هقارنت طرائق تقذير هعلواث توزيع كاها ري املعلوتني

Similar documents
Comparing Different Estimators for Parameters of Kumaraswamy Distribution

Available online at J. Math. Comput. Sci. 2 (2012), No. 4, ISSN:

FBD of SDOF Base Excitation. 2.4 Base Excitation. Particular Solution (sine term) SDOF Base Excitation (cont) F=-(-)-(-)= 2ζω ωf

Supplementary Information

Cameras and World Geometry

O & M Cost O & M Cost

Numerical Solution of Sine-Gordon Equation by Reduced Differential Transform Method

An Asymptotic Expansion for the Non-Central Chi-square Distribution. By Jinan Hamzah Farhood Department of Mathematics College of Education

Spectrum of The Direct Sum of Operators. 1. Introduction

Comparison between Fourier and Corrected Fourier Series Methods

Department of Mathematical and Statistical Sciences University of Alberta

Mathematical Statistics. 1 Introduction to the materials to be covered in this course

Relations on the Apostol Type (p, q)-frobenius-euler Polynomials and Generalizations of the Srivastava-Pintér Addition Theorems

Ideal Amplifier/Attenuator. Memoryless. where k is some real constant. Integrator. System with memory

Moment Generating Function

Outline. Review Homework Problem. Review Homework Problem II. Review Dimensionless Problem. Review Convection Problem

Degree of Approximation of Fourier Series

Sampling Example. ( ) δ ( f 1) (1/2)cos(12πt), T 0 = 1

WILD Estimating Abundance for Closed Populations with Mark-Recapture Methods

b : the two eigenvectors of the Grover iteration Quantum counting algorithm

Processamento Digital de Sinal

Parameter Optimization of Multi-element Synthetic Aperture Imaging Systems

th m m m m central moment : E[( X X) ] ( X X) ( x X) f ( x)

Extended Laguerre Polynomials

S n. = n. Sum of first n terms of an A. P is

10.3 Autocorrelation Function of Ergodic RP 10.4 Power Spectral Density of Ergodic RP 10.5 Normal RP (Gaussian RP)

ABSOLUTE INDEXED SUMMABILITY FACTOR OF AN INFINITE SERIES USING QUASI-F-POWER INCREASING SEQUENCES

New Class of Estimators of Population Mean. DECISION SCIENCES INSTITUTE New Class of Estimators of Population Mean Utilizing Median of Study Variable

Recurrence Relations for the Product, Ratio and Single Moments of Order Statistics from Truncated Inverse Weibull (IW) Distribution

Institute of Actuaries of India

Inference of the Second Order Autoregressive. Model with Unit Roots

LESSON 15: COMPOUND INTEREST

Big O Notation for Time Complexity of Algorithms

Paper Introduction. ~ Modelling the Uncertainty in Recovering Articulation from Acoustics ~ Korin Richmond, Simon King, and Paul Taylor.

Analysis of Using a Hybrid Neural Network Forecast Model to Study Annual Precipitation

Calculus Limits. Limit of a function.. 1. One-Sided Limits...1. Infinite limits 2. Vertical Asymptotes...3. Calculating Limits Using the Limit Laws.

ECSE Partial fraction expansion (m<n) 3 types of poles Simple Real poles Real Equal poles

F.Y. Diploma : Sem. II [AE/CH/FG/ME/PT/PG] Applied Mathematics

On a Z-Transformation Approach to a Continuous-Time Markov Process with Nonfixed Transition Rates

The Eigen Function of Linear Systems

1. Solve by the method of undetermined coefficients and by the method of variation of parameters. (4)

OLS bias for econometric models with errors-in-variables. The Lucas-critique Supplementary note to Lecture 17

Pure Math 30: Explained!

