Bias in Estimation of Stock-Recruit Function Parameters Caused by Nonrandom Environmental Variability

1988 ◽  
Vol 45 (3) ◽  
pp. 554-557 ◽  
Author(s):  
Michael J. Armstrong ◽  
Peter A. Shelton
Keyword(s):  
Monte Carlo ◽  
Random Distribution ◽  
Environmental Variability ◽  
Random Component ◽  
Periodic Forcing ◽  
Stock Size ◽  
Spawning Stock ◽  
The Mean ◽  
Parameter Precision ◽  
Parameter Values

Parameter estimation for stock–recruit models normally assumes a random distribution of residuals around the underlying function. Monte Carlo simulations, in which departures from the mean stock-recruit function were determined by periodic forcing with a random component, showed that bias may occur in the estimation of average parameter values if randomness is assumed. The bias occurred when the spawning stock size varied in-phase or out-of-phase with the periodic forcing and was greatest when the period was approximately twice the mean age of the spawning stock. In addition to bias, patterning of spawner stock size and recruitment data caused by the periodic variability gave misleading impressions of parameter precision.

Recruitment variation related to fecundity in marine fishes

2000 ◽  
Vol 57 (1) ◽  
pp. 116-124 ◽  
Author(s):  
S J Rickman ◽  
N K Dulvy ◽  
S Jennings ◽  
J D Reynolds
Keyword(s):  
Interannual Variation ◽  
Empirical Studies ◽  
Marine Fishes ◽  
Comparative Approach ◽  
Fish Stock ◽  
Closely Related Species ◽  
Stock Size ◽  
Evolutionary Relatedness ◽  
Spawning Stock ◽  
The Mean

An understanding of the processes that control recruitment variation is central to explaining the population dynamics of fishes and predicting their responses to exploitation. Theory predicts that interannual variation in recruitment should be positively correlated with the fecundity of fish species, but empirical studies have not supported this hypothesis. Here, we adopt a phylogenetic comparative approach, which accounts for evolutionary relatedness among stocks and species, to investigate this relationship. We calculated the mean fecundity of fishes from 52 stocks at the mean length of maturity and related this to interannual recruitment variation. We found that in 13 of 14 comparisons between stocks or closely related species, the stocks with higher fecundity have higher recruitment variation. This was true whether or not we controlled for spawning stock size. However, when the analyses were repeated using a traditional cross-species approach, which did not account for the evolutionary relatedness of stocks, the relationships were not significant. This is the first empirical study to link fecundity with recruitment variation and suggests that fecundity is an important component of fish stock dynamics.

scholarly journals Statistical Mirroring: A Good Alternative Estimator of Dispersion

2021 ◽  
Author(s):  
Kabir Bindawa Abdullahi
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Sample Size ◽  
Main Part ◽  
Random Distribution ◽  
Good Alternative ◽  
Suitable Alternative ◽  
The Mean ◽  
Alternative Estimator ◽  
Artificial Datasets

The statistical properties of a good estimator include robustness, unbiasedness, efficiency, and consistency. However, the commonly used estimators of dispersion have lack or are weak in one or more of these properties. In this paper, I proposed statistical mirroring as a good alternative estimator of dispersion around defined location estimates or points. In the main part of the paper, attention is restricted to Gaussian distribution and only estimators of dispersion around the mean that functionalize with all the observations of a dataset were considered at this time. The different estimators were compared with the proposed estimators in terms of alternativeness, scale and sample size robustness, outlier biasedness, and efficiency. Monte Carlo simulation was used to generate artificial datasets for application. The proposed estimators (of statistical meanic mirroring) turn out to be suitable alternative estimators of dispersion that is less biased (more resistant) to contaminations, robust to scale and sample size, and more efficient to a random distribution of variable than the standard deviation, variance, and coefficient of variation. However, statistical meanic mirroring is not suitable with a mean (of a normal distribution) close to zero, and on a scale below ratio level.

Effects of Initial Conditions on Monte Carlo Estimates of Bias in Estimating Functional Relationships

1988 ◽  
Vol 45 (1) ◽  
pp. 185-187 ◽  
Author(s):  
Robert G. Kope
Keyword(s):  
Monte Carlo ◽  
Time Series Data ◽  
Initial Conditions ◽  
Series Data ◽  
Stock Size ◽  
Functional Relationships ◽  
Stock Recruitment ◽  
Relationship Of ◽  
Parameter Values ◽  
The Relationship

Some of the results presented by Walters (1985. Can. J. Fish. Aquat. Sci. 42: 147–149) for the magnitude of bias in estimating functional relationships from time series data resulted from his choice of initial stock size in Monte Carlo simulations rather than the dynamics of the model. Walters used the same initial stock size in each simulation while varying parameters in the stock–recruitment relationship. Starting each simulation at the equilibrium stock size or allowing initial stock size to vary randomly produces larger estimates of bias and leads to different conclusions about the relationship of bias to parameter values in the model.

