Estimation of population profiles of two strains of the fly Megaselia scalaris (Diptera: Phoridae) by bootstrap simulation

Abstract

Based on experimental population profiles of strains of the fly Megaselia scalaris (Phoridae), the minimal number of sample profiles was determined that should be repeated by bootstrap simulation process in order to obtain a confident estimation of the mean population profile and present estimations of the standard error as a precise measure of the simulations made. The original data are from experimental populations founded with SR and R4 strains, with three replicates, which were kept for 33 weeks by serial transfer technique in a constant temperature room (25 +/- 1.0 degrees C). The variable used was population size and the model adopted for each profile was a stationary stochastic process. By these simulations, the three experimental population profiles were enlarged so as to determine minimum sample size. After sample size was determined, bootstrap simulations were made in order to calculate confidence intervals and to compare the mean population profiles of these two strains. The results show that with a minimum sample size of 50, stabilization of means begins.

Increasing transparency in machine learning through bootstrap simulation and shapely additive explanations

“…The use of bootstrap simulation generates 10,000 training and test-set combinations and thus also 10,000 model accuracy statistics and covariate gain statistics [31][32][33]. This method allows for empiric evaluation of the variability in model accuracy to increase the transparency of model efficacy [34][35][36].…”

“…This highlights a potential issue in replication of machine-learning methods on similar cohorts [22,[44][45][46][47]. Two studies may find vastly different results in the predictive accuracy of machine-learning methods even if they use near identical models, covariates, and model summary statistics just due to the choice of the train-test sets (which are determined strictly by random number generation) [32,35,36,48,49]. As a result, this study highlights the importance of utilizing multiple different train and test sets when executing machine-learning for prediction of clinical outcomes to accurately represent the variance that is present just in the choice of selection of train and test sets [16,18,50].…”