CSE 241 Algorithms and Data Structures 10/14/2015. Skip Lists

STUDY OF THE STRESS-STRENGTH RELIABILITY AMONG THE PARAMETERS OF GENERALIZED INVERSE WEIBULL DISTRIBUTION

xp (X = x) = P (X = 1) = θ. Hence, the method of moments estimator of θ is

The Non-Truncated Bulk Arrival Queue M x /M/1 with Reneging, Balking, State-Dependent and an Additional Server for Longer Queues

ODEs II, Supplement to Lectures 6 & 7: The Jordan Normal Form: Solving Autonomous, Homogeneous Linear Systems. April 2, 2003

Section 8 Convolution and Deconvolution

Intro to multivariate AR(1) models estimating interaction strengths, aka the B matrix

ECE 350 Matlab-Based Project #3

The Central Limit Theorems for Sums of Powers of Function of Independent Random Variables

The Central Limit Theorem

On a Problem of Littlewood

CSE 202: Design and Analysis of Algorithms Lecture 16

BEST LINEAR FORECASTS VS. BEST POSSIBLE FORECASTS

MATH Midterm Solutions

Basic Results in Functional Analysis

B. Maddah INDE 504 Simulation 09/02/17

N! AND THE GAMMA FUNCTION

The analysis of the method on the one variable function s limit Ke Wu

Exercise 3 Stochastic Models of Manufacturing Systems 4T400, 6 May

FIXED FUZZY POINT THEOREMS IN FUZZY METRIC SPACE

6/10/2014. Definition. Time series Data. Time series Graph. Components of time series. Time series Seasonal. Time series Trend

( ) ( ) Weibull Distribution: k ti. u u. Suppose t 1, t 2, t n are times to failure of a group of n mechanisms. The likelihood function is

TAKA KUSANO. laculty of Science Hrosh tlnlersty 1982) (n-l) + + Pn(t)x 0, (n-l) + + Pn(t)Y f(t,y), XR R are continuous functions.

M-ary Detection Problem. Lecture Notes 2: Detection Theory. Example 1: Additve White Gaussian Noise

Linear Time Invariant Systems

ON POINTWISE APPROXIMATION OF FUNCTIONS BY SOME MATRIX MEANS OF FOURIER SERIES

INTEGER INTERVAL VALUE OF NEWTON DIVIDED DIFFERENCE AND FORWARD AND BACKWARD INTERPOLATION FORMULA

Estimation of the Correlation Coefficient for a Bivariate Normal Distribution with Missing Data

On The Estimation of Two Missing Values in Randomized Complete Block Designs

Low-complexity Algorithms for MIMO Multiplexing Systems

Development of Kalman Filter and Analogs Schemes to Improve Numerical Weather Predictions

Chapter 3 Moments of a Distribution

Introduction to Engineering Reliability

APPLICATION OF A Z-TRANSFORMS METHOD FOR INVESTIGATION OF MARKOV G-NETWORKS

L-functions and Class Numbers

2012 GCE A Level H2 Maths Solution Paper Let x,

2 f(x) dx = 1, 0. 2f(x 1) dx d) 1 4t t6 t. t 2 dt i)

Maximum Likelihood Estimation

PRICING AMERICAN PUT OPTION WITH DIVIDENDS ON VARIATIONAL INEQUALITY

Algebra 2A. Algebra 2A- Unit 5

Research Article On Pointwise Approximation of Conjugate Functions by Some Hump Matrix Means of Conjugate Fourier Series

July 24-25, Overview. Why the Reliability Issue is Important? Some Well-known Reliability Measures. Weibull and lognormal Probability Plots

Review - Week 10. There are two types of errors one can make when performing significance tests:

Fresnel Dragging Explained

BINOMIAL THEOREM OBJECTIVE PROBLEMS in the expansion of ( 3 +kx ) are equal. Then k =

Stationarity and Error Correction

UNIVERSITY OF CANTABRIA

Research Design - - Topic 2 Inferential Statistics: The t-test 2010 R.C. Gardner, Ph.D. Independent t-test

An Analysis of State Evolution for Approximate Message Passing with Side Information

Samuel Sindayigaya 1, Nyongesa L. Kennedy 2, Adu A.M. Wasike 3

TWO INTERFACIAL COLLINEAR GRIFFITH CRACKS IN THERMO- ELASTIC COMPOSITE MEDIA

Improvement Over General And Wider Class of Estimators Using Ranked Set Sampling

Fourier transform. Continuous-time Fourier transform (CTFT) ω ω

K3 p K2 p Kp 0 p 2 p 3 p

Suppose we have observed values t 1, t 2, t n of a random variable T.

