A CLASS OF TRANSFORMED EFFICIENT RATIO ESTIMATORS OF FINITE POPULATION MEAN. Department of Statistics, Islamia College, Peshawar, Pakistan 2

Similar documents
The Grouping Methods and Rank Estimator, Based on Ranked Set sampling, for the linear Error in Variable Models

An Accurate Evaluation of Integrals in Convex and Non convex Polygonal Domain by Twelve Node Quadrilateral Finite Element Method

A New Approach For the Ranking of Fuzzy Sets With Different Heights

Sum of Linear and Fractional Multiobjective Programming Problem under Fuzzy Rules Constraints

2x x l. Module 3: Element Properties Lecture 4: Lagrange and Serendipity Elements

Simulation: Solving Dynamic Models ABE 5646 Week 11 Chapter 2, Spring 2010

Feature Reduction and Selection

Solitary and Traveling Wave Solutions to a Model. of Long Range Diffusion Involving Flux with. Stability Analysis


y and the total sum of

Proper Choice of Data Used for the Estimation of Datum Transformation Parameters

Solving two-person zero-sum game by Matlab

Variance estimation in EU-SILC survey

Lecture #15 Lecture Notes

A NOTE ON FUZZY CLOSURE OF A FUZZY SET

A Simple and Efficient Goal Programming Model for Computing of Fuzzy Linear Regression Parameters with Considering Outliers

Programming in Fortran 90 : 2017/2018

X- Chart Using ANOM Approach

Parallelism for Nested Loops with Non-uniform and Flow Dependences

Smoothing Spline ANOVA for variable screening

S1 Note. Basis functions.

Quality Improvement Algorithm for Tetrahedral Mesh Based on Optimal Delaunay Triangulation

Control strategies for network efficiency and resilience with route choice

Convex Fuzzy Set, Balanced Fuzzy Set, and Absolute Convex Fuzzy Set in a Fuzzy Vector Space

Empirical Distributions of Parameter Estimates. in Binary Logistic Regression Using Bootstrap

F Geometric Mean Graphs

Determining the Optimal Bandwidth Based on Multi-criterion Fusion

NUMERICAL SOLVING OPTIMAL CONTROL PROBLEMS BY THE METHOD OF VARIATIONS

An Application of the Dulmage-Mendelsohn Decomposition to Sparse Null Space Bases of Full Row Rank Matrices

Accounting for the Use of Different Length Scale Factors in x, y and z Directions

Optimization Methods: Integer Programming Integer Linear Programming 1. Module 7 Lecture Notes 1. Integer Linear Programming

Categories and Subject Descriptors B.7.2 [Integrated Circuits]: Design Aids Verification. General Terms Algorithms

Some Advanced SPC Tools 1. Cumulative Sum Control (Cusum) Chart For the data shown in Table 9-1, the x chart can be generated.

Review of approximation techniques

Support Vector Machines

KFUPM. SE301: Numerical Methods Topic 8 Ordinary Differential Equations (ODEs) Lecture (Term 101) Section 04. Read

Numerical Solution of Deformation Equations. in Homotopy Analysis Method

Classification / Regression Support Vector Machines

Intra-Parametric Analysis of a Fuzzy MOLP

Mathematics 256 a course in differential equations for engineering students

Solving Route Planning Using Euler Path Transform

Solutions to Programming Assignment Five Interpolation and Numerical Differentiation

Outline. Type of Machine Learning. Examples of Application. Unsupervised Learning

Unsupervised Learning and Clustering

THE FUZZY GROUP METHOD OF DATA HANDLING WITH FUZZY INPUTS. Yuriy Zaychenko

Cluster Analysis of Electrical Behavior

Introduction to Geometrical Optics - a 2D ray tracing Excel model for spherical mirrors - Part 2

Skew Angle Estimation and Correction of Hand Written, Textual and Large areas of Non-Textual Document Images: A Novel Approach

Hermite Splines in Lie Groups as Products of Geodesics

SLAM Summer School 2006 Practical 2: SLAM using Monocular Vision

Enhanced AMBTC for Image Compression using Block Classification and Interpolation

7/12/2016. GROUP ANALYSIS Martin M. Monti UCLA Psychology AGGREGATING MULTIPLE SUBJECTS VARIANCE AT THE GROUP LEVEL

Design of Georeference-Based Emission Activity Modeling System (G-BEAMS) for Japanese Emission Inventory Management

Load Balancing for Hex-Cell Interconnection Network

Fuzzy Filtering Algorithms for Image Processing: Performance Evaluation of Various Approaches

The Greedy Method. Outline and Reading. Change Money Problem. Greedy Algorithms. Applications of the Greedy Strategy. The Greedy Method Technique

