inferential statistics pt.2 (14c)

independent t test

statistic used to determine if the means of 2 independent samples are significantly different

<30

t tests are used for sample sizes __________

william sealy gosset

inventor of the independent t test

(m2 - m1)/sqrt((s²1/n1)+(s²2/n2)), means of 2 samples, standard deviation, sample sizes

t = __________, where m2 and m1 = __________, s²1 and s²2 = __________, and n1 and n2 = __________

variability, size of samples

the t formula considers __________ and __________

state hypotheses and specify significance level, conduct study and calculate t statistic, determine probability by comparing to a sampling distribution of t’s, decide whether to accept or reject the null

4 steps for a t test

n1 + n2 - 2

degrees of freedom (df) = __________

whether the IV affects the DV

two-tailed/non-directional hypothesis

whether the IV increases/decreases the DV

one-tailed/directional hypothesis

type i error

occurs when the null hypothesis is rejected, but it is actually true in the real world

test everyone in the population

we can never know if a type i error was made unless we __________

level of significance, alpha level

the probability of making a type i error is equal to the stated __________ or __________

false positive, IV has an effect on the DV when it really doesn’t

a type i error is like a __________, i.e. saying that the __________

1 - alpha

the probability of not rejecting the null hypothesis when it is actually true is __________

type ii error

occurs when the research hypothesis is true but the researcher fails to reject the null hypothesis in the study

false negative, there is no effect when there really is one

a type ii error is like a __________, i.e. concluding that __________

beta, hard to know

the probability of making a type ii error is called __________; the exact probability is __________

1 - beta

the probability of correctly rejecting the null hypothesis when it is not true is __________

power

the probability of correctly rejecting the null when it should be rejected is called the __________ of a statistical test

1 - beta

power = __________

decreases, direct control over

when beta increases, power __________; although a researcher does not have __________ beta and power

alpha level, sample size, effect size

3 factors affecting beta and power

decreases, increases

if alpha level increases, beta __________ and power __________

decreases, increases

if sample size increases, beta __________ and power __________

decreases, increases

if effect size increases, beta __________ and power __________

parametric tests

statistical tests that assume data follows a specific distribution and require interval or ratio data

analysis of variance (ANOVA), t tests

2 examples of parametric tests

non-parametric test

statistical tests that can also be used with nominal or ordinal data

wilcoxon signed-rank test, chi square

2 examples of non-parametric tests

analysis of variance (ANOVA)

statistical method used to analyze the results of factorial designs with 2 or more groups, to determine if there are significant main effects and/or interactions

f statistic

a value from an ANOVA or regression analysis that tests if the means between populations are significantly different

wilcoxon signed-rank test

non-parametric test that analyzes 2 groups, like an independent t test but with ordinal data

interval, ratio, less statistical power

non-parametric tests can also be used with __________ or __________ data, but have __________ compared to parametric tests

chi square

non-parametric test used to analyze nominal data

reliable, there is a small chance that we are wrong

if a statistical test is significant, it means we are confident that the effect is __________, i.e. __________

the size of the effect

significance of a statistical test does not indicate the __________

effect size

assesses the magnitude of the experimental effect

cohen’s d

statistic used to evaluate the relative size of the mean difference compared to variability within groups

mean difference, variability

cohen’s d evaluates the relative size of the __________ compared to __________ within groups

t formula

cohen’s d is similar to the __________

small, medium, or large

cohen’s d categorizes effects as __________