Stochastic homogenization and macroscopic modelling of composites and flow through porous media

2002 ◽  
pp. 337-378 ◽  
Author(s):  
Jozef Telega ◽  
Wlodzimierz Bielski
Keyword(s):  
Porous Medium ◽  
Random Distribution ◽  
Flow Through Porous Media ◽  
Macroscopic Models ◽  
Linear Elastic ◽  
Multi Scale ◽  
Convergence Method ◽  
Flow Through ◽  
The Mean ◽  
Random Porous Medium

The aim of this contribution is mainly twofold. First, the stochastic two-scale convergence in the mean developed by Bourgeat et al. [13] is used to derive the macroscopic models of: (i) diffusion in random porous medium, (ii) nonstationary flow of Stokesian fluid through random linear elastic porous medium. Second, the multi-scale convergence method developed by Allaire and Briane [7] for the case of several microperiodic scales is extended to random distribution of heterogeneities characterized by separated scales (stochastic reiterated homogenization). .

scholarly journals Statistical Tests of Symbolic Dynamics

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 817
Author(s):  
Fernando López ◽  
Mariano Matilla-García ◽  
Jesús Mur ◽  
Manuel Ruiz Marín
Keyword(s):  
Monte Carlo ◽  
Symbolic Dynamics ◽  
Null Hypothesis ◽  
Statistical Tests ◽  
General Applicability ◽  
Monte Carlo Experiments ◽  
The Mean ◽  
Theoretical Application ◽  
New Statistics ◽  
General Method

A novel general method for constructing nonparametric hypotheses tests based on the field of symbolic analysis is introduced in this paper. Several existing tests based on symbolic entropy that have been used for testing central hypotheses in several branches of science (particularly in economics and statistics) are particular cases of this general approach. This family of symbolic tests uses few assumptions, which increases the general applicability of any symbolic-based test. Additionally, as a theoretical application of this method, we construct and put forward four new statistics to test for the null hypothesis of spatiotemporal independence. There are very few tests in the specialized literature in this regard. The new tests were evaluated with the mean of several Monte Carlo experiments. The results highlight the outstanding performance of the proposed test.

Rigorous time-domain analysis of statistically oriented graphene sheet fluctuations

2017 ◽  
Vol 36 (5) ◽  
pp. 1351-1363 ◽  
Author(s):  
Athanasios N. Papadimopoulos ◽  
Stamatios A. Amanatiadis ◽  
Nikolaos V. Kantartzis ◽  
Theodoros T. Zygiridis ◽  
Theodoros D. Tsiboukis
Keyword(s):  
Monte Carlo ◽  
Standard Deviation ◽  
Finite Difference ◽  
Surface Waves ◽  
Time Domain ◽  
Finite Difference Time Domain ◽  
Mean Value ◽  
Content Type ◽  
The Mean ◽  
Difference Time

Purpose Important statistical variations are likely to appear in the propagation of surface plasmon polariton waves atop the surface of graphene sheets, degrading the expected performance of real-life THz applications. This paper aims to introduce an efficient numerical algorithm that is able to accurately and rapidly predict the influence of material-based uncertainties for diverse graphene configurations. Design/methodology/approach Initially, the surface conductivity of graphene is described at the far infrared spectrum and the uncertainties of its main parameters, namely, the chemical potential and the relaxation time, on the propagation properties of the surface waves are investigated, unveiling a considerable impact. Furthermore, the demanding two-dimensional material is numerically modeled as a surface boundary through a frequency-dependent finite-difference time-domain scheme, while a robust stochastic realization is accordingly developed. Findings The mean value and standard deviation of the propagating surface waves are extracted through a single-pass simulation in contrast to the laborious Monte Carlo technique, proving the accomplished high efficiency. Moreover, numerical results, including graphene’s surface current density and electric field distribution, indicate the notable precision, stability and convergence of the new graphene-based stochastic time-domain method in terms of the mean value and the order of magnitude of the standard deviation. Originality/value The combined uncertainties of the main parameters in graphene layers are modeled through a high-performance stochastic numerical algorithm, based on the finite-difference time-domain method. The significant accuracy of the numerical results, compared to the cumbersome Monte Carlo analysis, renders the featured technique a flexible computational tool that is able to enhance the design of graphene THz devices due to the uncertainty prediction.