CS 534: Computer Vision Model Fitting

Unsupervised Learning and Clustering

Efficient Load-Balanced IP Routing Scheme Based on Shortest Paths in Hose Model. Eiji Oki May 28, 2009 The University of Electro-Communications

APPLICATION OF MULTIVARIATE LOSS FUNCTION FOR ASSESSMENT OF THE QUALITY OF TECHNOLOGICAL PROCESS MANAGEMENT

Machine Learning: Algorithms and Applications

Unsupervised Learning

Image warping and stitching May 5 th, 2015

Anonymisation of Public Use Data Sets

High Dimensional Data Clustering

CS434a/541a: Pattern Recognition Prof. Olga Veksler. Lecture 15

Compiler Design. Spring Register Allocation. Sample Exercises and Solutions. Prof. Pedro C. Diniz

Shape Preserving Positive and Convex Data Visualization using Rational Bi-cubic Functions

THE THEORY OF REGIONALIZED VARIABLES

The Man-hour Estimation Models & Its Comparison of Interim Products Assembly for Shipbuilding

A Novel Accurate Algorithm to Ellipse Fitting for Iris Boundary Using Most Iris Edges. Mohammad Reza Mohammadi 1, Abolghasem Raie 2

TN348: Openlab Module - Colocalization

The official electronic file of this thesis or dissertation is maintained by the University Libraries on behalf of The Graduate School at Stony Brook

FITTING A CHI -square CURVE TO AN OBSERVI:D FREQUENCY DISTRIBUTION By w. T Federer BU-14-M Jan. 17, 1951

ECONOMICS 452* -- Stata 11 Tutorial 6. Stata 11 Tutorial 6. TOPIC: Representing Multi-Category Categorical Variables with Dummy Variable Regressors

Can We Beat the Prefix Filtering? An Adaptive Framework for Similarity Join and Search

Announcements. Supervised Learning

Machine Learning 9. week

Non-Split Restrained Dominating Set of an Interval Graph Using an Algorithm

Learning the Kernel Parameters in Kernel Minimum Distance Classifier

A Comparative Study for Outlier Detection Techniques in Data Mining

Multi-stable Perception. Necker Cube

Proposed Simplex Method For Fuzzy Linear Programming With Fuzziness at the Right Hand Side

Machine Learning. K-means Algorithm

Adaptive Transfer Learning

LU Decomposition Method Jamie Trahan, Autar Kaw, Kevin Martin University of South Florida United States of America

Problem Definitions and Evaluation Criteria for Computational Expensive Optimization

Decision Strategies for Rating Objects in Knowledge-Shared Research Networks

Econometrics 2. Panel Data Methods. Advanced Panel Data Methods I

Adjustment methods for differential measurement errors in multimode surveys

The Research of Support Vector Machine in Agricultural Data Classification

GSLM Operations Research II Fall 13/14

Type-2 Fuzzy Non-uniform Rational B-spline Model with Type-2 Fuzzy Data

WORKING PAPER SERIES 2014-EQM-03

Measuring Integration in the Network Structure: Some Suggestions on the Connectivity Index

Backpropagation: In Search of Performance Parameters

Structural Change in Demand for Cereals in Sri Lanka

Malaysian Journal of Applied Sciences

MAXIMUM LIKELIHOOD PARAMETER ESTIMATORS FOR THE TWO POPULATIONS GEV DISTRIBUTION

Air Transport Demand. Ta-Hui Yang Associate Professor Department of Logistics Management National Kaohsiung First Univ. of Sci. & Tech.

Transcription:

Pa. J. Statst. 5 Vol. 3(4), 353-36 A CLASS OF TRANSFORMED EFFICIENT RATIO ESTIMATORS OF FINITE POPULATION MEAN Sajjad Ahmad Khan, Hameed Al, Sadaf Manzoor and Alamgr Department of Statstcs, Islama College, Peshawar, Pastan Department of Statstcs, Unverst of Peshawar, Pastan Correspondng author Emal: sajjadhan@cp.edu.p ABSTRACT In ths paper we have proposed a class of transformed effcent estmators of fnte populaton mean b modfng Mohant and Sahoo (995) transformaton. The appromate bas and MSE of the proposed class of estmators have been found. Condtons under whch the proposed class of transformed estmators performs good, have been obtaned. Eamples are gven based on real lfe data to llustrate the results. KEYWORDS Aular Informaton, Transformaton, Effcenc, Mean Square Error.. INTRODUCTION In ths paper we have proposed an effcent estmator for estmatng the mean of the fnte populaton under smple random samplng wthout replacement samplng and stratfed random samplng schemes. Motvated b Subraman and Kunarpendan (), Bed (996), Mohant and Sahoo (995), Shabbr and Gupta (), we have made use of aular nformaton b ntroducng some transformaton. The Classcal estmator of the mean of the fnte populaton Y s. Varance of s V C, where n N (.) Cochran (94) ntroduced the tradtonal rato tpe estmator of populaton mean, as cr X wth the followng bas and MSE and cr (.) B Y C C (.) cr MSE Y C C C C. (.3) 5 Pastan Journal of Statstcs 353

