StatCrunch logo (home)

Report Properties
Thumbnail:

from Flickr
Created: Apr 30, 2017
Share: yes
Views: 184
Tags:
 
Results in this report
 
Data sets in this report
None
 
Need help?
To copy selected text, right click to Copy or choose the Copy option under your browser's Edit menu. Text copied in this manner can be pasted directly into most documents with formatting maintained.
To copy selected graphs, right click on the graph to Copy. When pasting into a document, make sure to paste the graph content rather than a link to the graph. For example, to paste in MS Word choose Edit > Paste Special, and select the Device Independent Bitmap option.
You can now also Mail results and reports. The email may contain a simple link to the StatCrunch site or the complete output with data and graphics attached. In addition to being a great way to deliver output to someone else, this is also a great way to save your own hard copy. To try it out, simply click on the Mail link.
Week 15 Prediction of Weights
Mail   Print   Twitter   Facebook

Introduction

In the hospital, accurate weight is considered a very vital factor when determining correct medicaton dosage. However, it is possible for a patients weight to be mistakenly recorded from time to time. This can cause a patient to receive an incorrect dosage of medication which could leas to disaterous results. Due to this possibility, a Children's hospital put into place a weight verification procedure based on each patient's medical record. The hospital is requesting a model that will have boundaries for weight based medical record. These boundaries would create flags when weights recorded outside these boundaries, causing a follow-up prior to medication distribution and avoid prescription error. A study was created to develop prediction intervals for each of their patients.  Recorded weights that fall outside of a patient’s prediction interval would be flagged for reweighing. This study is looking at girls weights. 

Methods

Measurements of 56 six girls, age range from 9-15 years old, were taken for this study. The measurments were preadmission weight (kg), hight (cm), time, and current weight (kg). This data will be analyzed to see if there is an effective wieght verification.

Analysis

First, we check for coorelations.

Result 1: Correlation   [Info]
Correlation matrix:
AgePWeightTimeHeight
PWeight0.80532188
(<0.0001)
1
(NaN)
-0.12198064
(0.3705)
0.76144183
(<0.0001)
Time0.053793257
(0.6938)
-0.12198064
(0.3705)
1
(NaN)
0.061227225
(0.654)
Height0.93755571
(<0.0001)
0.76144183
(<0.0001)
0.061227225
(0.654)
1
(NaN)
Weight0.82842363
(<0.0001)
0.97861932
(<0.0001)
0.028771747
(0.8333)
0.78572619
(<0.0001)

As show by the data set, there are several valid p-values. 

Next we will check our assumptions with scatter plots. 

Result 2: Scatter Plot weight vs time   [Info]
Right click to copy

Result 3: Scatter Plot Age vs Weight   [Info]
Right click to copy

Result 4: Scatter Plot p weight vs weight   [Info]
Right click to copy

The does not seem to be any major issues with normality or variablity. Since the conditions are satisfied we will now look at the Multiple linear regression analysis. 

 

Result 5: Multiple Linear Regression   [Info]
Multiple linear regression results:
Dependent Variable: PWeight
Independent Variable(s): Age, Time, Height, Weight

Stepwise results:
P-value to enter: 0.15
P-value to leave: 0.25
StepVariableActionP-valueRMSER-squaredR-squared (adj)
1WeightEntered<0.00011.72307980.95770.9569
2TimeEntered<0.00011.18821230.98030.9795

PWeight = 0.79504445 + 0.99241485 Weight + -0.0919444 Time

Parameter estimates:
ParameterEstimateStd. Err.DF95% L. Limit95% U. Limit
Intercept0.795044450.8528362653-0.915528472.5056174
Weight0.992414850.019495239530.953312351.0315173
Time-0.09194440.0118151953-0.11564267-0.068246131

Analysis of variance table for multiple regression model:
SourceDFSSMSF-statP-value
Model23715.01131857.50571315.6552<0.0001
Error5374.8279641.4118484
Total553789.8393

Summary of fit:
Root MSE: 1.1882123
R-squared: 0.9803
R-squared (adjusted): 0.9795

With 95% confidence we have evidence to so for every kg the girl was on admission their weight will change between 0.95 and 1.03 kgs. Time does not have any correlating changes on the admission weight. Be we do see alot of colineration.

Conclusion

We can use the child's pradmission weight, their hight and their current weight to make a standardized tool to help catch weight based medication errors. This could potentially save alot of lives and reduce harm.

HTML link:
<A href="https://www.statcrunch.com/5.0/viewreport.php?reportid=68694">Week 15 Prediction of Weights</A>

Comments
Want to comment? Subscribe
Already a member? Sign in.

Always Learning