Interval estimation under two study designs for kappa with binary classifications.

C A Hale; J L Fleiss

Home/Archive/PubMed

PubMed · 8369386

Interval estimation under two study designs for kappa with binary classifications.

C A Hale·J L Fleiss

View original source ↗Export metadata ↓

Abstract

Cornfield's test-based method of setting a confidence interval on a parameter associated with a two-by-two contingency table is adapted for use with the measure of agreement kappa. One-sided confidence intervals derived in this way are compared to other intervals proposed for kappa under two study designs. Both designs involve two ratings per subject on a dichotomous scale. In one design the same two raters make all evaluations; in the other, possibly different pairs of raters evaluate different subjects, or the same rater carries out a pair of independent assessments for each subject. It is shown through simulation that lower bounds based on Cornfield's test-based method attain the nominal coverage probability more often than other intervals proposed in the literature.

Explore related subjects

HIV Seropositivity Humans Male Mathematics Models, Statistical Nuclear Family Probability Research Design Journal Article Research Support, U.S. Gov't, P.H.S.

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

C A Hale, J L Fleiss. 1993. Interval estimation under two study designs for kappa with binary classifications.. https://pubmed.ncbi.nlm.nih.gov/8369386/

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

KEEP EXPLORING

Related citations

PubMed2002

Significant closure of the human immunodeficiency virus type 1 and hepatitis C virus preseroconversion detection windows with a transcription-mediated-amplification-driven assay.

While the present generation of serology-based assays has significantly decreased the number of human immunodeficiency virus type 1 (HIV-1) and hepatitis C virus (HCV) infections acquired by transfusion, the possibility of infected donations escaping detection still exists. The average seronegative viremic window duration during which immunological assays are unable to detect the virus is estimated to be between 16 and 22 days for HIV-1 and approximately 70 days for HCV. Significant reduction of detection window duration was demonstrated using a nucleic acid amplification assay, the Procleix HIV-1/HCV Assay, which utilizes transcription-mediated amplification technology to simultaneously detect HIV-1 and HCV RNAs. For 26 commercially available HIV-1 seroconversion panels tested, specimens were reactive in the HIV-1/HCV assay at the same time as or earlier than in serological assays. Overall, the HIV-1/HCV assay was able to reduce the detection window duration by an average of 14 days and 6 days compared to tests relying on recognition of HIV-1 antibody and p24 antigen, respectively. For 24 commercially available HCV seroconversion panels tested, the specimens were reactive in the HIV-1/HCV assay at an earlier blood sampling date than in serological assays, reducing the detection window duration by an average of 26 days. Similar results were obtained in testing the HIV-1 and HCV seroconversion panels in the virus-specific HIV-1- and HCV-discriminatory assays, respectively. In conclusion, the HIV-1/HCV assay and corresponding discriminatory assays significantly reduced detection window durations compared to immunoassays.

HIV Seropositivity↗

PubMed2001

AIDS-related discrimination in the workplace--the results of two evaluative surveys carried out during a three-year period in Hong Kong.

Two longitudinal surveys were carried out in 1996 and 1999 aimed at describing the situations of AIDS-related discrimination in the workplace and evaluating the effectiveness of some social interventions against discrimination towards HIV-positive employees. Two hundred and ninety-nine and 212 companies completed a questionnaire in 1996 and 1999, respectively. The results are mixed. Although most of the sampled companies had no HIV/AIDS-related policy, their awareness of related legislation increased over the three-year period. Over the three-year study period, more companies indicated they would disclose information of their HIV-positive employees if known to the company; however, fewer companies indicated they would dismiss an employee because of his or her HIV-positive status. Only a few companies indicated that they would provide counselling and support to an HIV-positive employee.

HIV Seropositivity↗

PubMed2001

[Treatment of HCV infection in HIV-positive patients].

Treatment of HCV infection in HIV seropositives is becoming a management priority because of: the increasing HCV and stage liver disease mortality and the unfavourable impact of HCV infection on efficacy and toxicity of antiretroviral combination treatment. Treatment end points are: eradication of HCV or suppression of HCV replication in order to slow HCV disease progression and to increase efficacy and to reduce hepatotoxicity of antiretrovirals. Interferon as monotherapy and in combination with ribavirin induces eradication of HCV in respectively 17 and 28% and suppression of viral replication in 26 and 36% of treated HIV infected subjects. The impact of these drugs on HIV disease evolution and on antiretroviral treatment efficacy, toxicity and compliance needs to be established. Then the cost-effectiveness of anti HCV therapy in anti HIV infected patients still needs to be defined.

HIV Seropositivity↗