354 A Class of Transformed Effcent Rato Estmators of Fnte Populaton Mean S S where C s the coeffcent of varaton of varable Y, C s the coeffcent Y X S of varaton of X, C s the coeffcent of covarance of X and Y and YX C s the coeffcent of correlaton between Y and X. CC The classcal regresson estmator gven b Hansen and Harwtz (943) s lr b X (.4) wth the followng mean square error lr MSE Y C (.5) Ths s a well-establshed fact that regresson estmator s effcent when the lnear relatonshp passes n the neghborhood of orgn. and An eponental rato tpe estmator due to Bhal and Tuteja (99) s gven b BT ep X X The bas and MSE due to 3C C B BT Y 8 BT s gven b MSE Y C C 4 C BT (.6) (.7) (.8) Mohant and Sahoo (995), ntroduces the followng transformaton n rato estmator of populaton mean and where t Z z t z U u M m m and u m s the mnmum and M M M m. s the mamum value of aular varable wth n the data.

Khan, Al, Manzoor and Alamgr 355 The bases and MSEs of t and t are gven b z z B t Y S S. (.9) u u B t Y S S. (.) z z MSE t Y C C C. (.) u u MSE t Y C C C. (.) where C C C C and c m M, c X X C C z,, u z c c c Shabbr and Gupta () proposed the followng transformed eponental rato tpe of estmator A a SG X ep A a (.3) where a NX and A X NX Wth the followng MSE MSE SG C C 8 N Y 4 N C where the optmum value of and s gven b (.4) C 8 N C Y C and X N N C.. SUGGESTED TRANSFORMATION Mohant and Sahoo (995) suggested the followng transformaton of the aular varable

356 A Class of Transformed Effcent Rato Estmators of Fnte Populaton Mean and or and (.) where m and M. Further we can wrte X X V and U. V f C U f Further we wrte V n and, c U n c where c and c. (3.) X X Obvousl, for the above transformaton one has to fnd out two features of aular varable, such as and for estmator of fnte populaton mean. One of the dsadvantage of the above transformaton s that, onl one constant are tang part n the reducton of MSE whle the other has no contrbuton at all. In order to remove the etra feature from estmator and to ncorporate onl those feature whch are tang contrbuton n the reducton of MSE, we precede as followng. We wrte (.) as c or Xc X where s constant or some functon of aular nformaton. The proposed transformaton s, or X c, and C E X, where 3. PROPOSED ESTIMATOR IN SIMPLE RANDOM SAMPLING X cx. Followng Bhal and Tuteja (99) and Shabbr and Gupta (), we suggest the followng class of estmators X pr X ep,,,3,4 (3.) X where X Xc and. X c, or E X Further c C, c, c3, c4.,,3,4. 3

Khan, Al, Manzoor and Alamgr 357 where & are sutable constant to be determned so that MSE s mnmum, where c s to be chosen, so that the transformed data results hgh gan n effcenc. We wll use the followng terms to fnd the Bas and MSE due to our proposed estmator e such that and Y e Y, E e E e E e e X e X or X c X,, C or E e e E e C E e C C C. or or Then we can wrte (3.) as follows e e pr Y e X e ep c c e 3e pr Y e X e 8 c c Terms wth power hgher than two can be gnored, we have e ee 3e pr Y Y e c c 8c We can defne the Bas due to our proposed estmator b pr pr Bas E Y e X e c 3C C C Bas pr Y X 8c c t For MSE, Squarng and tang epectaton of equaton (3.3), we have (3.) (3.3) (3.4) e ee 3e 3e E pr Y Y Y e X e c c 8c c (3.5) Snce pr pr MSE E Y

358 A Class of Transformed Effcent Rato Estmators of Fnte Populaton Mean C C 3C C MSE pr Y C c c 8 c c C C X C YX YX C c c (3.6) The optmum values of & can be obtaned b dfferentatng MSE of pr wth respect to the & b Dfferentatng (3.6) w.r.to and equatng to zero Y C 3C C c c 8c MSE pr C 3C c we get 3C YX C c Dfferentatng (3.6) w.r.to and equatng to zero, we get C C X C YX YX C c c MSE pr (3.7) we get (3.8) Solvng equaton (3.7) & (3.8) smultaneousl to get the optmum values of &. After smplfcaton we have C c 8 Y 3 C opt and opt opt C X c c C Substtutng these values n (3.6), we get MSE pr C Y C 8c C (3.9)

