Some results in non-parametric calibration

In statistical terminology, calibration is the problem of recovering the value of the control variable when the value of the response is given. Mathematically, it is the problem of determining the values ofthe independent variables that respond to a given function value: in other words, the problem involves finding a level set. In practice, the problem may in principle occur whenever a regression model is appropriate. Below we will describe some specific instances from medicine, ecology, and chemometry. To cover these examples, we will have to allow both the control and the response to be multivariate. Since the dimension of the response is often at least as large as that of the control, calibration may in many cases lead to a uniquely determined response. This is in particular true in chemometry where the dimension of the response is usually significantly larger than that of the control.

Name thesis:degree_name

M.S.

Level thesis:degree_level

Masters

Discipline thesis:degree_discipline

Statistics

Grantor dc:publisher

Texas Tech University

Year dc:date.issued

2000

Author dc:creator

• Misquitta, Penelope Patricia

• Nonparametric statistics

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/2346/22285

OAI identifier oai:identifier

oai:ttu-ir.tdl.org:2346/22285