Statistical Methods for Psychology

other (regression) and of obtaining a measure of the degree of this relationship (correla-

tion). The only restriction we will impose for the moment is that the relationship between

Xand Ybe linear. Curvilinear relationships will not be considered, although in Chapter 15

we will see how they can be handled by closely related procedures.

9.1 Scatterplot

When we collect measures on two variables for the purpose of examining the relationship

between these variables, one of the most useful techniques for gaining insight into this

relationship is a scatterplot(also called a scatter diagram). In a scatterplot, each experi-

mental subject in the study is represented by a point in two-dimensional space. The coordi-

nates of this point ( , ) are the individual’s (or object’s) scores on variables Xand Y,

respectively. Examples of three such plots appear in Figure 9.1.

Xi Yi

Section 9.1 Scatterplot 247

scatterplot

scatter diagram

10

–10

Adjusted infant mortality

20

Physicians per 10,000 population

(a) Infant mortality as a function

of number of physicians

10 12 14 16 18

74

66

Life expectancy (males)

0 1500

5

0

–5

35

20

Cancer rate

600

Solar radiation

(c) Cancer rate as a function of solar radiation

200

30

25

Per capita health expenditure ($)

(b) Life expectancy as a function

of health care expenditures

500 1000

73

72

71

70

69

68

67

300 400 500

Figure 9.1 Three scatter diagrams