Sunbeam Corporation

Sunbeam Corporation
The Sunbeam Corporation makes a wide variety of appliances for the home. One product is a digital blood pressure gauge.
For obvious reasons the blood pressure readings made by the monitor need to be accurate. Whena new model is being
designed, one of the crucial step is to test it. To do this, a sample of people is selected. Each person has his/her systolic
blood pressure taken by a highly repsected physician. They immediately have their systolic blood pressure taken using the
Sunbeam monitor as that determined by the physician, the monitor is determined to pass the test.
In a recent test 15 people were randomly selected to be in the sample. The blood pressure readings for these pople, using
both methods, are also contained in the data file
a. Based on the sample data and a significance level equal to 0.05, what conclusion should Sunbeam engineers reach
regarding the blood pressure monitor ? Discuss your answer in a short statement.
b. Consider the context of this problem. Does it make sense to you that any deviation from the equality between the man
blood pressure reading would be of interest/ Examine the data to determine a, perhaps, more reasonable criterion.
c. Calculate a 95% confidence interval for the paired difference between the two mean blood pressure readings. Would you
Ho : There is no significant difference between blood pressure between Sunbeam BP Monitor and Physician's reading
use:
Blood Pressure Readings
t-Test: Paired Two Sample for Means
(mm Hg)
Sunbeam
Physician's Sunbeam BP
BP Monitor Physician's Reading
Monitor Reading
Reading
Reading
112 126 Mean 120.20 120.73
109 108 Variance 127.31 63.78
139 116 Observations 15 15
141 123 Pearson Correlation 0.04344
120 138 Hypothesized Mean Difference 0
99 123 df 14
128 119 t Stat -0.1526
118 122 P(T<=t) one-tail 0.4405
116 116 t Critical one-tail 1.7613
120 118 P(T<=t) two-tail 0.8809 p>0.05 DO NOT REJECT THE Ho
111 114 t Critical two-tail 2.1448
123 108
114 130
121 123
132 127
CONCLUSION:
A two-tailed test is appropriate for this problem since we want to determine if there is any difference between the groups we are
comparing. So,we are interested in determining both the positive and negative tails of the distribution. The Decision Rule states
that if the p-value is less than alpha, reject the H0. In this case, the p-value (0.8809) is greater than alpha (0.05) so we will fail
to reject H0. We have enough evidence to support the claim that there is no significant difference between blood pressure
between Sunbeam BP Monitor and Physician's readings. We fail to reject the null hypothesis.
ANSWERS
1) It was revealed that there is no significant difference between the readings obtained by the Physician and the Sunbeam BP
monitor's readings. I would recommend the engineers to pursue the production of this device.
2) It should be considered that deviation from the equality as a subject of interest for further research. There are certain errors
in data collection process that affects the readings, take for example in this case is the tool that is being used to collect the
readings.I suggest the engineers might need to updgade and calibrate the device to lessen the level of errors in the future. I
should also consider human error as the physician took the readings in a manual fashion.
3) We want to Calculate a 95% confidence interval for the paired difference between the two mean blood pressure readings.
Solution:
The one set of data we're interested in is the difference between the Phisycian's Readings and the Sunbeam Monitor's
Readings. Let's define this variable as difference = B-A, and calculate the difference for each readings:
We want to use these n=15 to construct a confidence interval for the mean difference. This makes it appropriate to use a t-
interval instead of a z-interval to estimate the mean difference. Let's check the conditions for making a t interval.
Random: 15 people were randomly selected to be in the sample
Normal: Since our sample of n=15, 15 samples is small, we need to plot the data.
Histogram of Mean Differences
6
Frequency
4
Difference in Blood Pressure Readings 2
(B-A) (mm Hg) 0
-24 -8.333333333 More
Bin
so it should be safe to proceed.
Sunbeam BP
Physician's
Monitor
Reading
Reading
Mean 120.20 120.73

Standard Error 2.91 2.06
𝟏𝟓 − 𝟏 𝟕. 𝟗𝟗 𝟐 + 𝟏𝟓 − 𝟏 𝟏𝟏. 𝟐𝟖 𝟐
𝑺𝑷 = = 𝟗. 𝟕𝟕 Median 120 122
𝟏𝟓 + 𝟏𝟓 − 𝟐
Mode 120 123
Standard Deviation 11.28 7.99
Sample Variance 127.31 63.78
Kurtosis 0.07 0.40
Skewness 0.30 0.28
Range 42 30
Minimum 99 108
Maximum 141 138
From t-Table : 𝑡0.05(2−𝑡𝑎𝑖𝑙𝑒𝑑) = 2.048 Sum 1803 1811
Count 15 15
𝟏 𝟏 Confidence Level(95.0%) 6.25 4.42
𝟏𝟐𝟎. 𝟕𝟑 − 𝟏𝟐𝟎. 𝟐𝟎 ± 𝟐. 𝟎𝟒𝟖 𝟗. 𝟕𝟕 +
𝟏𝟓 𝟏𝟓
𝟎. 𝟓𝟐 ± 𝟕. 𝟑𝟎𝟔
Interval ≈ ( -6.786 , 7.826)
Recommendation:
I would consider Sunbeam Blood Pressure Monitor as a good substitute for a doctor's blood pressure reading. It is said to have
a 95% confidence level that Sunbeam BP monitor can be accurate at an Interval ≈ -6.786 to 7.826. In reality, if we read
someone's BP using a manual device, it can only give us readings with place value of tens. Example: 120/80 mmHg (for
optimal blood level), 200/120 mmHg (high-blood pressure), 100/60 mmHg (anemic). Considering human errors , we can obtain
possible readings that are less than or more than 10 mmHg from the accurate measure. In general, I would recommend the to
use of this product because it can conveniently give a reading in just a snap. Patient's who are ill or incapable can even use
this device by themselves with ease.

Sunbeam Corporation

Uploaded by

Copyright:

Available Formats

Sunbeam Corporation

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Sunbeam Corporation

Uploaded by

Copyright:

Available Formats

Sunbeam Corporation

Mean 120.20 120.73

You might also like