A Solution to the Effect of Sample Size on Outlier Elimination

1994 ◽  
Vol 47 (3) ◽  
pp. 631-650 ◽  
Author(s):  
Mark Van Selst ◽  
Pierre Jolicoeur
Keyword(s):  
Monte Carlo ◽  
Standard Deviation ◽  
Sample Size ◽  
Monte Carlo Study ◽  
The Other ◽  
Recursive Procedure ◽  
Elimination Procedure ◽  
New Procedures

Results from a Monte Carlo study demonstrate how a non-recursive, a simple recursive, a modified recursive, and a hybrid outlier elimination procedure are influenced by population skew and sample size. All the procedures are based on computing a mean and a standard deviation from a sample in order to determine whether an observation is an outlier. Miller (1991) showed that the estimated mean produced by the simple non-recursive procedure can be affected by sample size and that this effect can produce a bias in certain kinds of experiments. We extended this result to the other three procedures. We also create two new procedures in which the criterion used to identify outliers is adjusted as a function of sample size so as to produce results that are unaffected by sample size.

scholarly journals Skewness of Maximum Likelihood Estimators in the Weibull Censored Data

Symmetry ◽  
2019 ◽  
Vol 11 (11) ◽  
pp. 1351 ◽  
Author(s):  
Tiago M. Magalhães ◽  
Diego I. Gallardo ◽  
Héctor W. Gómez
Keyword(s):  
Monte Carlo ◽  
Maximum Likelihood ◽  
Sample Size ◽  
Censored Data ◽  
Maximum Likelihood Estimators ◽  
Monte Carlo Study ◽  
Parameter Distribution ◽  
Regression Parameter ◽  
Skewness Coefficient ◽  
Matrix Formula

In this paper, we obtain a matrix formula of order n − 1 / 2 , where n is the sample size, for the skewness coefficient of the distribution of the maximum likelihood estimators in the Weibull censored data. The present result is a nice approach to verify if the assumption of the normality of the regression parameter distribution is satisfied. Also, the expression derived is simple, as one only has to define a few matrices. We conduct an extensive Monte Carlo study to illustrate the behavior of the skewness coefficient and we apply it in two real datasets.

Monte Carlo Study on Thermal Transport in Si/Ge Superlattice Basing on Phonon Dispersion Discrepancies

2011 ◽  
Vol 284-286 ◽  
pp. 392-395
Author(s):  
Zan Wang ◽  
Hong Yu Zhu ◽  
Yi Wu Ruan
Keyword(s):  
Monte Carlo ◽  
Thermal Transport ◽  
Phonon Dispersion ◽  
Monte Carlo Model ◽  
Monte Carlo Study ◽  
The Other ◽  
Pass Through

Based on the classical diffuse mismatch model (DMM), the dedicated Monte Carlo model for Si/Ge superlattice is proposed and the method to cope with the scattering at the interface is provided. In this model, phonons transport between two different materials can be taken as the movements between the different phonon dispersion relationships. If there is a corresponding position in the other material, the phonon with a given frequency will be able to pass through the interface, otherwise it will be reflected.

Monte Carlo Simulation of the Growth of ZnSe by MBE

1986 ◽  
Vol 77 ◽  
Author(s):  
R. Venkatasubramanian ◽  
N. Otsuka ◽  
S. Datta ◽  
L. A. Kolodziejski ◽  
R. L. Gunshor
Keyword(s):  
Monte Carlo Simulation ◽  
Monte Carlo ◽  
Molecular Beam ◽  
Flux Ratio ◽  
Monte Carlo Study ◽  
The Other ◽  
Structural Quality ◽  
Wide Range

ABSTRACTA Monte Carlo study of the growth of ZnSe by Molecular beam epitaxy is presented. The study is focused on the role of surface kinetic reactions on the structural quality of the epilayers. Two different models for the incorporation of Se molecules, one with a highly reactive physisorbed state and the other with a relatively nonreactive physisorbed state are employed for simulations. It is shown that the structural quality of the epilayers is very sensitive to the flux ratio if the physisorbed state is relatively nonreactive. It is also shown that if the physisorbed state is highly reactive, good quality epilayers are obtained over a wide range of flux ratio.

Pairwise Multiple Comparison Procedures with Unequal N’s and/or Variances: A Monte Carlo Study

1976 ◽  
Vol 1 (2) ◽  
pp. 113-125 ◽  
Author(s):  
Paul A. Games ◽  
John F. Howell
Keyword(s):  
Monte Carlo ◽  
Sample Size ◽  
Error Rate ◽  
Type I Error ◽  
Monte Carlo Study ◽  
Multiple Comparison ◽  
Type I ◽  
Type I Errors ◽  
Type I Error Rate ◽  
Multiple Comparison Procedures

Three different methods for testing all pairs of yȳk, - yȳk’ were contrasted under varying sample size (n) and variance conditions. With unequal n’s of six and up, only the Behrens-Fisher statistic provided satisfactory control of both the familywise rate of Type I errors and Type I error rate on each contrast. Satisfactory control with unequal n’s of three and up is dubious even with this statistic.

Sign in / Sign up

Export Citation Format

Share Document