A Monte Carlo–Based Bayesian Approach for Measuring Agreement in a Qualitative Scale

Calle-Alonso, Fernando; Pérez, Carlos J.

doi:10.1177/0146621614554080

Cited by 2 publications

(1 citation statement)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is reflected in the high positive predictive value of the ELISA, showing that a positive serological test is good evidence to support a diagnosis of WA-MCF whereas a negative test has no predictive value. This is also supported by the BAI which demonstrated a reasonable agreement between the indirect ELISA and the PCR in detecting positive cases and poorer agreement between the tests in detecting negative cases [30].…”

Section: Discussionmentioning

confidence: 81%

Field validation of clinical and laboratory diagnosis of wildebeest associated malignant catarrhal fever in cattle

et al. 2019

View full text Add to dashboard Cite

Background Wildebeest associated malignant catarrhal fever (WA-MCF) is a fatal disease of cattle. Outbreaks are seasonal and associated with close interaction between cattle and calving wildebeest. In Kenya, WA-MCF has a dramatic effect on cattle-keepers who lose up to 10% of their cattle herds per year. The objective of this study was to report the impact of WA-MCF on a commercial ranch and assess the performance of clinical diagnosis compared to laboratory diagnosis as a disease management tool. A retrospective study of WA-MCF in cattle was conducted from 2014 to 2016 at Kapiti Plains Ranch Ltd., Kenya. During this period, 325 animals showed clinical signs of WA-MCF and of these, 123 were opportunistically sampled. In addition, 51 clinically healthy animals were sampled. Nested polymerase chain reaction (PCR) and indirect enzyme linked immunosorbent assay (ELISA) were used to confirm clinically diagnosed cases of WA-MCF. A latent class model (LCM) was used to evaluate the diagnostic parameters of clinical diagnosis and the tests in the absence of a gold standard. Results By PCR, 94% (95% C.I. 89–97%) of clinically affected animals were positive to WA-MCF while 63% (95% C.I. 54–71%) were positive by indirect ELISA. The LCM demonstrated the indirect ELISA had poor sensitivity 63.3% (95% PCI 54.4–71.7%) and specificity 62.6% (95% PCI 39.2–84.9%) while the nested PCR performed better with sensitivity 96.1% (95% PCI 90.7–99.7%) and specificity 92.9% (95% PCI 76.1–99.8%). The sensitivity and specificity of clinical diagnosis were 99.1% (95% PCI 96.8–100.0%) and 71.5% (95% PCI 48.0–97.2%) respectively. Conclusions Clinical diagnosis was demonstrated to be an effective method to identify affected animals although animals may be incorrectly classified resulting in financial loss. The study revealed indirect ELISA as a poor test and nested PCR to be a more appropriate confirmatory test for diagnosing acute WA-MCF. However, the logistics of PCR make it unsuitable for field diagnosis of WA-MCF. The future of WA-MCF diagnosis should be aimed at development of penside techniques, which will allow for fast detection in the field. Electronic supplementary material The online version of this article (10.1186/s12917-019-1818-8) contains supplementary material, which is available to authorized users.

show abstract

Section: Discussionmentioning

confidence: 81%

Field validation of clinical and laboratory diagnosis of wildebeest associated malignant catarrhal fever in cattle

et al. 2019

View full text Add to dashboard Cite

show abstract

Bayesian approaches to the weighted kappa-like inter-rater agreement measures

Tran

Demirhan

Dolgun

2021

Stat Methods Med Res

View full text Add to dashboard Cite

Inter-rater agreement measures are used to estimate the degree of agreement between two or more assessors. When the agreement table is ordinal, different weight functions that incorporate row and column scores are used along with the agreement measures. The selection of row and column scores is effectual on the estimated degree of agreement. The weighted measures are prone to the anomalies frequently seen in agreement tables such as unbalanced table structures or grey zones due to the assessment behaviour of the raters. In this study, Bayesian approaches for the estimation of inter-rater agreement measures are proposed. The Bayesian approaches make it possible to include prior information on the assessment behaviour of the raters in the analysis and impose order restrictions on the row and column scores. In this way, we improve the accuracy of the agreement measures and mitigate the impact of the anomalies in the estimation of the strength of agreement between the raters. The elicitation of prior distributions is described theoretically and practically for the Bayesian estimation of five agreement measures with three different weights using an agreement table having two grey zones. A Monte Carlo simulation study is conducted to assess the classification accuracy of the Bayesian and classical approaches for the considered agreement measures for a given level of agreement. Recommendations for the selection of the highest performing agreement measure and weight combination are made in the breakdown of the table structure and sample size.

show abstract

A Monte Carlo–Based Bayesian Approach for Measuring Agreement in a Qualitative Scale

Cited by 2 publications

References 56 publications

Field validation of clinical and laboratory diagnosis of wildebeest associated malignant catarrhal fever in cattle

Field validation of clinical and laboratory diagnosis of wildebeest associated malignant catarrhal fever in cattle

Bayesian approaches to the weighted kappa-like inter-rater agreement measures

Contact Info

Product

Resources

About