Application of Bootstrap method in spectrometric data analysis
By

XIAO Jiali, Jenny
( 0830300038)

A Final Year Project thesis (STAT 4121; 3 Credits) submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Statistics

at BNU-HKBU UNITED INTERNATIONAL COLLEGE December, 2011

DECLARATION

I hereby declare that all the work done in this Project is of my independent effort. I also certify that I have never submitted the idea and product of this Project for academic or employment credits.

XIAO Jiali, Jenny (0830300038)

Date:

ii

Application of Bootstrap method in spectrometric data analysis
XIAO Jiali, Jenny

Science and Technology Division

Abstract
In this project the bootstrap methodology for spectrometric data is considered. The bootstrap can also compare two populations, without the normality condition and without the restriction to comparison of means. The most important new idea is that bootstrap resampling must mimic the separate samples design that produced the original data. Bootstrap in mean, bootstrap in median, and bootstrap in confidence interval are three kinds of effective way to handle mass spectrometric data. Then,we need to reduce dimension based on bootstrap method. It may allow the data to be more easily visualized. Afterwards, using results obtained by bootstrap, we use data mining method to predict a patient has ovarian cancer or not. Decision tree induction and neural network are usual way to classify it. Keywords: Bootstrap, data mining, classification tree, decision tree induction, neural network, mass spectrometry data, ovarian cancer, control...

iii

Contents
1 Introduction 1.1 1.2 1.3 Mass Spectrometry . . . . . . . . . . . . . . . . . . . . . . Bootstrap Method . . . . . . . . . . . . . . . . . . . . . . Data Mining . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1