Hypothesis testing with active information

Díaz–Pachón, Daniel Andrés; Sáenz, Juan Pablo; Rao, J. Sunil

doi:10.1016/j.spl.2020.108742

Cited by 10 publications

(12 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To reveal whether the national urbanization strategy has an impact on urban shrinkage, we applied two hypothesis testing approaches ( Tables S5 and S6 ), including the t -test (two-sample equal variance) ( Díaz–Pachón et al., 2020 ; Schnuerch et al., 2020 ) and the Friedman test (two-way ANOVA by rank) ( Beasley and Zumbo, 2003 ; DeJuan and Seater, 2007 ). We set the null hypothesis that national urbanization strategies have no effect on shrinking cities and analyzed the significance of the shrinkage rate at the national level under the three types of urbanization strategies in 2013–2018 to test the authenticity of the null hypothesis.…”

Section: Resultsmentioning

confidence: 99%

Satellite monitoring of shrinking cities on the globe and containment solutions

et al. 2022

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Satellite monitoring of shrinking cities on the globe and containment solutions

et al. 2022

View full text Add to dashboard Cite

“…The scenario considered by Díaz-Pachón and Rao in which all the symptomatic individuals are tested (as it is required in most universities and companies in the U.S.) is one example. 5 In this case, the only modification of Algorithm 1 is that p1 in (22) becomes…”

Section: Algorithmmentioning

confidence: 99%

“…That is, if the true proportion is overestimated, the active information will be positive and large; if the true proportion is underestimated, the active information will be negative; and if the true proportion is accurately estimated, the active information will be around zero. 22,23 Moeover, active information can be decomposed into two parts, 𝐼 + = 𝐼 + 𝑇 + 𝐼 + 𝐶 , where 𝐼 + 𝑇 = log ( p * ,1 𝑇 ∕𝑝 (1) ) measures the difference in information from the biased estimate to the real prevalence, and 𝐼 + 𝐶 = log…”

Section: Active Information: the Indexmentioning

confidence: 99%

“…Both Díaz-Rao and Algorithm 1 are close to the real prevalence, and there is not statistical difference between them for this scenario. 22 For the next protocols, the assumption that all symptomatic individuals were sampled is removed, which implies that the Diaz-Rao correction cannot be assessed and Algorithm 1 is followed without modifications.…”

Section: Data From the Israeli Ministry Of Healthmentioning

confidence: 99%

“…The active information for the correction 𝐼 + 𝐶 ≈ −0.34 reduces the bias, producing 𝐼 + ≈ 0.59. 22 Population 1000 10000 100000 1000000…”

mentioning

confidence: 99%

See 2 more Smart Citations

Correcting prevalence estimation for biased sampling with testing errors

Zhou

Díaz–Pachón

Zhao

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Surveillance studies for Covid-19 prevalence estimation are subject to sampling bias due to oversampling of symptomatic individuals and error-prone tests, particularly rapid antigen tests which are known to have high false negative rates for asymptomatic individuals. This results in naïve estimators which can be very far from the truth.In this work, we present a method that removes these two sources of error directly. Moreover, our procedure can be easily extended to the stratified error situation in which a test has very different error rate profiles for symptomatic and asymptomatic individuals as is the case for rapid antigen testing. The result is an easily understandable four-step algorithm that produces much more reliable prevalence estimates as demonstrated on data from the Israeli Ministry of Health. Thus it may re-open the debate about whether we are under-valuing rapid testing as a surveillance tool and may have policy implications in Third-World countries or disadvantaged communities where access to PCR testing may be less accessible.

show abstract

Correcting prevalence estimation for biased sampling with testing errors

Zhou,

Díaz‐Pachón,

Zhao

et al. 2023

Statistics in Medicine

Self Cite

View full text Add to dashboard Cite

Sampling for prevalence estimation of infection is subject to bias by both oversampling of symptomatic individuals and error‐prone tests. This results in naïve estimators of prevalence (ie, proportion of observed infected individuals in the sample) that can be very far from the true proportion of infected. In this work, we present a method of prevalence estimation that reduces both the effect of bias due to testing errors and oversampling of symptomatic individuals, eliminating it altogether in some scenarios. Moreover, this procedure considers stratified errors in which tests have different error rate profiles for symptomatic and asymptomatic individuals. This results in easily implementable algorithms, for which code is provided, that produce better prevalence estimates than other methods (in terms of reducing and/or removing bias), as demonstrated by formal results, simulations, and on COVID‐19 data from the Israeli Ministry of Health.

show abstract

Hypothesis testing with active information

Cited by 10 publications

References 5 publications

Satellite monitoring of shrinking cities on the globe and containment solutions

Satellite monitoring of shrinking cities on the globe and containment solutions

Correcting prevalence estimation for biased sampling with testing errors

Correcting prevalence estimation for biased sampling with testing errors

Contact Info

Product

Resources

About