Selecting the minimum prediction base of historical data to perform 5-year predictions of the cancer burden: The GoF-optimal method

Highlights • Different strategies were compared to assess 5-year predictions of cancer. • Poisson linear and log-linear models with age-specific slopes were used. • For each cancer site, the minimum prediction base depends on the model. • A proper prediction base could have between 3 and 5 years. •...

Full description

Saved in:
Bibliographic Details
Published in:Cancer epidemiology 2015-06, Vol.39 (3), p.473-479
Main Authors: Valls, Joan, Castellà, Gerard, Dyba, Tadeusz, Clèries, Ramon
Format: Article
Language:English
Subjects:
Age
Cancer
Cancer incidence
Cancer mortality
Epidemiology
Finland - epidemiology
Hematology, Oncology and Palliative Medicine
Humans
Incidence
Internal Medicine
Mens health
Methods
Models, Statistical
Mortality
Neoplasms - epidemiology
Poisson age-drift model
Poisson age-period model
Prediction
Prediction base
Prognosis
Public health
Spain - epidemiology
Survival Rate
Time Factors
Trends
Womens health
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Highlights • Different strategies were compared to assess 5-year predictions of cancer. • Poisson linear and log-linear models with age-specific slopes were used. • For each cancer site, the minimum prediction base depends on the model. • A proper prediction base could have between 3 and 5 years. • A minimum prediction base for 5-year predictions can be found through GoF-optimal.
ISSN:1877-7821
1877-783X
DOI:10.1016/j.canep.2015.03.014