PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 7548706

Hazard function estimation using B-splines.

P S Rosenberg
View original source ↗Export metadata ↓

Abstract

A flexible parametric procedure is given to model the hazard function as a linear combination of cubic B-splines and to obtain maximum likelihood estimates from censored survival data. The approach yields smooth estimates of the hazard and survivorship functions that are intermediate in structure between strongly parametric and non-parametric models. A simple method is described for selecting the number and location of knots. Simulation results show favorable root mean square error compared to non-parametric estimates for both the hazard and survivorship functions. Three methods are given to calculate confidence intervals based on the delta method, profile likelihood, and bootstrap, respectively. The procedure is applied to estimate hazard rates for acquired immunodeficiency syndrome (AIDS) following infection with human immunodeficiency virus (HIV). Spline methods can accommodate complex censoring mechanisms such as those that arise in the AIDS setting. To illustrate, HIV infection incidence is estimated for a cohort of hemophiliacs in which the dates of HIV infection are interval-censored and some subjects were born after the onset of the HIV epidemic.

Explore related subjects

Acquired Immunodeficiency SyndromeBiometryBisexualityConfidence IntervalsHIVHIV InfectionsHomosexuality, MaleHumansMaleMathematicsModels, StatisticalSurvival RateTime FactorsComparative StudyJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

P S Rosenberg. 1995. Hazard function estimation using B-splines.. https://pubmed.ncbi.nlm.nih.gov/7548706/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed1996

Surveillance of tuberculosis and AIDS co-morbidity--Florida, 1981-1993.

Because immunosuppression induced by human immunodeficiency virus (HIV) infection increases the likelihood that latent tuberculosis (TB) infection will become active in HIV-infected persons (1,2), in 1987, extrapulmonary or disseminated TB was added to the acquired immunodeficiency syndrome (AIDS) surveillance case definition (3), and in 1993, pulmonary TB in HIV-infected persons was added to the case definition (4). In Florida and other areas (5), AIDS surveillance activities include assessment of the completeness and validity of reported cases based on confidential record linkages with the TB registry and other disease registries. In December 1993, the Florida Department of Health and Rehabilitative Services (HRS) matched cases from the AIDS and TB registries to verify documented TB data, include more complete TB data on the AIDS registry, and identify cases from the AIDS registry with unreported TB. This report summarizes an analysis of this match, which underscored the need for collaboration and crosstraining of surveillance staff in AIDS and TB reporting.

Acquired Immunodeficiency Syndrome↗
PubMed1996

The 1990 Florida Dental Investigation: is the case really closed?

In 1994, a magazine article, a newspaper article, and a segment of the television newsmagazine 60 Minutes presented information that cast doubt on the Centers for Disease Control and Prevention's conclusion that a dentist in Florida had infected six of his patients with the human immunodeficiency virus (HIV). These reports were based on previously unavailable documentary evidence, which suggested that the infected patients had unreported or undetected risk factors for HIV infection and that the molecular analyses used to determine that the dentist and his patients had the same strains of HIV had potentially serious flaws. A recent article in this journal sought to dismiss the relevance of this information in the eyes of the scientific community. That report, however, failed to respond directly to many key pieces of evidence, and it offered no rebuttal beyond personal invective and a reassertion of previously published material. Although scientists and clinicians should not rely solely on media reports when drawing conclusions about this complex and controversial case, they deserve a chance to consider and reflect on this material in a meaningful way.

Acquired Immunodeficiency Syndrome↗
PubMed1996

The 1990 Florida Dental Investigation: theory and fact.

Controversy remains about the Centers for Disease Control and Prevention's (CDC) conclusion that a dentist in Florida transmitted human immunodeficiency virus to six of his patients in the late 1980s. The most vocal doubt has come from journalists affiliated with the television program 60 Minutes. Although unanswered questions about the case remain, the evidence continues to overwhelmingly support the CDC's theory. The criticism of the CDC investigation consists largely of assertions that contrary evidence theoretically might exist.

Acquired Immunodeficiency Syndrome↗