Description
1. Problems 11.13-11.18 in Rosner
The Update to the Task Force Report on Blood Pressure Control in Children reported the observed 90th percentile of SBP in single years of age
from age 1 to 17 based on prior studies. The data for boys of average
height are given in Table 1. Suppose we seek a more efficient way to
display the data and choose linear regression to accomplish this task.
Age (x) SBP (y) Age (x) SBP (y)
1 99 10 115
2 102 11 117
3 105 12 120
4 107 13 122
5 108 14 125
6 110 15 127
7 111 16 130
8 112 17 132
9 114
Table 1: 90th percentile of SBP of boys aged 1 to 17 study
(a) Fit a regression line relating age to SBP, using the data in Table 1.
(b) Provide a 95% confidence interval for the slope of the regression line.
(c) What is the predicted blood pressure for an average 13-year-old boy
as estimated from the regression line?
(d) What is the standard error of the estimate in (c)?
2. Problems 11.31-11.33 in Rosner
A study of cardiovascular reactivity is conducted by measuring the change
in blood pressure before and after a stimulating experience (like playing
a video game). Blood-pressure measurements were made using an automated monitor (a machine) and using manual method. One way to relate
measures of reactivity for the automated and manual blood pressures is the
correlation coefficient. Suppose the correlation coefficient relating these
to measures of reactivity is 0.19, based on 79 people having reactivity
measured by each type of blood-pressure monitor.
(a) What is the appropriate procedure to test if there is a relationship
between reactivity as measured by the automated and manual monitors?
1
(b) Conduct the test procedure in (a) and report a p-value. What do the
results mean, in words?
(c) Provide a 95% CI for the correlation coefficient between these two
measures of reactivity.
3. Problems 12.6-12.8 in Rosner
Twenty-two young asthmatic volunteers were studied to assess the shortterm effects of sulfur dioxide (SO2) exposure under various conditions.
The baseline data in Table 2 were presented regarding bronchial reactivity
to SO2 stratified by lung function (as defined by forced expiratory volume
/ forced vital capacity [FEV1/FVC]) at screening.
Lung-function group
Group A Group B Group C
FEV1/FVC ≤ 74% FEV1/FVC 75-84% FEV1/FVC ≥ 85%
20.8 7.5 9.2
4.1 7.5 2.0
30.0 11.9 2.5
24.7 4.5 6.1
13.8 3.1 7.5
8.0
4.7
28.1
10.3
10.0
5.1
2.2
Table 2: Relationship of bronchial reactivity to SO2 (cm H2O/s) grouped by
lung function
(a) Test the hypothesis that there is an overall mean difference in bronchial
reactivity among the three lung-function groups.
(b) Compare the means of each pair of groups using the pairwise comparison method.
(c) Compare the means of each pair of groups using the Bonferroni
method.
4. Problems 12.44 in Rosner
Refer to data set LEAD.csv. Use nonparametric methods to compare
MAXFWT among the three exposure groups defined by the variable LEAD_GRP.
2
