Cumulants and Bartlett Identities in Cox Regression

DOI10.1007/978-3-319-25826-3_5zbMath1357.62289MaRDI QIDQ2956048

Jianming Ye, Per Aslak Mykland

Publication date: 16 January 2017

Published in: The Fascination of Probability, Statistics and their Applications (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-319-25826-3_5

zbMATH Keywords

partial likelihood; survival analysis; proportional hazards model; Bartlett correction; Bartlett identities

Mathematics Subject Classification ID

62F12: Asymptotic properties of parametric estimators

62E15: Exact distribution theory in statistics

62N02: Estimation in survival analysis and censored data

Related Items

Embedding and asymptotic expansions for martingales

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Cox's regression model for counting processes: A large sample study
• Theory of partial likelihood
• A large sample study of Cox's regression model
• Bartlett type identities for martingales
• Bartlett identities and large deviations in likelihood theory
• Saddlepoint methods and statistical inference. With comments and a rejoinder by the author
• Dual likelihood
• Embedding and asymptotic expansions for martingales
• Martingale expansions and second order inference
• Modified signed log likelihood ratio
• A Note on the Differentiation of Cumulants of Log Likelihood Derivatives
• On the corrections to the likelihood ratio statistics
• Conditionality resolutions
• On the Edgeworth expansion and bootstrap approximation for the cox regression model under random censorship
• Multivariate point processes: predictable projection, Radon-Nikodym derivatives, representation of martingales
• Partial likelihood
• A Simple Derivation of r* for Curved Exponential Families
• Thiele: Pioneer in Statistics
• The Early History of the Cumulants and the Gram‐Charlier Series
• APPROXIMATE CONFIDENCE INTERVALS
• APPROXIMATE CONFIDENCE INTERVALS
• Statistical models based on counting processes
• Likelihood computations without Bartlett identities