group is studied depth, hoping to reveal universal principles

Naturalistic Observation

non-experimental technique of observing and recording behavior in naturally occurring situations with out trying to manipulate and control the situation

Survey

non-experimental technique for obtaining self-reported attitudes or behaviors of a particular group, usually by questioning a representative, random sample of group

Social desirability bias

tendency to respond to a question in the way they think a researcher expects or wishes

Self report bias

tendency for people to not accurately report their behaviors

Sampling bias

flawed sampling process that produces an unrepresentative sample

Representative Sample

sample from large group that accurately represents the characteristics of a larger population

convenience sampling

collecting data from a group that is readily available

Random sample

sample which fairly represents population due to equal inclusion across members

Population

the group being studied and samples being drawn from them

Correlation

extent to which 2 factors or variables vary together, how well either factor predict the other

Correlation coefficient

statistical index of the relationship between 2 things

Variable

anything that can vary and is feasible and ethical to measure

Scatterplots

graphed cluster of dots, each of which represents the values of 2 variables. The slope of the points suggests the direction of the relationship between the 2 variables. The amount of scatter, suggest the strength of the correlation (little scatter indicates high correlation).

Positive correlation

variables in scatterplot rise and fall together (directly related)

Negative correlation

variables in a scatterplot are inversely related. One variable rises while other falls.

Directionality problem

can not tell us which variable is the cause and which is the effect

Third-variable problem

separate "third" variable could actually be the cause

Correlation and causation

correlation does not equal causation

Illusory correlation

perceiving a relationship where none exists, or perceiving a stronger-than-actual relationship

regression toward the mean

tendency for extreme or unusual scores or events to fall back (regress) toward the average

Experiment

enable researchers to isolate the effect of one or more factors

experiment group

group that receives treatment (independent)

Control group

group that does not receive treatment, comparison for effect

Random assignment

assigning participants to either the control or experimental group by chance, minimizing preexisting differences between groups

Confounding variable

influences both dependent and independent variables

Placebo

fake treatment

Single-blind procedure

research participants are unaware (blind) about whether or not they received the treatment or placebo

Double blind procedure

both the research participants and staff are unaware (blind) about whether the research participants have received treatment/placebo

Placebo effect

participant believes they have received treatment and experience therapeutic relief due to expectations

independent variable

factor is manipulated, variable whose effect is being studied

Experimental bias

when researchers may unintentionally influence results to confirm their own beliefs

Dependent variable

outcome that is measured in an experiment

Validity

the experiment tests what it is supposed to test

Quantitative Research

uses numerical data to represent degrees of variable

Likert Scale

responses fall on a continuum (strongly agree/disagree)

Qualitative Research

rely on in-depth, narrative data

structured interview

understand the causes and consequences of someones behavior

informed consent

participants are given enough information about a study to enable them to choose whether they wish to participate

confederate

people who seem to be participants but actually are part of research team/out-group

debriefed

post experimental explanation of a study, including its purpse and any deceptions

IRB

protecting welfare, rights, and privacy of human subjects

informed assent

an agreement by an individual not competent to give legally valid informed consent

Descriptive statistics

numerical data used to measure and describe characteristics of groups; central tendency and measures of variation

Histogram

bar graph depicting a frequency distribution (labeling only - axis can be misleading - check range)

Measure of central tendency

a single score that represents a whole set of scores

Mode

most frequently occurring score(s) in a distribution

Mean

average of scores

Median

middle score in distribution, half above, half below

Percentile Rank

percentage of scores that are lower than a given score

skewed distribution

a representation of score that lack symmetry around their average value; usually caused by high or low

Measures of distribution

single number of central tendency does not tell us about the amount of variation in the data (how similar/diverse scores are)

Range

difference between the highest and lowest scores of distribution

Standard deviation

computed measure of how much scores vary around the mean score

Normal curve

symmetrical, bell-shaped curve that describes the distribution of many types of data, most scores fall near the mean

inferential statistics

numerical data that allow one to generalize - to infer probability of something being true to a population

Meta analysis

analyzing bigger samples, bigger samples are better than smaller ones

Null hypothesis

states that there is no relationship between the two variables being studied

Statistical significance

statistical statement of how likely it is that an obtained result occurred by chance, assuming there is no difference between population being studied

alternative hypothesis

theory that the observations are related (not independent) some how

p-value

statistical measure indicating the probability result

effect size

strength of the relationship between two variables, the larger the effect size, the more can be explained by the other