Sensitivity of parametric link functions in generalized linear models.

J S Yick; A H Lee

doi:10.1080/10543409808835248

Home/Archive/PubMed

PubMed · 9741855

Sensitivity of parametric link functions in generalized linear models.

J S Yick·A H Lee

View original source ↗Export metadata ↓

Abstract

A common method of choosing the link function in generalized linear models is to specify a parametric link family indexed by unknown parameters. The maximum likelihood estimates of such link parameters, however, may often depend on one or several extreme observations. Diagnostics are derived to assess the sensitivity of the parametric link analysis. Two examples demonstrate that the proposed diagnostics can identify jointly influential observations on the link even when masking is present.

Explore related subjects

Blood Sedimentation Humans Leukemia, Myeloid, Acute Linear Models Mathematical Computing Models, Biological Predictive Value of Tests Prognosis Sensitivity and Specificity Journal Article

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

J S Yick, A H Lee. 1998. Sensitivity of parametric link functions in generalized linear models.. https://doi.org/10.1080/10543409808835248

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

KEEP EXPLORING

Related citations

PubMed2006

[Erythrocyte sedimentation rate--more than an old fashion?].

The erythrocyte sedimentation rate (ESR) is a time-honored blood test, which assesses the degree of erythrocyte aggregation by acute phase proteins such as fibrinogen and immunoglobulins. Various intrinsic factors may influence the ESR, among them polycytemia, microcytosis or fibrinogen consumption lead to a decreased ESR, while anemia, macrocytosis or hypoalbuminemia lead to an increased ESR. The ESR still is a very valid test for the diagnosis of certain chronic diseases (polymyalgia, rheumatoid arthritis, multiple myeloma, septic arthritis and ostemyelitis) and the follow-up of certain chronic diseases (polymyalgia rheumatica, systemic lupus erythematodes, chronic infections, prostatic cancer, and Hodgkin's disease). In acute disease states and their monitoring C-reactive protein and eventually procalcitonin are the tests of choice. The ESR should not be used for screening and check-up examinations in asymptomatic patients.

Blood Sedimentation↗

PubMed2006

Best practice in primary care pathology: review 2.

This second best practice review examines five series of common primary care questions in laboratory medicine: (1) laboratory testing for allergy, (2) diagnosis and monitoring of menopause, (3) the use of urine cytology, (4) the usefulness of the erythrocyte sedimentation rate, and (5) the investigation of possible urinary tract infection. The review is presented in a question-answer format. The recommendations represent a précis of guidance found using a standardised literature search of national and international guidance notes, consensus statements, health policy documents, and evidence based medicine reviews, supplemented by MEDLINE EMBASE searches to identify relevant primary research documents. They are standards but form a guide to be set in the clinical context. Most are consensus rather than evidence based. They will be updated periodically to take account of new information.

Blood Sedimentation↗

PubMed2006

Rice-body formation and tenosynovitis of the wrist: a case report.

A 61-year-old woman presented with mild pain and swelling on the volar aspect of the wrist, hand, and little finger. Radiography showed a soft-tissue mass shadow, and magnetic resonance imaging showed acute tenosynovitis of the flexor tendons and an inflammatory mass inside the carpal tunnel. Laboratory test results were normal, except for an elevated erythrocyte sedimentation rate (40 mm/h). The patient had an ambiguous Mantoux test result but no history of mycobacterial exposure. Exhaustive investigations for rheumatic disease were negative. Surgical exploration of the lesion revealed rice bodies in the common flexor tendon synovial sheath, extending distally to the tip of the fifth finger. Removal of the rice bodies and thorough excision of the sheath was performed. The patient regained a full and painless range of motion in about 3 months. One-year follow-up revealed no underlying disorder.

Blood Sedimentation↗