276 FINAL THANK GOD

nominal

categorical, no values

ordinal

categorical with rankings,

interval

equal intervals, temperature

ratio

true zero, equal intervals, order, weight

p-value

reject null when greater than or equal to .05

parametric tests

when distribution is normal, t-test and ANOVA

nonparametric tests

when you cant assume normal distribution, chi square

test for difference

chi square, t test, anova

test for relationships

simple regression, correlation, multiple regression

t test requirements

categorical IV, continuous DV, normal distrubution, parametric

independent t test

compare two groups at the same time

paired sample t test

compare means of a group at different times

anova requirements

two or more groups, nominal IV, continuous DV, F symbol

between subjects design

each participant measured at only one level of only one condition

within subjects design

each participant exposed to every condition

validity

the degree to which a study accurately measures what it intends to measure

Reliability

the consistency and repeatability of findings or measurements

Measures of central tendency

Mean, median, mode

Measures of dispersion

Range, standard deviation, variance

correlation

two continuous variables moving together, little r

regression

two or more continuous variables, prediction and explains changes

strong correlation coefficients

.8 to 1

correlation assumptions

continuous variables, linear relationships, normal distribution, no outliers

multiple regression

one DV and multiple IVs

measures of shape

symmetry, skew, modality, kurtosis

kurtosis

how peaked the distribution is

leptokurtic

high peak, majority of data in one or two points

platykurtic

lowest, looks flat

mesokurtic

normal distribution

control group

group where variable is not being tested

treatment group

receives treatment or intervention being studied

deductive research

starts with a theory, quantative

inductive research

starts broad then makes theories, qualitative

type 1 error

false positive

type 2 error

false negative