|
موجز عن البحث:
|
The amount of explained variation R2 is an
overall measure used to quantify the information in a model and especially
how useful the model might be when predicting future observations. explained
variation is useful in guiding model choice for all types of predictive
regression models, including linear and generalized linear models and
survival analysis. In this work we consider how individual observations in a
data set can influence the value of various R2 measures proposed for survival
analysis including local influence to assess mathematically the effect of
small changes. We discuss methodologies for assessing influence on Graf et
al.’s R2G measure, Harrell’s C-index and Nagelkerke’s R2N. The ideas are illustrated on data on 1391 patients
diagnosed with Diffuse Large B-cell Lymphoma (DLBCL), a major subtype of
Non-Hodgkin’s Lymphoma (NHL).
|
|
ملخص المشاركة:
|
We investigate predictive accuracy,
especially for Non-Hodgkin’s Lymphoma (NHL) based on a study of 1391 patients
followed for 10-years (1992 to 2002). In this area physicians usually use the
International Prognostic Index (IPI) to order to identify low and high risk
patients (Shipp et al., 1993). We consider whether it is possible to improve
on the IPI. Four R2-type measures are used to assess IPI performance for
predictive purposes and how it compares with a prognostic index obtained from
the data to hand. The measures are: a) the Nagelkerke information gain R2
routinely given in R, b) an R2- measure based on the Brier Score (Graf et
al., 1999), c) the Schemper and Henderson survival process measure (Schemper
and Henderson, 2000) and d) the Stare et al. ( 2010) explained rank
variation. We review and compare through simulation and an analysis of the
NHL data.
|
