Exam 3 Flashcards
follows a bell-shaped curve using 2 parameters, mean and standard deviation, yo distinguish one normal curve from another
normal distribution
has mean 0 and standard deviation equal to 1
N(0,1)
standard normal distribution
how do you find a z score for a normal distribution?
sample stat - null / standard error
what is the central limit theorem?
for random samples with sufficiently large sample size, the distribution of many common sample statistics can be approximated with a normal distribution
where is the shape of a normal distribution centered at?
population mean
if a randomization distribution is normally distributed, N(__, __)
N(null value, SE)
the t-distribution shape is ____ and is centered at _____
bell-shaped
0
when do you use theoretical methods?
when sample is large
n>30, or n>50 if skewed
or
population data is normally distributed
when can we use the difference in two proportions?
when the successes and failures for each group is > 10
when can you use a confidence interval or hypothesis test for a difference in means?
n>/ 30 if not skew
n>/50 if skew
data is symmetrical
what test do you use when you have one categorical variable and many groups?
chi square goodness of fit
what test do you use when you have 2 categorical variables and many groups?
chi square test for association/independence
how do you find an expected value for a chi square goodness of fit test?
n(p)
n = sample size
p = proportion for that specific group
how do you find a chi square statistic?
(observed-expected)^2 / expected
assumption/condition for a chi square goodness of fit test for one categorical variable
expected count is larger than 5 for all groups
what is the null hypothesis for a chi-squared test for independence?
variables are not associated/variables are independent
what is the alternative hypothesis for a chi-squared test for independence?
variables are associated/variables are dependent
when can you use a chi-squared test for independence?
when expected counts are > 5
expected count for a chi-squared test of independence =
(row total x column total) / sample size
a one way ANOVA uses what variable(s)?
one quantitative and one categorical
what is the null and alternative hypothesis for a one way ANOVA?
Ho: all means are the same
Ha: at least one mean is different
when can you use a one way ANOVA?
sample size is large enough that n>30 or n>50 if skewed
data is normally distributed
equal variance (no standard deviation per group is more than 5x the other)
total variability = _____ + _____
variability between groups + variability within groups?
what is the test statistic for a one way ANOVA?
F = between group variability/within group variability
higher F = ____ difference, ____ Ho
more difference
reject Ho
what is a pairwise t-test?
a follow up test from an ANOVA that tests the difference in two means for each pair of samples/groups