AN ALGEBRAIC APPROACH TO M-BAND WAVELETS CONSTRUCTION

A Note on a Characterization of J-Shaped Distribution. by Truncated Moment

Transcription:

هقارنت طرائق تقذير هعلواث توزيع كاها ري املعلوتني يف حالت البياناث املفقودة باستخذام احملاكاة د أ. الباحثة ظافر حسين رشيد جامعة بغداد- كمية االدارة واالقتصاد قسم االحصاء آوات سردار وادي املستخلص Maxiu Lielihood Mehod Shiage Mehod Siha ho Bowa, Sheo ad La Moe Calo MSE Absac he esiaio of he paaees of wo Paaees Gaa Disibuio i case of issig daa has bee ade by usig wo ipoa ehods: he Maxiu Lielihood Mehod ad he Shiage Mehod. he foe oe cosiss of hee ehods o solve he MLE o-liea equaio by which he esiaos of he axiu lielihood ca be obaied: ewo-raphso, ho ad Siha ehods. ho ad Siha ehods ae developed by he eseache o be suiable i case of issig daa. Fuheoe, he Bowa, Sheo ad La Mehod, which depeds o he hee Paaees Gaa Disibuio o ge he axiu lielihood esiaos, has bee developed. A copaiso has bee ade bewee he ehods i he expeieal aspec o fid he bes ehod hough siulaio by usig he Moe Calo Mehod. Seveal expeieaios have bee ade by usig he ipoa saisical easue: Mea Squae Eo MSE. : املقذهت واهلذف:

Icoplee Dey Coi ad Dey Coi ad JI Maxiu Lielihood Mehod Siha ho Shiage Mehod Siha, Bowa, Sheo ad La Moe Calo MSE : تقذير هعلواث توزيع كاها ري املعلوتني يف حالت البياناث املفقودة:

Disibuio of Cuulaive ie- o- Failue Lielihood Fucio MLEs Maxiu Lielihood Esiaio, = X + X + +X ;=,,, X i X i ~ i.i.d gaa, X i i ~ gaa, ; =,,, ; =,,, f f \ exp X i f f \ P R PR= Mixue Model

f f \ exp P R exp P R=,, =,,, =,,, = ax {\ > 0} M M M /

Esiaig by Maxiu Lielihood Mehod i i i exp L, i i L, f exp, \ f \ LL, M ML L L L L M : LL, M 0 : LL, ML L LL

Digaa Fucio ML L ML ML L ML... 5 0 6 4 L Maxiu Lielihood Esiaios MLEs ewo-raphso Mehod i 4 i i i i g g g ML g

i i i i i ML i M, Develope of ho Mehod ho ho L 4y /3, 4y L ho L L / ML

0 / 6 L L L 4 / 3 4 Siha Develope of Siha Mehod Siha L, y Siha L

ML L ] [ ML ML L L s L s s s

Bowa, Sheo ad La Develope of Bowa, Sheo ad La Mehod Bowa, Sheo ad La, 3, X i Rado Vaiable 0 0,, ;, x I e x x f x X 30 i X i Moe Geeaig Fucio X = Ee X dx e x e x x y = x X e 3 Z = Z Z Ee X X X Ee... ] ]...[ ][ [ X X X