scholarly journals Rapid review of available evidence on the serial interval and generation time of COVID-19

BMJ Open ◽  
2020 ◽  
Vol 10 (11) ◽  
pp. e040263
Author(s):  
John Griffin ◽  
Miriam Casey ◽  
Áine Collins ◽  
Kevin Hunt ◽  
David McEvoy ◽  
...  
Keyword(s):  
Generation Time ◽  
Social Contact ◽  
Careful Consideration ◽  
Rapid Review ◽  
Eligibility Criteria ◽  
Reproduction Numbers ◽  
Serial Interval ◽  
Scientific Papers ◽  
The Mean ◽  
Parameter Values

The serial interval is the time between symptom onsets in an infector–infectee pair. The generation time, also known as the generation interval, is the time between infection events in an infector–infectee pair. The serial interval and the generation time are key parameters for assessing the dynamics of a disease. A number of scientific papers reported information pertaining to the serial interval and/or generation time for COVID-19. Objective Conduct a review of available evidence to advise on appropriate parameter values for serial interval and generation time in national COVID-19 transmission models for Ireland and on methodological issues relating to those parameters. Methods We conducted a rapid review of the literature covering the period 1 January 2020 and 21 August 2020, following predefined eligibility criteria. Forty scientific papers met our inclusion criteria and were included in the review. Results The mean of the serial interval ranged from 3.03 to 7.6 days, based on 38 estimates, and the median from 1.0 to 6.0 days (based on 15 estimates). Only three estimates were provided for the mean of the generation time. These ranged from 3.95 to 5.20 days. One estimate of 5.0 days was provided for the median of the generation time. Discussion Estimates of the serial interval and the generation time are very dependent on the specific factors that apply at the time that the data are collected, including the level of social contact. Consequently, the estimates may not be entirely relevant to other environments. Therefore, local estimates should be obtained as soon as possible. Careful consideration should be given to the methodology that is used. Real-time estimations of the serial interval/generation time, allowing for variations over time, may provide more accurate estimates of reproduction numbers than using conventionally fixed serial interval/generation time distributions.

Kinetic Monte Carlo Simulation of Impurity Effects on Nucleation and Growth of SiC Clusters on Si(100)

2013 ◽  
Vol 740-742 ◽  
pp. 393-396
Author(s):  
Maxim N. Lubov ◽  
Jörg Pezoldt ◽  
Yuri V. Trushin
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Cluster Size ◽  
Kinetic Monte Carlo ◽  
Nucleation And Growth ◽  
Nucleation Density ◽  
Nucleation Process ◽  
Impurity Effects ◽  
Kinetic Monte Carlo Simulations ◽  
The Mean

The influence of attractive and repulsive impurities on the nucleation process of the SiC clusters on Si(100) surface was investigated. Kinetic Monte Carlo simulations of the SiC clusters growth show that that increase of the impurity concentration (both attractive and repulsive) leads to decrease of the mean cluster size and rise of the nucleation density of the clusters.

scholarly journals Evaluation of Bearing Capacity of Strip Footing Using Random Layers Concept

2015 ◽  
Vol 37 (3) ◽  
pp. 31-39 ◽  
Author(s):  
Marek Kawa ◽  
Dariusz Łydżba
Keyword(s):  
Monte Carlo ◽  
Bearing Capacity ◽  
Failure Mechanism ◽  
Design Theory ◽  
Cohesive Soil ◽  
Probability Of Failure ◽  
Mean Value ◽  
Strip Footing ◽  
Random Field Theory ◽  
The Mean

Abstract The paper deals with evaluation of bearing capacity of strip foundation on random purely cohesive soil. The approach proposed combines random field theory in the form of random layers with classical limit analysis and Monte Carlo simulation. For given realization of random the bearing capacity of strip footing is evaluated by employing the kinematic approach of yield design theory. The results in the form of histograms for both bearing capacity of footing as well as optimal depth of failure mechanism are obtained for different thickness of random layers. For zero and infinite thickness of random layer the values of depth of failure mechanism as well as bearing capacity assessment are derived in a closed form. Finally based on a sequence of Monte Carlo simulations the bearing capacity of strip footing corresponding to a certain probability of failure is estimated. While the mean value of the foundation bearing capacity increases with the thickness of the random layers, the ultimate load corresponding to a certain probability of failure appears to be a decreasing function of random layers thickness.

Sign in / Sign up

Export Citation Format

Share Document