Basic Statistics

THE SCATTER DIAGRAM: SINGLE SAMPLE 167

155 -

mi

5 150-

E

h

Table 12.1 Weights and Systolic Blood Pressure for 10 Males

5 145-

v)

l140-

U

(^9) m 135-
r.
._ - u
3 130-
w
125-
Number Weight (lb) SBP (rnmHg)
1 2 3 4 5 6 7 8 9
10
165
243
180
152
163
210
203
195
178
218
134
155
137
124
128
131
143
136
127
146
variable and age as the predictor variable, we would have a negative relationship since
vital capacity tends to decrease with increasing age.
If the points fall roughly within a circle, there is essentially little or no appreciable
relationship between the predictor variable and the outcome variable. If all the points
fall close to a straight line or curve, we say that there is a strong relationship between
X and Y. The points in Figure 12.1 tend to fall fairly close to a straight line; in this
sample systolic blood pressure tends to increase linearly with weight.
The points on many scatter diagrams seem to follow a straight line at least over
a limited range of the X variable. However, in some examples the points appear to
follow a curve. Additional methods for examining the relationship between X and Y
from scatter diagrams are given by Chambers et al. [1983] and Cleveland [1985].
.
120 J
140 160 180 200 220 240 260
Weight (Ib)
Figure 12.1 Scatter diagram of weight versus systolic blood pressure.