Home|Journals|Articles by Year|Audio Abstracts
 

Original Research

Ann Med Res. 2010; 17(4): 347-353


The Use of Biased Regression Methods in Predicting Systolic Blood Pressure

 

Esra Pamukçu*, Cemil Çolak**, Sinan Çalık*, Zülfiye Kuzu***

.




Abstract


 

Objective: In this study, it is aimed to investigate the results of Least Square Regression (LS), Ridge Regression (RR) and Principal Components Regression (PCR) methods in predicting systolic blood pressure.

Material and Methods: This study is cross-sectional and analytical. It had not been occured a control group for the purpose of comparison. Age, height, abdominal circumference, glucose, HDL, LDL, urea, creatinine, potassium, HGB, HCT and diastolic blood pressure were discussed as explanatory variables. Data were obtained from 128 patients who came to Fırat University Medical Center’s Cardiology Clinic between 1 October 2009 and 28 December 2009.

Results: R-square values for LS, RR and PCR were obtained as 0.6003, 0.5876 and 0.5994, respectively. Mean Square Error (MSE) values were obtained as 13.305, 13.515 and 13.319, respectively. Because multicollinearity was resolved and the results accordance with theoretical expectations was obtained, Ridge parameter k = 0.02 was chosen in the RR method.

Conclusion: It was decided that diastolic blood pressure, abdominal circumference and creatinine variables can be used to predict systolic blood pressure and a more consistent, more stable and accordance with theoretical expectations estimates had been obtained with RR and PCR methods. According to the results of PCR and RR, it was determined that PCR provides better estimates than RR.

Key Words: Multicollinearity; Systolic Blood Pressure; Least Square; Ridge Regression; Principal Components Regression.






Full-text options


Share this Article


Online Article Submission
• ejmanager.com




ejPort - eJManager.com
Refer & Earn
JournalList
About BiblioMed
License Information
Terms & Conditions
Privacy Policy
Contact Us

The articles in Bibliomed are open access articles licensed under Creative Commons Attribution 4.0 International License (CC BY), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.