On the bias and mean-square error of order-restricted maximum likelihood estimators

2005 ◽  
Vol 130 (1-2) ◽  
pp. 229-250 ◽  
Author(s):  
Sanjay Chaudhuri ◽  
Michael D. Perlman
Keyword(s):  
Maximum Likelihood ◽  
Mean Square Error ◽  
Maximum Likelihood Estimators ◽  
Restricted Maximum Likelihood ◽  
Mean Square ◽  
Order Restricted

Prediction Uncertainty in the Bornhuetter-Ferguson Claims Reserving Method: Revisited

2010 ◽  
Vol 5 (1) ◽  
pp. 7-17 ◽  
Author(s):  
D. H. Alai ◽  
M. Merz ◽  
M. V. Wüthrich
Keyword(s):  
Maximum Likelihood ◽  
Stochastic Model ◽  
Mean Square Error ◽  
Generalized Linear Models ◽  
Linear Models ◽  
Maximum Likelihood Estimators ◽  
Model Parameters ◽  
Mean Square ◽  
Conditional Mean ◽  
Prediction Uncertainty

AbstractWe revisit the stochastic model of Alai et al. (2009) for the Bornhuetter-Ferguson claims reserving method, Bornhuetter & Ferguson (1972). We derive an estimator of its conditional mean square error of prediction (MSEP) using an approach that is based on generalized linear models and maximum likelihood estimators for the model parameters. This approach leads to simple formulas, which can easily be implemented in a spreadsheet.

scholarly journals اقتراح استعمال مبدأ اعظم دالة انتروبي POME على توزيع كاما العام في تقدير احتمالات البقاء للسكان في العراق

2016 ◽  
Vol 22 (93) ◽  
pp. 454
Author(s):  
عمر عبد المحسن علي ◽  
رغدة زياد طارق
Keyword(s):  
Maximum Likelihood ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Mean Square ◽  
Percent Error ◽  
Mean Absolute Percent Error ◽  
Generalized Gamma ◽  
Economic Survey ◽  
Absolute Percent Error

المستخلص: تم في هذا البحث تقدير دالة البقاء على قيد الحياة لبيانات تعاني من اضطراب وتشويش للمسح الاجتماعي والاقتصادي للأسرة في العراق 2012 (Iraq Household Socio-Economic Survey: IHSES II 2012) لبيانات فئات خماسية العمر تتبع توزيع كاما العام (Generalized Gamma: GG). واستعملت طريقتين للأغراض التقدير والموائمة fitting وهي طريقة مبدأ اعظم دالة انتروبي Principle of Maximizing Entropy: POME  وطريقة تمهيد لامعلمية بدالة لبّية Kernel ، للتغلب على المشاكل الرياضية التي تعتري التكاملات التي يتضمنها هذا التوزيع بالذات المتمثلة بتكامل دالة كاما الناقص، هذا الى جانب استعمال الطريقة التقليدية وهي الامكان الاعظم Maximum Likelihood: ML حيث تتم المقارنة على اساس اسلوب الجهاز المركزي للإحصاء في احتساب دالة البقاء من خلال برنامج MORTPAK كقيم حقيقية. وبعد ذلك القيام بالمقارنة باستعمال معيار جذر متوسط مربعات الخطأ Root Mean Square Error: RMSE  ، ومعيار متوسط مطلق نسبة الخطأ Mean Absolute Percent Error: MAPE  . وأظهرت النتائج أفضلية طريقة الانتروبي في تقدير دالة البقاء على الطرائق الاخرى.  

scholarly journals Best estimation for the Reliability of 2-parameter Weibull Distribution

2009 ◽  
Vol 6 (4) ◽  
pp. 705-710
Author(s):  
Baghdad Science Journal
Keyword(s):  
Maximum Likelihood ◽  
Weibull Distribution ◽  
Mean Square Error ◽  
Maximum Likelihood Method ◽  
Likelihood Method ◽  
Statistical Criterion ◽  
Mean Square ◽  
Simulation Process ◽  
The Mean ◽  
Two Parameter

This Research Tries To Investigate The Problem Of Estimating The Reliability Of Two Parameter Weibull Distribution,By Using Maximum Likelihood Method, And White Method. The Comparison Is done Through Simulation Process Depending On Three Choices Of Models (?=0.8 , ß=0.9) , (?=1.2 , ß=1.5) and (?=2.5 , ß=2). And Sample Size n=10 , 70, 150 We Use the Statistical Criterion Based On the Mean Square Error (MSE) For Comparison Amongst The Methods.

