PSYCH - FULL UNIT 0 - RESEARCH DESIGN

HYPOTHESIS

a tentative explanation, must be falsifiable + able to be supported/rejected

QUALITATIVE DATA

descriptive data (eye color)

QUANTITATIVE DATA

numerical data, ideal + necessary for stats

POPULATION

everyone the research could apply to

SAMPLE

the people/person specifically chosen for your study

CORRELATION

identify relationship between 2 variables

• advantage: useful when experiments are unethical

• disadvantage: doesn’t equal causation

DIRECTIONALITY PROBLEM

which direction does the correlation go? (depression causes low self-esteem + vise versa)

3RD VARIABLE PROBLEM

diff variable is responsible for relationship

STRONG RELATIONSHIPS

tight clusters on graph

EXPERIMENTS

purposefully manipulate variables to determine cause/effect

• advantage: only type that establishes cause/effect

• disadvantage: can be unethical, too artificial

INDEPENDENT VARIABLE

purposefully altered by researcher to look for effect

EXPERIMENTAL GROUP

received the treatment

CONTROL GROUP

placebo, baseline

DEPENDENT VARIABLE

measured variable, is depends on the independent variable

PLACEBO EFFECT

any observed effect on a behavior that is “caused” by the placebo

DOUBLE-BLIND

experiment where neither participant or experimenter are aware of which condition people are assigned to (drug studies)

SINGLE-BLIND

only participant is blind - used if experiments can’t be blind

CONFOUND

error/flaw in study that is accidentally introduced

RANDOM ASSIGNMENT

assign to either control or experimental group at random - increase chance of equal representation across groups, allows you to say cause/effect

NATURALISTIC OBSERVATION

observe ppl in their natural settings

• advantage: real world validity

• disadvantage: no cause/effect

CASE STUDY

studies 1 person (usually) in great detail

• advantage: collect lots of info

• disadvantage: no cause/effect

META-ANALYSIS

combines multiple studies to increase sample size + examine effect sizes

DESCRIPTIVE STATISTICS

show shape of the data

MEAN

average

MEDIAN

middle # in a set of data

MODE

# that occurs most often

BIMODAL

has 2 modes - usually indicates good bad scores

SKEWS

created by outliers

NEGATIVE SKEW

mean is to the left (neg side), mode is to the right

POSITIVE SKEW

mean is to the right

RANGE

distance between smallest + biggest #

STANDARD DEVIATION

average amount the scores are spread from the mean (bigger # = more spread)

INFERENTIAL STATISTICS

establishes significance (meaningfulness)

STATISTICAL SIGNIFICANCE

results not due to change, manipulation caused the difference

EFFECT SIZE

data has practical significance/magnitude of impact, bigger = better

REGRESSION TOWARDS THE MEAN

as samples size increases, it gets closes to a true average (minimizes impact of outliers)

PERCENTILE RANK

% of scores in a distribution that are less than a given score (90th percentile = 90% of ppl are below u)

CONFIDENTIALITY

names kept secret

INFORMED CONSENT

must agree to be part of study

INFORMED ASSENT

minors + parents must agree to be part of study

DEBRIEFING

must be told the true purpose of study (done after for deception)

DECEPTION

must be warranted

NO HARM

mental/physical

SURVEYS

usually turned into correlation, subject to self-report bias

SURVEY ERRORS

• social desirability: ppl lie to look good

• wording effects: how u frame the question can impact answers

RANDOM SAMPLE

method for choosing participants for your study, everyone has a chance to take part, increases generalizability

REPRESENTATIVE SAMPLE

sample mimics the general population (ethnic, gender, age)

CONVENIENCE SAMPLE

select participants on availability, less representative + generalizable

SAMPLING BIAS

sample isn’t representative due to convenience sampling

CULTURAL NORMS

behaviors of a particular group can influence research results

EXPERIMENTER BIAS/PARTICIPANT BIAS

experimenter/participant expectations influence the outcome

COGNITIVE BIAS

bias in thinking/judgement

CONFORMATION BIAS

find info that supports our preexisting beliefs

HINDSIGHT BIAS

“i knew it all along”

OVERCONFIDENCE

overestimate our knowledge/abilities

RESEARCH NEEDS

peer review + adequate samples sizes