Stats 1045 Vocab 4 Flashcards

1
Q

Ecological Correlations

A

Correlations based on rates or averages, often used in political science or sociology, that tend to over-state the strength of an association.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

Correlation Coefficient

A

A pure number, without units, that is not affected by changes of scale.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

Association

A

What correlation ACTUALLY measures (contrast this with the next question before you answer!).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

Causation

A

What correlation DOES NOT necessarily measure, but is often confused to measure.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Graph of Averages

A

A scatter plot that shows the average value of Y for each value of X.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Regression Fallacy

A

The incorrect notion that the regression effect is due to some real-world cause or force rather than just the spread in the data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

Regression Line

A

A plot of all regression estimates, created using the regression method, that lie on the same line.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

Error (in regression prediction)

A

The name of the value that occurs in regression predictions when we perform the following subtraction: (Actual y-value) - (predicted y-value).

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

R.M.S. Error For Regression

A

This value indicates how far typical points are above or below the regression line.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Square root of

A

The equation for finding the R.M.S. error for regression.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

Residual

A

Another name for prediction errors in regression.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

Residual Plot

A

The diagram that is made when we transfer each point on a scatter diagram to a new graph that replaces all the y-coordinates with their residual values.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

Homoscedastic

A

Concerning a scatter plot, we use the phrase “football shaped” in place of this more technical term.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

Heteroscedastic

A

The technical word that means all the vertical strips in a scatter plot do NOT have the same scatter.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

The least-squared line

A

A name used for the regression equation that emphasizes the fact that the regression equation minimizes the r.m.s error.

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

Slope and Intercept

A

The two descriptive statistics that are used to specify the regression line.

17
Q

The regression equation

A

The name of the equation for the regression line

18
Q

Y=Slope^X+intercept

A

How the formula for the regression line of y on x is written.

19
Q

Multiple Regression

A

A regression technique that involves using more than one x-variable to predict the value for the y-variable. This technique is mentioned in the reading in section 1 of chapter 12 (pg 209) and again in section 3.