= e e e... i X i Z e 3 e f f ; \ 33 \,,,, f L exp 34

LL M LL M LL L ML LL 0 0 0 35 A 36 M A M A A 37

A M A =0 bl bl bl 38 M, bl bl 3- التقذير باستخذام طريقت التقلص طريقت هقرتحت: Esiaio by Shiage Mehod Poposed Mehod Siha ho ho Siha hopso ~ h h 0 h 39 ~ ~ h h ~ MSE ~ E E[ h h ]

h MSE ~ h MSE h h B h h h [ MSE ~ h h ] 40 0 h 4 [ MSE h 4 ] h 3: اجلانب التجريبي: = 6, =0,30,50,00 =,,,

=6, = =,,, =6 =,,, 6 =0 4- اختيار قين املعلواث االفرتاضيت: Ivese asfo 0, xi,,,..., x i i,,..., i Logu, i i,,..., Coiuous Uifo Vaiae 43 44 u i

38 L MSE i L MSE 4 i L =6 Model s bl sh 0.8066.849.3490.958.58030 30.08993.09045.044303.469.067377 50.04854.048776.00645.076054.0570 00.0307.030648 0.98450.046986.007584 0.9364.93790.46558.388.7074 30.9373.9388.46660.535.7070 50.837.8473.0856.4433.04865 00.05534.0568.00548.06568.0908 0 3.466788 3.466856 3.4955 3.49059 3.443056 30 3.303605 3.30367 3.56079 3.387 3.79875 50 3.6837 3.68385 3.0806 3.8039 3.44595 00 3.093468 3.093536 3.045960 3.099038 3.069748

Model 3 = 6 s MSE bl sh 0 0.960 0.9598 0.04508 0.35964 0.58 30 0.0973 0.0947 0.09646 0.4936 0.09954 50 0.046000 0.045986 0.043455 0.05340 0.04488 00 0.03558 0.03554 0.0766 0.07795 0.068 0 0.7348 0.7345 0.70544 0.749495 0.77889 30 0.40874 0.40855 0.39858 0.45460 0.399499 50 0.789 0.7883 0.0779 0.3373 0.80 00 0.088964 0.088957 0.0863 0.09566 0.086983 0.635.6335.569675.66847.590438 30 0.86749 0.86740 0.835807 0.898 0.848707 50 0.447087 0.447079 0.4334 0.469963 0.439544 00 0.9575 0.95749 0.8905 0.05979 0.98 =6 Model 3 s bl sh 0.94603.95096.4834.3398.778 30.09895.099449.0594.3368.07686 50.0509.0563.005388.078905.0850 00.03345.033974 0.987699.050349.00837 0.5685.5759.8056.6433.39908 30.003.00387.076705.97.088546 50.068009.068083.044399.076006.0564 00.07479.07553.00393.0358.05738 0.59968.5999.44076.67975.5033 30.0583.05853.089933.859.097893 50.058069.05809.0495.0603.05043 00.03088.030.0636.033976.0473

Model =6 MSE s bl sh 3 0 0.4343 0.436 0.589 0.64597 0.337 30 0.638 0.69 0.07993 0.30088 0.565 50 0.05586 0.05580 0.04986 0.06045 0.050396 00 0.06605 0.06607 0.058 0.030977 0.05407 0 0.98553 0.98546 0.943 0.03909 0.94847 30 0.0836 0.083 0.0386 0.79 0.05933 50 0.05964 0.0596 0.056765 0.06370 0.058053 00 0.03487 0.03486 0.0663 0.056 0.0935 0 0.906 0.905 0.85054 0.9645 0.8756 30 0.03539 0.03538 0.006 0.07 0.0837 50 0.050805 0.050805 0.0495 0.053348 0.04995 00 0.0655 0.0655 0.0853 0.03890 0.09 = Model s bl sh 3 0.50498.5077.863.7789.34467 30.094805.095085.06494.97.078790 50.055664.05594.03354.079.039648 00.0309.03369 0.999787.04876.06078 0.338.33898.99765.36875.3633 30.96489.96568.63445.363.80006 50.4595.4673.08557.363.0985 00.056454.05653.0340.05995.039976 0 3.50888 3.50896 3.475607 3.5783 3.496 30 3.86676 3.867 3.5343 3.303935 3.70063 50 3.00047 3.0008 3.6678 3.05076 3.8343 00 3.089478 3.08954 3.0569 3.09590 3.07867

