Different Measures of Reliability in Regression

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21340%2F11%3A00192338" target="_blank" >RIV/68407700:21340/11:00192338 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Different Measures of Reliability in Regression

Popis výsledku v původním jazyce

This paper is concerned with the reliability of individual predictions in regression. It is well known that predictions by regression models have for different inputs different reliability, and if predictions by one regression model have a higher reliability than those by another in some part of the input space, they can nevertheless be less reliable in another part. Therefore, the reliability of individual predictions is a very important field of study. We describe conformal predictors and some methodsfor estimating the reliability of individual predictions such as sensitivity analysis or local modeling of prediction error. Finally, we carry out a simulation to compare the methods in an experiment.

Název v anglickém jazyce

Different Measures of Reliability in Regression

Popis výsledku anglicky

This paper is concerned with the reliability of individual predictions in regression. It is well known that predictions by regression models have for different inputs different reliability, and if predictions by one regression model have a higher reliability than those by another in some part of the input space, they can nevertheless be less reliable in another part. Therefore, the reliability of individual predictions is a very important field of study. We describe conformal predictors and some methodsfor estimating the reliability of individual predictions such as sensitivity analysis or local modeling of prediction error. Finally, we carry out a simulation to compare the methods in an experiment.

Druh

O - Ostatní výsledky

CEP obor

BA - Obecná matematika

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2011

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů