AP Stats - Sentence Stems and Flashcards

Shape (using SOCS to describe distribution)

“The graph is roughly (skewed L/R, symmetric, uni/bimodal)”

Outliers (using SOCS to describe distribution)

“There are no apparent outliers / (the graph appears to have an outlier at (#) (SOCS)”

Center (using SOCS to describe distribution)

“The graph's center is (roughly) at (mean or median)”

Spread (using SOCS to describe distribution)

“The (units in context) vary from (min) to (max)”

Direction (using DOFS to describe a scatter plot)

“The direction of association between (x variable) and (y variable) is (positve/negative)”

Outliers (using DOFS to describe a scatter plot)

“There are no apparent outliers / (the graph appears to have an outlier at (#) (DOFS)”

Form (using DOFS to describe a scatter plot)

“The form is (linear/curved/has gaps)”

Strength (using DOFS to describe a scatter plot)

“The association appears to be (strong/moderate/weak)”

Interpreting r (correlation coefficient)

There is a (strong/moderate/weak) (positive/negative) linear relationship between (x variable) and (y variable)”

Interpreting r² (coefficient of determination)

“(r²)% of the variation in response variable can be explained by the linear relationship with explanatory variable”

Interpreting b (slope of least squares regression)

“For each additional (x variable), the (y variable) is predicted to increase/decrease by (b)”

Interpreting a (y-intercept of least squares regression)

“At a (x variable), of zero units our model predicts (#) in (y variable)”

Interpret a residual plot

“There is (an/no) obvious curve pattern in the residual plot, so a linear model (is not/is) appropriate”

Interpreting probability (using law of large numbers)

“After many, many (trials), the percent of (successes) will approach (α)%”

Identifying a binomial distribution (BINS)

Binary (success or failure), Independent trials (previous trials don’t affect future), Number of trials is fixed (n = _), Same probability of of success (p = _)

Identifying a geometric distribution (BINS)

Same as binary. However, instead of fixed trials, it is meausuring # of trials until success

Contructing confidence interval

We want to estimate (p/μ) = true (proportion/mean) of (parameter in context) with (α)% confidence. We will use a one sample (z/t) interval for (p/μ)

Interpreting confidence interval

We are (α)% confident that the interval from (lower bound) to (upper bound) captures are true (parameter in context)

Interpreting confidence level

If we take many, many samples and calculate a confidence interval for each, about (α)% of them will capture the true (proportion/mean) of (parameter in context)

Constructing a significance test

We will use a 2 sample (z/t) test for (p1 - p2 / μ1 - μ2) . Let (p1 - p2 / μ1 - μ2) = true difference of (proportion/mean) of (parameter in context)

Interpreting p-value (less than α)

Since the p-value = (#) is less than α = (#), we reject H₀. There is convincing evidence to support H_A

Interpreting p-value (greater than α)

Since the p-value = (#) is greater than α = (#), we fail to reject H₀, there is not convincing evidence to support H_A

Type I error (False positive)

Reject H₀ when it’s true

Type II error (False negative)

Fail to reject H₀ when it’s false

Hypotheses for GoF test

H₀: The claimed distribution of (item) is true. H_A: The claimed distribution of (item) is not true

Hypotheses for Independence/Association

H₀: there is no association between (item) and (item). H_A: There is an association between (item) and (item)

Hypotheses for Homogeneity

H₀: There is no difference in distribution of (item) and (item). H_A: There is a difference in distribution of (item) and (item)