Khan, Al, Manzoor and Alamgr 359 4. THEORETICAL COMPARISON OF THE PROPOSED ESTIMATOR IN SRSWOR In ths secton we wll compare the MSE of our proposed estmator wth the estng estmator dscussed here above. ) MSE MSE If pr C 8c C C C ths s hold true for all choces of c. ) MSE MSE If pr cr C 8c C C C CC C 3) MSE MSE If pr lr C 8c C C C 4) MSE MSE If pr BT C 8 C c C C C 4 C 5) MSE MSE If pr SG

Parameters 36 A Class of Transformed Effcent Rato Estmators of Fnte Populaton Mean C C C 8c 8 C N 4 C C N C 8 C N c c 4 N C Condtons to 5 wll alwas hold true for all tpes of real data especall for some choces of c. 5. NUMERICAL COMPARISON OF THE PROPOSED ESTIMATOR FOR SRS In ths secton we wll mae an assessment of the effcenc of our proposed estmator under SRS usng data sets from real lfe eamples. It should be noted that f we put c N or X X NX then our proposed estmator wll reduces to Shabbr and Gupta () estmator. Populaton Source: US Agrcultural Statstcs (995) Y ; Speces group n 995 X ; Speces group n 995 Populaton 3 Source: Pastan MFA (4) Y ; Dstrct wse tomato producton (n tons), n Pastan (3) X ; Dstrct wse tomato producton () Populaton Source: Agrculture Statstcs () Y ; The State wse producton of major spces n thousand metrc tons of Inda. (,) X ; The State wse producton of major spces n thousand metrc tons of Inda.(,) Populaton 4 Source: Murth (967) page 8 N 69 97 9 8 N 7 5 3 Y 454.9 335.6 84.5 5.864 X 455.6 35.8 38.476.664 C.483.37893.753.757 C.3756.3.856.354.9.987.4453.953

Khan, Al, Manzoor and Alamgr 36 Estmators Table Mean Square Error of the Proposed Estmator for c C, c, c3, c4 3 and the Estng Estmators Populaton Populaton Populaton 3 Populaton 4 7995.485 954.736 54789.37 67.86 cr 38874.563 38.8 458.7 96.84 lr 3779. 5.63 3963.5 887.57 t 3673.3 6.77 5453.9 9339.943 t 36544.483 733.54 589.63 9473.9 BT 3836.836 78.85 7768.63 9574.837 SG 384.536 98.8 39463.855 8766.5 Proposed Class of Estmators pr 3876.86 96.99 3936.7 876.599 pr 7493.55 657.4 567.6 867.6 pr3 364.3 863.47 3379. 87.855 pr4 3484.3 956.834 3887.953 8753.95 CONCLUSION From the above analss t s clear that our proposed estmators for varous value of transformer c C, c, c3, c4 are superor to all other estmators 3 consdered n ths paper. Hence the transformaton results consderable reducton n MSE, as obvous from the above table and hgh gan n effcenc. Smlar strateg can be used for further optmzaton of estng estmators or for the development of new estmators.

36 A Class of Transformed Effcent Rato Estmators of Fnte Populaton Mean REFERENCES. Bahl, S. and Tuteja, R.K. (99). Rato and product tpe eponental estmator. Journal of Informaton and Optmzaton Scences,, 59-63.. Cochran, W.G. (94). The estmaton of the elds of the cereal eperments b samplng for the rato of gran to total produce. The Journal of Agrcultural Scence, 3(), 6-75 3. Gupta, G. and Shabbr, J. (8). On mprovement n estmatng the populaton mean n smple random samplng. Journal of Appled Statstcs, 35(5), 559-566. 4. Hansen M.H. and Hurwtz W.N. (943). On the theor of samplng from fnte populatons. Annal of the Mathematcs and Statstcs, 4, 333-6. 5. Government of Pastan (4). Crops Area Producton. Mnstr of Food and Agrculture, Islamabad, Pastan. 6. Mohant, S. and Sahoo, J. (995). A note on mprovng the rato method of estmaton through lnear transformaton usng certan nown populaton parameters. Sanha Seres B 57(), 93-. 7. Shabbr, J. and Gupta, S. (). On estmatng fnte populaton mean n smple and stratfed random samplng. Communcaton n Statstcs Theor and Method, 4, 99-. 8. Sngh, H.P., Talor, R. and Kaaran, M.S. (4). An estmator of Populaton mean usng power transformaton. J.I.S.A.S., 58(), 3-3. 9. Srvastava, S.K. and Jhajj, H.S. (983). A class of estmators of the populaton mean usng mult-aular nformaton. Calc. Statst. Assoc. Bull., 3, 47-56.