Question

Using this SAS code for the data. The outcome variable is SBP and should be coded to appear on the y-axis. Note: you have to write the appropriate program Answer the following questions: Report the correlation coefficient and the p-value. (2pts) Report the parameter estimate for the intercept and heart rate (4pts) Using the regression equation, what is the expected blood pressure for someone with a heart rate of 153? (4pts) data sas_test; input hr sbp; datalines; 35 80 50 82 52 81 58 95 62 105 65 107 67 105 74 120 89 149 101 157 120 202 185 160 ; run;

Answer 1

Solution-A:

with proc corr get the correlation coeffcient and p value

SAS CODE:

data sas_test;
input hr sbp @@;
datalines;
35 80 50 82 52 81 58 95 62 105 65 107 67 105 74 120 89 149 101 157 120 202 185 160
;
run;
proc corr data=sas_test;
var sbp;
with hr;
run

Output:

The CORR Procedure

1 With Variables:	hr
1 Variables:	sbp

Simple Statistics
Variable	N	Mean	Std Dev	Sum	Minimum	Maximum
hr	12	79.83333	40.55711	958.00000	35.00000	185.00000
sbp	12	120.25000	38.54425	1443	80.00000	202.00000

Pearson Correlation Coefficients, N = 12 Prob > |r| under H0: Rho=0
	sbp
hr	0.80023 0.0018

correlation coeffcient,r=0.80023

p value=0.0018

There exists a strong positive relationship between sbp and hr and relationship is statistically significant

Solution-b:

with proc reg find regression equation of sbp on hr

SAS Code:

proc reg data=sas_test;
model sbp=hr;
run;

Output:

The REG Procedure

Model: MODEL1

Dependent Variable: sbp

Number of Observations Read	12
Number of Observations Used	12

Analysis of Variance
Source	DF	Sum of Squares	Mean Square	F Value	Pr > F
Model	1	10465	10465	17.81	0.0018
Error	10	5877.18707	587.71871
Corrected Total	11	16342

Root MSE	24.24291	R-Square	0.6404
Dependent Mean	120.25000	Adj R-Sq	0.6044
Coeff Var	20.16042

Parameter Estimates
Variable	DF	Parameter Estimate	Standard Error	t Value	Pr > |t|
Intercept	1	59.53557	15.99988	3.72	0.0040
hr	1	0.76051	0.18023	4.22	0.0018

The REG Procedure

Model: MODEL1

Dependent Variable: sbp

From regression output:

model is

sbp=59.53557+0.76051*hr

expected blood pressure for someone with a heart rate of 153 ,substitute hr=153

sbp=59.53557+0.76051*153

= 175.8936

expected blood pressure=175.8936