Model = s MSE bl sh 3 0 0.870 0.854 0.75 0.90090 0.76487 30 0.0865 0.0860 0.0337 0.759 0.05698 50 0.046087 0.04608 0.04348 0.050 0.044485 00 0.0584 0.0583 0.0494 0.05 0.0773 0 0.80876 0.808749 0.787537 0.84644 0.797868 30 0.398460 0.398450 0.386374 0.49959 0.3938 50 0.0363 0.0357 0.94769 0.06300 0.97789 00 0.08467 0.08465 0.08476 0.087750 0.08547 0.85380.85370.80.889703.836468 30 0.90387 0.90386 0.8857 0.935539 0.894509 50 0.4730 0.47308 0.46000 0.476940 0.465877 00 0.0840 0.0838 0.05940 0.79 0.08 = Model s bl sh 3 0.6003.60478.769.878.44049 30.09697.09707.06455.069.080879 50.058863.0594.06446.074605.04794 00.03456.034805.005.04594.08478 0.7009.7030.53496.8445.683 30.0854.0894.08576.07.093585 50.059657.059696.0430.064009.05399 00.0985.0934.0749.03044.0036 0.73486.73498.6358.79734.6798 30.09865.09867.087500.0436.093064 50.067553.067565.056454.06993.06009 00.030546.030558.09453.03675.05005

Model = s MSE bl sh 3 0 0.00 0.00 0.90769 0.0934 0.95663 30 0.4 0.409 0.0846 0.4037 0.044 50 0.049788 0.049786 0.04674 0.055407 0.04798 00 0.0508 0.0509 0.03664 0.07646 0.04079 0 0.07934 0.0793 0.0369 0.6578 0.0508 30 0.0404 0.040 0.00863 0.09059 0.044 50 0.053044 0.05304 0.0557 0.054334 0.0508 00 0.090 0.0909 0.077 0.0849 0.0474 0 0.657 0.656 0.0880 0.6438 0.0707 30 0.05057 0.05056 0.093 0.0859 0.03954 50 0.053677 0.053677 0.0568 0.054073 0.0594 00 0.04364 0.04364 0.03789 0.0537 0.04046

: 4 االستنتاجاث والتوصياث, MSE Siha, ho Bowa, Sheo ad La

املصادر العربيت: املصادر األجنبيت:. Bowa, K.O., Sheo, L.R. ad La, H.K. 987 Siulaio ad Easiaio Pobles Associaed wih he 3-Paaee Gaa Desiy. Couicaios i Saisics, Seies B- Siulaio ad Copuaio, Vol.6, o.4, PP.47-88.. Choi, S.C., ad Wee, R. 969, Maxiu Lielihood Esiaio of he Paaees of he Gaa Disibuio ad hei Bias, echoeics, Vol., o. 4, PP. 683-690.. Coi, D.W., ad Dey, K.A. 999, Aalysis of Gouped Daa fo Field- Failue Repoig Syses, Reliabiliy Egieeig ad Syse Safey, 65, 95-0.. Coi, D.W., ad JI,. 000, Gaa Disibuio Paaee Esiaio fo Field Reliabiliy Daa wih Missig Failue ies, IEEE asacios, 3, 6-66.. Dey, K.A. 98, Saisical Aalysis of oisy ad Icoplee Failue Daa i Poceedigs Aual Reliabiliy ad Maiaiabiliy Syposiu RAMS, IEEE, Piscaaway. J. PP. 93-97.. Lawless. J. F. 003, Saisical Models ad Mehods fo Lifeie Daa, d ed., ew Jesey, Joh Wiley & Sos, Ic.. Sheo, L. R., ad Bowa, K.O. 970, Reas o ho s Esiaos fo he Gaa Disibuio, Mohly Weahe Review, Vol. 98, o., PP. 54-60.