235688 An Optimal Nonparametric Test of Symmetry Based on the Overlapping Coefficient Using an Extreme Ranked Set Sample: Application to Noninvasive Measurement of Cardiac Output by Electrical Velocimetry in Neonates

Wednesday, November 2, 2011: 12:30 PM

Hani Samawi, Associate Prof of Biostatistics , Jiann-Ping Hsu College of public Health, Georgia Southern University, Statesboro, GA
Robert Vogel, Professor of Biostatistics , Jphcoph, Geogia Southern University, Statesboro, GA
B. Smith-Weaver, Professor and MD , Department of Pediatrics2, Mercer University School of Medicine, Macon, GA
Van De Water, Professor and MD , Surgery, Mercer University School of Medicine, Macon, GA
     
In this paper we provide a more efficient nonparametric test of symmetry based on the empirical overlap coefficient using kernel density estimation applied to an extreme ranked set sample. Our investigation reveals that our proposed test of symmetry is more powerful than all available tests of symmetry. Intensive simulation is conducted to examine the power of the proposed test. An illustration is provided using cardiac output and body weight of neonates in a neonatal intensive care unit.

Learning Areas:
Biostatistics, economics
Protection of the public in relation to communicable diseases including prevention or control
Public health biology

Learning Objectives:
To describe the need for researchers to check the underlying distribution assumptions before using any statistical procedures to analyze medical or public health data. Also, to compare different test procedure to decide which test statistics is more efficient for test for symmetry. Analyze data from Noninvasive Measurement of Cardiac Output by Electrical Velocimetry in Neonates data.

Presenting author's disclosure statement:

Qualified on the content I am responsible for because: I am an associate professor of Biostatistics and I have many publications on this research topic. I have a long history of statistical consultation and data analysis.
Any relevant financial relationships? No

I agree to comply with the American Public Health Association Conflict of Interest and Commercial Support Guidelines, and to disclose to the participants any off-label or experimental uses of a commercial product or service discussed in my presentation.

See more of: Statistical Applications: General Methods
See more of: Statistics