Skip to Main content Skip to Navigation
Journal articles

Relationship between Derivatives of the Observed and Full Loglikelihoods and Application to Newton-Raphson Algorithm

Daniel Commenges 1, * Virginie Rondeau 1
* Corresponding author
Abstract : In the case of incomplete data we give general relationships between the first and second derivatives of the loglikelihood relative to the full and the incomplete observation set-ups. In the case where these quantities are easy to compute for the full observation set-up we propose to compute their analogue for the incomplete observation set-up using the above mentioned relationships: this involves numerical integrations. Once we are able to compute these quantities, Newton-Raphson type algorithms can be applied to find the maximum likelihood estimators, together with estimates of their variances. We detail the application of this approach to parametric multiplicative frailty models and we show that the method works well in practice using both a real data and a simulated example. The proposed algorithm outperforms a Newton-Raphson type algorithm using numerical derivatives.
Document type :
Journal articles
Complete list of metadatas

https://www.hal.inserm.fr/inserm-00262032
Contributor : Evelyne Mouillet <>
Submitted on : Monday, March 10, 2008 - 4:31:00 PM
Last modification on : Wednesday, November 29, 2017 - 2:54:13 PM
Long-term archiving on: : Thursday, May 20, 2010 - 9:48:16 PM

Identifiers

  • HAL Id : inserm-00262032, version 1

Collections

Citation

Daniel Commenges, Virginie Rondeau. Relationship between Derivatives of the Observed and Full Loglikelihoods and Application to Newton-Raphson Algorithm. International Journal of Biostatistics, De Gruyter, 2006, 2 (1), pp.1-26. ⟨inserm-00262032⟩

Share

Metrics

Record views

175

Files downloads

288