Interpretation

AP stats interpretations

Interpret r

There appears to be a [ weak / moderate / strong ] [ positive / negative ] linear relationship between explanatory variable and response variable.

Interpret slope(b)

As explanatory variable increases by 1 unit, predicted response variable increases/decreases b units

Interpret y—intercept(a)

If explanatory variable is 0 units, the predicted response variable is a units.

Standard error of residuals (s)

When using this model, a typical predicted value of response variable will differ from the actual value by about s units.

Interpret coefficient of determination ( r2 ):

“r2 percent of the variation in response variable can be explained by its linear relationship with explanatory variable.“

Interpret residual

The model [ overpredicted / underpredicted ] by a units

Interpret INTERVAL:

I am confidence level% confident that the interval from lower bound to upper bound contains the true [proportion / mean /diff of props/ diff of means/ mean diff/slope of regression line ] [in context]

Interpret LEVEL

If we took many samples and constructed their confidence intervals, about confidence level% of the resulting confidence intervals would contain the true [ proportion / mean /difference of proportions/ difference of means/ slope ] [in context].“

Interpret p-value

If the null hypothesis of null is true, the probability of getting a result [as extreme or more extreme/as small or smaller/as larger or larger] than the one observed in our sample by chance is about. p-value

Power

If the alternative hypothesis is true, the probability of rejecting the null in favor of the alternative is [Power].

Expected value

If we were to do this many times, on average we would be successful about b times.

Standard Deviation

A typical context differs from the mean by about s.