Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Profile information matrix for nonlinear transformation models.

A Tsodikov1, G Garibotti

  • 1Department of Biostatistics, School of Public Health, University of Michigan, 1420 Washington Heights, Ann Arbor, MI 48109-2029, USA. tsodikov@umich.edu

Lifetime Data Analysis
|October 6, 2006
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Molecular profiling of ETS and non-ETS aberrations in prostate cancer patients from northern India.

The Prostate·2021
Same author

[Early prediction of the neurological result at 12 months in newborns at neurological risk].

Anales de pediatria (Barcelona, Spain : 2003)·2014
Same author

A novel approach to biomarker discovery in head and neck cancer using an autoantibody signature.

Oncogene·2012
Same author

The tumor suppressor gene rap1GAP is silenced by miR-101-mediated EZH2 overexpression in invasive squamous cell carcinoma.

Oncogene·2011
Same author

Semiparametric models: a generalized self-consistency approach.

Journal of the Royal Statistical Society. Series B, Statistical methodology·2010
Same author

Cytokeratin-positive cells in PBSC collections from normal donors and patients with non-epithelial cell-derived tumors.

Cytotherapy·2010

We developed a stable and efficient algorithm for estimating the profile information matrix in semiparametric models. This method overcomes the curse of dimensionality for nonlinear transformation models, improving statistical inference.

Area of Science:

  • Statistics
  • Econometrics
  • Biostatistics

Background:

  • Semiparametric models present challenges in interval estimation and hypothesis testing due to high dimensionality.
  • The profile information matrix is a viable alternative for focusing on key parameters.
  • Current methods for profile information matrix estimation are often inefficient, unstable, or affected by the curse of dimensionality.

Purpose of the Study:

  • To propose a numerically stable and efficient algorithm for estimating the exact observed profile information matrix.
  • To address the limitations of existing methods in handling high-dimensional semiparametric models.
  • To provide a robust tool for statistical inference in Nonlinear Transformation Models.

Main Methods:

  • Development of a novel algorithm for computing the exact observed profile information matrix.

Related Experiment Videos

  • The algorithm avoids large matrix inversions and explicit profile surface calculations.
  • Focus on regression coefficients within the class of Nonlinear Transformation Models.

    • Main Results:

    • The proposed algorithm provides a numerically stable and efficient estimation of the observed profile information matrix.
    • It effectively overcomes the curse of dimensionality inherent in semiparametric models.
    • The method is exact and does not rely on approximations or ad-hoc procedures.

    Conclusions:

    • The new algorithm offers a significant improvement for statistical inference in semiparametric regression.
    • It provides a reliable and efficient way to estimate the profile information matrix for Nonlinear Transformation Models.
    • This advancement facilitates more accurate hypothesis testing and interval estimation in complex statistical models.