Chapter 4

Question 1

data in which two variables are measured on each individual

Answer 1

bivariate data

Question 2

graph that shows the relationship between two quantitative variables measured on the same individual - represented by points

Answer 2

scatter diagram

Question 3

when above-average values of one variable are associated with above-average values of the other variable (or below/below)

Answer 3

positive association

Question 4

measure of the strength and direction of the linear relation between two quantitative variables - not resistant to outliers

Answer 4

linear correlation coefficient

Question 5

relation that creates a U shape on the scatter diagram

Answer 5

quadratic relation

Question 6

makes residuals as small as possible

Answer 6

least-squares regression line

Question 7

difference between predicted value and actual value

Answer 7

residual

Question 8

point where the line intersects the vertical axis

Answer 8

y-intercept

Question 9

predicting outside the range of the x-values in sample data - can result in bad predictions, not recommended

Answer 9

extrapolation

Question 10

proportion of variation in the response variable that is explained by the least-squares regression line - number between 1 and 0 (0 means no explanatory value, 1 means 100% explanation)

Answer 10

coefficient of determination (R2)

Question 11

differences between predicted value and actual value as a result of other incidental factors and random error

Answer 11

deviations

Question 12

deviation due to difference between observed value and mean value of response variable (unexplained + explained)

Answer 12

total deviation

Question 13

deviation due to difference between predicted value and mean value of response variable (below line)

Answer 13

explained deviation

Question 14

deviation due to difference between observed value and predicted value (above line)

Answer 14

unexplained deviation

Question 15

scatter plot where the explanatory variable is plotted on the horizontal axis and the corresponding residual is on the vertical axis - if it shows a discernable pattern, variables may not be linearly related

Answer 15

residual plot

Question 16

constant error variance - if a residual plot shows residuals increasing/decreasing as the explanatory variable increases, linear model is violated

Answer 16

homoscedasticity

Question 17

an observation that significantly affects the least-squares regression line’s slope / y-intercept and the correlation coefficient

Answer 17

influential observation

Question 18

AKA two-way table - shows relationship between two qualitative variables (row variable and column variable)

Answer 18

contingency table

Question 19

boxes in a contingency table that represent the intersections of the row variable and column variable values

Answer 19

cell

Question 20

frequency / relative frequency distribution of either the row or column variable in the contingency table

Answer 20

marginal distribution

Question 21

lists the relative frequency of each category of the response variable, given a specific value of the explanatory variable in the contingency table

Answer 21

conditional distribution

Question 22

when an association between two variables inverts or goes away when a third variable is introduced to the analysis

Answer 22

Simpson’s paradox