Rapid review

___% of the variability in (y variable) can be explained by the association between (y variable) and (x variable).

Interpretation of R-Squared

The correlation coefficient (r) describes the strength and direction of a linear relation. Strong means that the data points tend to be close to the values predicted by the __________.

line of best fit.

The model predicts that (y) will change by approximately __________ as (x) increases by 1 (units) on average.

the slope.

Actual – predicted (A - P) OR __________

observed – expected.

I am _____% confident that the interval __________ captures the _____ (POPULATION PARAMETER mean/proportion/slope of regression of .... steal the wording from question).

Confidence Interval

If samples of size n were collected from the population over and over again, _____% of the intervals generated from these samples would capture the _____ (POPULATION PARAMETER mean/proportion/slope of regression of .... steal your wording from the question).

Confidence Level

Because zero (is/is not) on the interval, the difference (is not/is) statistically significant.

Two Sample Confidence Interval conclusion.

The first part of the conclusion of a statistical test states the p-value and whether or not you __________ the null.

reject.

A Type I Error occurs when you reject the null but the null is __________.

TRUE.

You can reduce the probability of a Type I error by __________ alpha.

lowering.

A Type II Error occurs when you fail to reject the null but the null is __________.

FALSE.

To increase the power of a test, you can __________ the sample size.

increase.

GAPS for describing linear associations stand for __________, OUTLIERS, ASSOCIATION, LINEAR?, STRENGTH.

Gaps.

If an experiment uses RANDOM ASSIGNMENT to treatments, you can make __________ claims.

causation.

Median and IQR are resistant to __________ (and skew).

extreme values.

A good experiment must have RANDOM, REPLICATION, and __________.

CONTROL.

The control group does not receive an actual treatment but may receive a __________ treatment.

placebo.

The probability of A given B is represented as __________.

P(A|B).

Expected Value in discrete probability distributions equals the sum of (each outcome x's its __________).

probability.

Degrees of freedom for our T test for mean is __________.

n - 1.

When you know the % you want and need the z score along the x-axis, you use __________.

INVNORM.

As sample size increases, Margin of Error __________.

DECREASES.

A p-value is the probability of getting your (sample results/test statistic) or ones that are __________ when the null hypothesis is true.

more extreme.

Statistical significance means our observed difference is too large to be explainable by __________ alone.

random chance.

The probability of a Type I error is shown when the p-value is __________ than alpha.

less.

The slope of regression degree of freedom is __________.

n - 2.

To study the distribution of a population vs sampling distributions, the key is the change in __________.

standard deviation.