Method to estimate relative risk using exposed proportion and case group data

Yada, Yoichi

doi:10.1038/s41598-017-02302-1

Cited by 6 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Relative risk is an intuitive measure that summarizes the risks in two different groups into one (Noordzij et al , 2017). It requires data from two groups – the experimental or test group and the control group (Andrade, 2015; Yada, 2017). In the present study, the sample of perpetrators who committed financial services frauds constituted the experimental or test group, and the sample of perpetrators who committed non-financial services frauds constituted the control group.…”

Section: Methodsmentioning

confidence: 99%

“…In the present study, the sample of perpetrators who committed financial services frauds constituted the experimental or test group, and the sample of perpetrators who committed non-financial services frauds constituted the control group. To calculate the relative risk of exhibition of a particular red flag behavior, its risk/ probability of exhibition in the experimental group was divided by its risk/probability of exhibition in the control group (Yada, 2017) (for details refer to Table 3). Calculation of relative risk was considered particularly relevant in the present case because it helped quantify the risk differences in the two groups and present a reliable and accurate picture of the strength of particular risk factors (Siegerink and Rohmann, 2018).…”

Section: Coding and Analysismentioning

confidence: 99%

See 1 more Smart Citation

Red flag behaviors in financial services frauds: a mixed-methods study

Sandhu

2021

JFRC

View full text Add to dashboard Cite

Purpose This study aims to enlist the red flag behaviors exhibited in financial services frauds. Design/methodology/approach A pluralistic mixed methodology was adopted in this study. Data collected via semi-structured interviews were coded, quantified and subjected to descriptive analysis to identify the most frequently exhibited red flag behaviors in financial services frauds. The relative risk of exhibition of the identified red flag behaviors was assessed by intuitively comparing the red flag behaviors identified in financial services frauds (experimental group, n = 24) with the red flag behaviors identified in a heterogeneous control sample of non-financial services frauds (control group, n = 28). Findings This study identifies six red flag behaviors likely to be more frequently exhibited in financial services frauds than in non-financial services frauds. Practical implications Results of this study can be used to develop a typical behavioral profile of a financial services fraud perpetrator. Active communication of this profile in fraud awareness training can help make fraud conspicuous in the financial services industry. Originality/value This study is unique because human behavior as a possible fraud indicator is an under-researched area. Further, this study examines first level of evidence and attempts an ex-post analysis of actual red flag behaviors exhibited in acknowledged fraud cases in which the perpetrator/perpetrators has/have been clearly identified.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Coding and Analysismentioning

confidence: 99%

Red flag behaviors in financial services frauds: a mixed-methods study

Sandhu

2021

JFRC

View full text Add to dashboard Cite

show abstract

“…Many researchers have worked on statistical inference problems of relative risk. To list a few, 22 worked on estimating the relative risk in cohort studies and clinical trials; 23 developed methods to conduct both point estimation and confidence interval estimation for relative risk using exposed proportion and case group data; 24 discussed the exact one-sided and two-sided confidence intervals for relative risk with data collected from a matched-pairs design or a two-arm independent binomial experiment.…”

Section: Bounded-width Confidence Intervalsmentioning

confidence: 99%

Bounded-width confidence interval following optimal sequential analysis of adverse events with binary data

Silva

Zhuang

2022

Stat Methods Med Res

View full text Add to dashboard Cite

In sequential testing with binary data, sample size and time to detect a signal are the key performance measures to optimize. While the former should be optimized in Phase III clinical trials, minimizing the latter is of major importance in post-market drug and vaccine safety surveillance of adverse events. The precision of the relative risk estimator on termination of the analysis is a meaningful design criterion as well. This paper presents a linear programming framework to find the optimal alpha spending that minimizes expected time to signal, or expected sample size as needed. The solution enables (a) to bound the width of the confidence interval following the end of the analysis, (b) designs with outer signaling thresholds and inner non-signaling thresholds, and (c) sequential designs with variable Bernoulli probabilities. To illustrate, we use real data on the monitoring of adverse events following the H1N1 vaccination. The numerical results are obtained using the R Sequential package.

show abstract

“…-'Intuitive risk' = an approach associated with either situation-or evidence-specific decision-making that involves recognising cues or patterns (17). Intuitive risk utilises both subjective and objective information (18,19,20,21).…”

Section: Terminologymentioning

confidence: 99%

Zoonoplasticity as an intuitive risk protocol for companion-animal-linked zoonoses

Warwick¹

2020

Rev. Sci. Tech. OIE

View full text Add to dashboard Cite

Zoonoses are diseases transmissible between non-human and human animals. Over 200 zoonoses are known, of which at least 60 are associated with (especially exotic) companion animals. Current risk-impact assessment approaches for zoonoses are largely cumbersome and, to be meaningful, may require extensive detailed information. A literature search and review were conducted for current risk assessment protocols for common zoonoses, with subsequent development of two novel rapid scoring methods for evaluating potential risk associated with companion-animal-linked zoonoses. Accordingly, a novel, two-tier methodological concept -'zoonoplasticity' -was prepared using an intuitive risk approach. The first tier considers risk principles for companion animals and husbandry practices, and pre-weights animals by class or species. The second tier considers established pathogen-or disease-based questions and assigns a degree of risk. Thus, the zoonoplasticity concept enables pathogens or their resultant zoonoses to be scored and provides a clear points-based protocol offering guidance concerning potential threat, in particular where more quantifiable risk assessment is unavailable because of information deficits. The zoonoplasticity concept was tested with 15 animal species and 22 known zoonoses against European Centre for Disease Prevention and Control (ECDC) operational guidance as a comparative system. Risk categorisation was 100% consistent for 21 of the 22 specific zoonoses, while requiring minimal information input, and the overall comparison rate was 98.85%. Zoonoplasticity is not intended to provide an absolute measure of risk or to replace existing methodologies, rather it is an attempt to standardise a practical judgement protocol that accounts for various relevant issues, and to offer a potentially helpful indicator of concern. The zoonoplasticity concept will be relevant to remits for medical professionals, veterinary medical professionals, public health professionals, government administrators, biomedical researchers and others.

show abstract

Method to estimate relative risk using exposed proportion and case group data

Cited by 6 publications

References 12 publications

Red flag behaviors in financial services frauds: a mixed-methods study

Red flag behaviors in financial services frauds: a mixed-methods study

Bounded-width confidence interval following optimal sequential analysis of adverse events with binary data

Zoonoplasticity as an intuitive risk protocol for companion-animal-linked zoonoses

Contact Info

Product

Resources

About