Chapter 7: Linear Regression Flashcards
1
Q
Regression definition go!
A
- uses relationship between variables for prediction
- two variables are involved….the predictor and the criterion
- variables are not equal
2
Q
Least square criterion?
A
Y prime= predicted y value
Y= observed Y value
Y-Y prime = prediction error for each data point
3
Q
Least Squares regression line?
A
- line that minimizes total prediction error
- all vert distances should be in their absolute min
- only one line….
4
Q
Least squares regression line formula?
A
- Y'= byX+ay Y'= predicted value by= slope ay= y-axis intercept for min error in y X= any value of x
5
Q
How to make the regression line?
A
solve Y’ for the lowest and highest x values.
- plot the value and connect the two points.
calc y int and connect line to the int
6
Q
What is the best predictor of Y???
A
the regression line
7
Q
Prediction errors?WTF?
A
- the weaker the relationshup the more the scores vary from the regression line
the stronger the regression line =the closer
8
Q
Size wise what do you want the standard error of the esitmate to be?
A
- want it to be small
9
Q
Characteristics of the standard error of the estimate?
A
- treat it like standard deviation for predictions of percents..
+1/-1 = 68%
+/- 2= 95%
+/- 3= 99%
10
Q
Homoscedasticity ?
A
constant variance
- basing std error on the spread
- best case
11
Q
Heteroscedasicity??
A
- non constant variance
- worst case
- predictions will not rep well
- cone shaped