scholarly journals Optimal Designs For the Restricted Maximum Likelihood Estimators in a Random Split-Plot Model

2017 ◽  
Vol 56 (1) ◽  
pp. 64-71
Author(s):  
Oluwole Nuga ◽  
G. N. Amahia ◽  
Fatai Salami
Keyword(s):  
Maximum Likelihood ◽  
Variance Components ◽  
Information Matrix ◽  
Maximum Likelihood Estimators ◽  
Restricted Maximum Likelihood ◽  
Optimal Designs ◽  
Absolute Difference ◽  
Statistical Efficiency ◽  
Split Plot ◽  
True Values

The design effect for the restricted maximum likelihood estimators of variance components in acompletely randomized split-plot model is studied. The model was used to represent the response generated froman experimental scenario where the whole-plot and split-plot factors are random. The work generated groups ofbalanced designs from same number of experimental runs and compared them for optimality using the derived Fisher Information matrix of the restricted maximum likelihood (REML) estimators. The measure for optimalityis the D-optimality criterion; the resulting optimal designs depend on the relative magnitudes of the true values of the variance components. The results show that when the factor variances are larger than the error variances, designs where the absolute difference between the number of whole-plots and the number of levels of the splitplot factor is relatively small show substantial gain in statistical efficiency over other designs.

scholarly journals "Evaluation of Some Methods for Estimating the Weibull Distribution Parameters"

2017 ◽  
Vol 4 (2) ◽  
pp. 8-14
Author(s):  
J. A. Labban ◽  
H. H. Depheal
Keyword(s):  
Maximum Likelihood ◽  
Maximum Likelihood Estimation ◽  
Weibull Distribution ◽  
Least Squares ◽  
Mean Square Error ◽  
Random Sample ◽  
Likelihood Estimation ◽  
Mean Square ◽  
Distribution Parameters

"This paper some of different methods to estimate the parameters of the 2-Paramaters Weibull distribution such as (Maximum likelihood Estimation, Moments, Least Squares, Term Omission). Mean square error will be considered to compare methods fits in case to select the best one. There by simulation will be implemented to generate different random sample of the 2-parameters Weibull distribution, those contain (n=10, 50, 100, 200) iteration each 1000 times."

scholarly journals Data bank: nine numerical methods for determining the parameters of weibull for wind energy generation tested by five statistical tools

2021 ◽  
Vol 12 (2) ◽  
pp. 1114
Author(s):  
Ahmed Samir Badawi ◽  
Siti Hajar Yusoff ◽  
Alhareth Mohammed Zyoud ◽  
Sheroz Khan ◽  
Aisha Hashim ◽  
...  
Keyword(s):  
Maximum Likelihood ◽  
Numerical Methods ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Prediction Accuracy ◽  
Maximum Likelihood Method ◽  
Likelihood Method ◽  
Mean Square ◽  
Modified Maximum Likelihood

This study aims to determine the potential of wind energy in the mediterranean coastal plain of Palestine. The parameters of the Weibull distribution were calculated on basis of wind speed data. Accordingly, two approaches were employed: analysis of a set of actual time series data and theoretical Weibull probability function. In this analysis, the parameters Weibull shape factor ‘<em>k</em>’ and the Weibull scale factor ‘<em>c</em>’ were adopted. These suitability values were calculated using the following popular methods: method of moments (MM), standard deviation method (STDM), empirical method (EM), maximum likelihood method (MLM), modified maximum likelihood method (MMLM), second modified maximum likelihood method (SMMLM), graphical method (GM), least mean square method (LSM) and energy pattern factor method (EPF). The performance of these numerical methods was tested by root mean square error (RMSE), index of agreement (IA), Chi-square test (X<sup>2</sup>), mean absolute percentage error (MAPE) and relative root mean square error (RRMSE) to estimate the percentage of error. Among the prediction techniques. The EPF exhibited the greatest accuracy performance followed by MM and MLM, whereas the SMMLM exhibited the worst performance. The RMSE achieved the best prediction accuracy, whereas the RRMSE attained the worst prediction accuracy.

Sign in / Sign up

Export Citation Format

Share Document