Will the Number of Replicates In Bootstrapped Data Alter the Bioequivalence Results?
Journal Title: UNKNOWN - Year 2015, Vol 4, Issue 2
Abstract
"The estimation of 90% parametric confidence intervals (CIs) of mean Cmax and AUC’s ratios in bioequivalence (BE) tests are based upon the assumption that formulation effects of test and reference drug are comparable. Bootstrap nonparametric 90% CIs of formulation effects were estimated with the different replicates (500, 1000, 2000 and 5000) and then compared with the parametric 90% CIs of the original datasets. Histograms and density curves of formulation effects obtained from resampled datasets were similar to those of normal distribution. Currently, the 80 - 125% rule based upon the parametric 90% CIs is widely accepted under the assumption of normally distributed formulation effects in log-transformed data. However, number of replicates in the bootstrapping has significant impact on altering the study results "
Authors and Affiliations
Keywords
Related Articles
- EP ID EP356207
- DOI -
- Views 83
- Downloads 0
The Determination of Minimum Bubbling Velocity, Minimum Fluidization Velocity and Fluidization Index of Fine Powders (Hematite) using Gas-Solid Tapered Beds
The Determination of Minimum Bubbling Velocity, Minimum Fluidization Velocity and Fluidization Index of Fine Powders (Hematite) using Gas-Solid Tapered Beds
Operative Treatment of Thyroid Nodules
A thyroid nodule is a growth within the thyroid gland. Thyroid nodules are extremely common and can be seen in 5 to 10 percent of women and 1 to 5 percent of men. Fine-needle aspiration biopsy (FNAB) is the gold-standard...
A Rare Case of Acrocallosal Syndrome in a Neonate – A Case Report
"ABSTRACT Acrocallosal syndrome is characterised by classical craniofacial and digital malformations with partial or complete agenesis of corpus callosum. This is considered as a rare disorder and is included in the Rare...
Survey Paper on Data Mining Using Neural Network
Data Mining means mine or sorted important data from huge amount of data. It is most useful in every field like business, engineering, web data etc. Classification of data is most difficult task in data mining which is u...
Review of Multi-objective Evolutionary Algorithm
Datamining is an analytic process designed to explore data in search of consistent patterns and/or systematic relationships between variables, and then to validate the findings by applying the detected patterns to new su...