Module 2: NHST

α-level

the probability of a Type l error esist is 0.05 or 5%

β-level

the maximum acceptable probability of a Type ll error 0.2 or 20%

alternative(experimental) hypothesis (H₁ )

the hypothesis that an effect will be present

Bonferroni correction

central limit theorem

as samples get large (usually greater than 30) the sampling distribution has a normal distribution with a mean equal to the population mean

confidence interval

boundaries within which we believe the population value will fall in

degrees of freedom (df)

the number of scores used to compute the total adjusted for the fact that we’re trying to estimate the population value

experimental hypothesis

familywise or experimentwise error rate

fit

the degree to which a statistical model represents the data collected (good, moderate, poor)

interval estimate

likelihood

linear model

maximum likelihood

method of least squares

null hypothesis (H_o )

an effect is absence

one-tailed test

a statistical model that tests a directional hypothesis

ordinary least squares

parameter

constants that represent some fundamental truth about the variables in the model

point estimate

population

all of an entities or group

power

the ability of a test to detect an effect

sample

smaller subset of the population

sampling distribution

the frequency distribution of sample means from the same population

sampling variation

samples vary because they contain different members of the population

standard error or standard error of the mean (SE)

the standard deviation of sample means

test statistic

the ratio of effect relative to error

two-tailed test

a statistical model that tests a non directional hypothesis

type l error

we believe there is an effect in the population when there isn’t (false positive)

type ll error

we there is no effect in the population when there is