Details
| Original language | English |
|---|---|
| Pages (from-to) | 2652-2663 |
| Number of pages | 12 |
| Journal | Statistics in medicine |
| Volume | 38 |
| Issue number | 14 |
| Early online date | 5 Mar 2019 |
| Publication status | Published - 30 Jun 2019 |
Abstract
Bioassays are highly standardized trials for assessing the impact of a chemical compound on a model organism. In that context, it is standard to compare several treatment groups with an untreated control. If the same type of bioassay is carried out several times, the amount of information about the historical controls rises with every new study. This information can be applied to predict the outcome of one future control using a prediction interval. Since the observations are counts of success out of a given sample size, like mortality or histopathological findings, the data can be assumed to be binomial but may exhibit overdispersion caused by the variability between historical studies. We describe two approaches that account for overdispersion: asymptotic prediction intervals using the quasi-binomial assumption and prediction intervals based on the quantiles of the beta-binomial distribution. Both interval types were α-calibrated using bootstrap methods. For an assessment of the intervals coverage probabilities, a simulation study based on various numbers of historical studies and sample sizes as well as different binomial proportions and varying levels of overdispersion was run. It could be shown that α-calibration can improve the coverage probabilities of both interval types. The coverage probability of the calibrated intervals, calculated based on at least 10 historical studies, was satisfactory close to the nominal 95%. In a last step, the intervals were computed based on a real data set from the NTP homepage, using historical controls from bioassays with the mice strain B6C3F1.
Keywords
- alpha-calibration bootstrap, beta-binomial, bioassay, extra binomial variation, quasi-binomial
ASJC Scopus subject areas
- Medicine(all)
- Epidemiology
- Mathematics(all)
- Statistics and Probability
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Statistics in medicine, Vol. 38, No. 14, 30.06.2019, p. 2652-2663.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Prediction intervals for overdispersed binomial data with application to historical controls
AU - Menssen, Max
AU - Schaarschmidt, Frank
N1 - Funding information: We want to thank Prof Dr Ludwig Hothorn for giving helpful suggestions and Clemens Buczilowski for his technicalsupport. Furthermore, we want to thank the reviewers for reading the manuscript and for their helpful comments.
PY - 2019/6/30
Y1 - 2019/6/30
N2 - Bioassays are highly standardized trials for assessing the impact of a chemical compound on a model organism. In that context, it is standard to compare several treatment groups with an untreated control. If the same type of bioassay is carried out several times, the amount of information about the historical controls rises with every new study. This information can be applied to predict the outcome of one future control using a prediction interval. Since the observations are counts of success out of a given sample size, like mortality or histopathological findings, the data can be assumed to be binomial but may exhibit overdispersion caused by the variability between historical studies. We describe two approaches that account for overdispersion: asymptotic prediction intervals using the quasi-binomial assumption and prediction intervals based on the quantiles of the beta-binomial distribution. Both interval types were α-calibrated using bootstrap methods. For an assessment of the intervals coverage probabilities, a simulation study based on various numbers of historical studies and sample sizes as well as different binomial proportions and varying levels of overdispersion was run. It could be shown that α-calibration can improve the coverage probabilities of both interval types. The coverage probability of the calibrated intervals, calculated based on at least 10 historical studies, was satisfactory close to the nominal 95%. In a last step, the intervals were computed based on a real data set from the NTP homepage, using historical controls from bioassays with the mice strain B6C3F1.
AB - Bioassays are highly standardized trials for assessing the impact of a chemical compound on a model organism. In that context, it is standard to compare several treatment groups with an untreated control. If the same type of bioassay is carried out several times, the amount of information about the historical controls rises with every new study. This information can be applied to predict the outcome of one future control using a prediction interval. Since the observations are counts of success out of a given sample size, like mortality or histopathological findings, the data can be assumed to be binomial but may exhibit overdispersion caused by the variability between historical studies. We describe two approaches that account for overdispersion: asymptotic prediction intervals using the quasi-binomial assumption and prediction intervals based on the quantiles of the beta-binomial distribution. Both interval types were α-calibrated using bootstrap methods. For an assessment of the intervals coverage probabilities, a simulation study based on various numbers of historical studies and sample sizes as well as different binomial proportions and varying levels of overdispersion was run. It could be shown that α-calibration can improve the coverage probabilities of both interval types. The coverage probability of the calibrated intervals, calculated based on at least 10 historical studies, was satisfactory close to the nominal 95%. In a last step, the intervals were computed based on a real data set from the NTP homepage, using historical controls from bioassays with the mice strain B6C3F1.
KW - alpha-calibration bootstrap
KW - beta-binomial
KW - bioassay
KW - extra binomial variation
KW - quasi-binomial
UR - http://www.scopus.com/inward/record.url?scp=85062514015&partnerID=8YFLogxK
U2 - 10.1002/sim.8124
DO - 10.1002/sim.8124
M3 - Article
C2 - 30835886
AN - SCOPUS:85062514015
VL - 38
SP - 2652
EP - 2663
JO - Statistics in medicine
JF - Statistics in medicine
SN - 0277-6715
IS - 14
ER -