Stats Chapter 10: Regression

What is the purpose of regression analysis?

To predict one variable when another correlated variable is known

Regression uses the relationship between variables to:

make predictions

The stronger the correlation, the _____ the prediction.

more accurate

Regression predicts:

Y from X

The regression equation is:

Ŷ = bX + a

Ŷ represents:

the predicted value of Y

X represents:

the known value used to make a prediction

b represents:

the slope

a represents:

the y-intercept

The y-intercept is:

where the regression line crosses the y-axis when X = 0

The slope indicates:

how much Y changes for every one-unit increase in X

The regression line is called:

the least squares regression line

The least squares regression line is the line that:

best fits the data points

Regression requires:

a correlation between variables

A stronger correlation produces:

more accurate predictions

A weak correlation produces:

less accurate predictions

Which correlation would produce the best predictions?

the correlation furthest from zero

Regression uses which variable to make predictions?

X

Regression predicts which variable?

Y

In the equation Ŷ = bX + a, which value is multiplied by X?

b

In the equation Ŷ = bX + a, which value is added at the end?

a

The components of a regression equation are found in which SPSS table?

Coefficients table

In SPSS output, the slope is labeled as:

b

In SPSS output, the y-intercept is labeled as:

a

A positive slope indicates:

as X increases, Y increases

A negative slope indicates:

as X increases, Y decreases

If the slope equals zero:

the regression line is horizontal

Regression is used to:

make predictions, not determine causation

Regression does not prove:

causation

A good predictor variable should have a _____ correlation with the outcome variable.

strong

Which regression prediction is most accurate?

the one based on the strongest correlation

If r = -.80, regression predictions will be:

more accurate than if r = .30

The sign of the slope indicates:

the direction of the relationship

A positive correlation should produce a _____ slope.

positive

A negative correlation should produce a _____ slope.

negative

To predict Y, substitute the known value into:

X

The predicted value obtained from a regression equation is called:

Ŷ (Y-hat)

Regression and correlation both require:

paired scores

The least squares regression line minimizes:

prediction error

Regression predictions are exact only when:

r = ±1

As r approaches 0, regression predictions become:

less accurate

The best regression model is based on:

the strongest correlation