You calculate it using: observed y - predicted y
What is the residual?
The type of significance test used for the mean of a single population when the standard deviation of the population is unknown.
What is a T test?
To calculate, subtract the mean of the distribution from the observed x, then divide by the standard deviation.
What is the z-score (or standardized value)?
This should be used to simulate random assignment.
What is a random number generator, flipping a coin, etc.?
This tells us the long-term outcome of a probability distribution. It should never be rounded.
What is the expected value?
How degrees of freedom are calculated for each kind of test: t-test for means, chi-squared test for goodness of fit, t-test for slope
t-test for means: n-1
chi-squared test for goodness of fit: # of categories -1
t-test for slope: n-2
This tells us what proportion of data lies at or below a given value.
What is a percentile?
The proportion of the variation in y that is explained by the linear relationship with x.
What is the coefficient of determination (or r squared)?
Events that have no outcomes in common and can never occur simultaneously, for which the addition rule is used.
What are mutually exclusive events?
The kind of test used to distinguish an association or difference in two categorical variables from a prediction.
What a chi-squared test?
The square of the standard deviation.
What is the variance?
When a least squares regression line is used to predict a y value for an x value that is very far from all other x values in the data set.
What is extrapolation?
A kind of experimental design when individuals receive both treatments and the results are compared.
What is a matched pairs experiment?
The condition involving the population size that must be satisfied to use sigma divided by the square root of n as the standard deviation of a sampling distribution.
What is the 10% condition?
The different Large Counts Conditions for proportions and for means.
What are:
for t-test: n is greater than or equal to 30
for z-test: np is greater than or equal to 10 & n(1-p) is greater than or equal to 10
The equation of a LSRL is:
predicted test score = 60 + 3.75 (hours spent studying)
Interpret the slope of the line in context.
What is "For every one hour increase in hours spent studying, the predicted test score is expected/predicted to increase by 3.75 points." ?
The requirement for being able to generalize results to an entire population.
What is a random sample?
The probability that a person is summoned for jury duty the first time in their 5th year of being eligible when there is a 15% chance of being summoned for jury duty annually.
What is .078?
The formula for calculating the confidence interval for the slope of a LSRL.
What is:
b +/- t*(SE of b)