|
Activity Number:
|
188
- Contributed Poster Presentations: Section on Nonparametric Statistics
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Monday, July 30, 2018 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
Section on Nonparametric Statistics
|
|
Abstract #328653
|
|
|
Title:
|
Adaptive Classification on Partial Linear Models
|
|
Author(s):
|
Chitrak Banerjee* and Lyudmila Sakhanenko
|
|
Companies:
|
Michigan State University and Michigan State University
|
|
Keywords:
|
Semiparametric;
Growth Curve ;
classification
|
|
Abstract:
|
In this work we want to model the tumor growth through a semi-parametric approach. We take into account both the demographic information as well as the effect of growth as a smooth function of time. The ultimate goal of the work is to classify the growth of tumors into one of two competing models. In one model we will be able to show there is a dependence of the tumor growth on the demographic information through some linear part as well as a time dependence modeled through a smooth growth curve. In the other model the growth of the tumor will only depend on the smooth function of time. Moreover with some regularity assumption we will also be able to provide the consistency of the classifier in correctly classifying the curves. We will also provide some empirical or theoretical rate for the classifier. In the process we will show that under certain condition our classifier would perform better than the naive classifier that can be constructed from our model.
|
Authors who are presenting talks have a * after their name.
