Scatterplot with a y^ overlay in context

make the scatterplot and add equation + equation in context

correlation coefficient (r) in context

The correlation coefficient r = ____ indicates a (weak/moderate/strong) (positive/negative) linear relationship between (var 1) and (var 2) in (Measurement/description)

coefficient of determination (r^2) in context

The coefficient of determination r=__ indicates that approx (r in % form) of the variation using (var 1) to predict (var 2) is accounted for by the least squares regression line while using (var 1) to predict (var 2), the other (100-r%) is unaccounted for

Slope of the least-squares regression (b) in context

The predicted (measure) goes up/down (#) every ___ (measure)

find residual --> L2 - Y1(L1) Scatterplot --> x: L1 y: L3

6 description first sentence

The residual plot appears (homo/hetero) in nature.

This shows that the residuals are evenly and randomly scattered about a mean of 0 indicating constant error variants, signaling a reliable model.

This shows a non-constant spread indicating a violation of regression assumptions and can lead to a unrealiable statistical inference

standard deviation of the residuals (SDres) in context

SDres = ___ indicates that the actual (var) is typically (SD) away from the number predicted by the least squares regression line with x = (x-variable)

outliers and influential points (high-leverage)

8 description outlier beginning + correlation

Point # is an outlier because it has a large residual. The point for point # makes the correlation closer to 0 because it decreases the strength of what would otherwise be a moderately strong/weak positive/negative association.

8 description outlier slop + y-int.

Because this point's x coordinate is very close to mean x, it won't influence the slope very much. However, it will make the y-intercept increase/decrease because its y coordinate is so large compared to the rest of the values.

8 description influential beginning + correlation

Point # is a influential point because it has a much larger x-value than the other points. Because the point for point # is in the pos/neg linear pattern formed by most of the data values, it will make the correlation closer to 1.

8 description influential slope

Also, because the point is likely to be below the least-squares regression line, it will "pull down" the line on the right side, making the slop closer to 0.

Help

Options

focusNode

Didn't know it?
click below

Knew it?
click below

Don't Know

Remaining cards (0)

Know

retry

shuffle

restart

0:00

Embed Code - If you would like this activity on your web page, copy the script below and paste it into your web page.

Normal Size Small Size show me how

AP STATS UNIT 2

Term	Definition
1.	Scatterplot with a y^ overlay in context
1 description	make the scatterplot and add equation + equation in context
2.	correlation coefficient (r) in context
2 description	The correlation coefficient r = ____ indicates a (weak/moderate/strong) (positive/negative) linear relationship between (var 1) and (var 2) in (Measurement/description)
3.	coefficient of determination (r^2) in context
3 description	The coefficient of determination r=__ indicates that approx (r in % form) of the variation using (var 1) to predict (var 2) is accounted for by the least squares regression line while using (var 1) to predict (var 2), the other (100-r%) is unaccounted for
4.	Slope of the least-squares regression (b) in context
4 description	The predicted (measure) goes up/down (#) every ___ (measure)
5.	residuals
5 description	find residual --> L2 - Y1(L1) Scatterplot --> x: L1 y: L3
6.	residual plot with analysis
6 description first sentence	The residual plot appears (homo/hetero) in nature.
6 description homo	This shows that the residuals are evenly and randomly scattered about a mean of 0 indicating constant error variants, signaling a reliable model.
6 description hetero	This shows a non-constant spread indicating a violation of regression assumptions and can lead to a unrealiable statistical inference
7.	standard deviation of the residuals (SDres) in context
7 description	SDres = ___ indicates that the actual (var) is typically (SD) away from the number predicted by the least squares regression line with x = (x-variable)
8.	outliers and influential points (high-leverage)
8 description outlier beginning + correlation	Point # is an outlier because it has a large residual. The point for point # makes the correlation closer to 0 because it decreases the strength of what would otherwise be a moderately strong/weak positive/negative association.
8 description outlier slop + y-int.	Because this point's x coordinate is very close to mean x, it won't influence the slope very much. However, it will make the y-intercept increase/decrease because its y coordinate is so large compared to the rest of the values.
8 description influential beginning + correlation	Point # is a influential point because it has a much larger x-value than the other points. Because the point for point # is in the pos/neg linear pattern formed by most of the data values, it will make the correlation closer to 1.
8 description influential slope	Also, because the point is likely to be below the least-squares regression line, it will "pull down" the line on the right side, making the slop closer to 0.

Created by: lilli.spears1

"Know" box contains:
Time elapsed:
Retries: