ERROR RATES STABILITY OF THE HOMOSCEDASTIC DISCRIMINANT FUNCTION
|
|
- Dominic Farmer
- 5 years ago
- Views:
Transcription
1 ISSN UNAAB 00 Journal of Natural Scences, Engneerng and Technology ERROR RATES STABILITY OF THE HOMOSCEDASTIC DISCRIMINANT FUNCTION A. ADEBANJI, S. NOKOE AND O. IYANIWURA 3 *Department of Mathematcs, Kwame Nkrumah Unversty of Scence and Technology, Kumas, Ghana. Department of Appled Mathematcs and Computer Scence, Unversty for Development Studes, Navrongo, Ghana. E-mal: nokoe_bomaths@yahoo.co.uk. 3Department of Statstcs, Unversty of Ibadan, Ibadan, Ngera. Emal: jo_yanwura@yahoo.com *Correspondng author: tnuadebanj@yahoo.com ABSTRACT In ths study the stablty of the observed error rates of the homoscedastc dscrmnant functon relatve to the number of parameters n the model usng smulated data from multvarate normal populatons was nvestgated. Three models were consdered, the four, sx and eght varables models, each havng four values of the separator functon ( ). Equal and unequal pror probabltes were consdered for the dfferent number of parameter and separator functon confguratons. The asymptotc performance of the models was consdered usng the cross valdaton error rate estmaton procedure. Results ndcate the sx varable models as beng more stable (dsplayng less varablty n the estmated error rates) than the other models under consderaton. Less deteroraton was observed for the sx-varable model specfcaton as was evdent n the other models and ths was more pronounced for smaller values of. Keywords: Homoscedastc, Dscrmnant functon, pror probabltes, asymptotc. 000 Mathematcs Subject Classfcaton: 6H30, 65C0 INTRODUCTION Gven two or more groups of populatons and a set of assocated varables, one wants to locate a subset of the varables and assocated functons of the subset that leads to maxmum separaton among the centrods of the groups. The exploratory multvarate procedure of determnng varables and a reduced set of functons called dscrmnants or dscrmnant functons s called dscrmnant analyss. Dscrmnants that are lnear functons of the varables are called J. Nat. Sc. Engr. Tech. 00, 9():6-3 6 Lnear Dscrmnant Functons (LDF) or homoscedastc dscrmnant functon (derved from the assumpton of homoscedastcty of the varance-covarance matrx). In ths study, estmaton of the stablty (determned as a measure of wthn sample varablty) n the error rates of the dfferent models under consderaton s of nterest. Ths s an overall ndcator of the performance of the dscrmnant functon.
2 A. ADEBANJI, S. NOKOE AND O. IYANIWURA 3 Observatons are drawn from two multvarate normal populatons (groups) The Model MATERIALS AND METHODS R (,, R In the classcal homoscedastc model, the ). The mean vectors of lkelhood rato classfcaton functon for an p R (0,...,0) and are gven as observed vector x s derved as p f (,0,...0) ( x) exp x ( ) ( ) ( ) and respectvely and f( x) both matrces have dentty varance covar- pxp ance structures and. The performance of the functon s not dependent on the locaton of n the mean vector. Under a homoscedastc normal model for the group condtonal dstrbutons of the feature vector X on an entty, t s assumed that X () The th group-condtonal densty f s gven as p ( ) exp ( X ) ( X ) () where MNV (, ) (, ) f (, ) ( ;, ) conssts of the elements of {( ) ( )} / (3) (4) We assgn a new p-varable observaton x to R f P( P ) and the dstnct elements of. The square root of the Mahalanobs dstance s predetermned as,3,5 and 7 usng ( x ( )) ( ) k (otherwse assgn to ) (5) k log( C( ))/( C( )). (, ) s the pror probablty of an observed vector comng from populaton and C( j) C s the cost ncurred when an observaton from R R j s classfed as havng R j, j, come from ( ),. Thus C( ) C( j j) 0. In ths study, we assume equal cost of msclassfcaton and k reduces to the log of the rato of the pror probabltes. It may be remarked that a Bayes rule may result n a large probablty of msclassfcaton and several attempts have been made to overcome ths dffculty. When pror probabltes are known, the Bayes rule s optmum n the sense that t mnmses average expected cost (Gr - 004). For an observed vector x, f the plug-n rule J. Nat. Sc. Engr. Tech. 00, 9():6-3 7
3 s gven as approxmaton to the Bayes rule F s a good estmate of F. r (.) 0 s the classfcaton rule obtaned when sample X, X, estmates of and S of are plugged nto (5). The probablty that a randomly chosen en- R R j tty from s allocated to on the ba- r0 ( x; F) ss of, has an error rate specfc to the th group as And the overall error rate s, j, ( ) (6) (7) where s as earler defned. In usng error rates to measure the performance of a sample-based allocaton rule, t s the condtonal error rates that are of prmary concern once the rule has been formed from the tranng data (Johnson and Wchern-998). The overall error rate for equal prors, s gven by where and r0 ( x; F), ths provdes a good g j eo( F) eo ( F) g eo( F) eo ( F) j s as earler defned. r0 ( x; F) ef ( ) eof ( ) n { ( )/4}{ p 4( p) O } eo( F) ( ) ERROR RATES STABILITY OF THE HOMOSCEDASTIC... If the dmenson p s small, the sample szes n, n occurrng n practce wll probably be large enough to apply ths result. However, f p s not small, extremely large sample szes f wll probably be requred to make ths results relevant (Gr 004). (8) (9) J. Nat. Sc. Engr. Tech. 00, 9():6-3 8 The leave-one-out (cross valdaton) error rate estmaton procedure of Lachenbruch and Mckey (968) s used as the performance evaluator for the models under consderaton. The smulaton study From (7), we can determne approxmately how large n must be for a specfed and p n order for the uncondtonal error rate not to exceed too far the best obtanable as gven by the optmal error rate. Indeed, f n s small, then for p>, the error rate s not far short of ½, whch s the error rate for a randomzed rule that gnores the feature vector and makes a choce of groups accordng to the toss of a con (McLachlan 99). The sample szes have to be specfed, here we set the values of n at 5, 50, 75, 00, 00, 300, 400, 500, 600, 700, 800, 900, 000, 00, 00,,300, 400, 500, 000, 500, 3000 respectvely. The sze of n s decded by the predetermned sample sze ratos n :n. The ratos are : and : thus determnng the pror probabltes to be consdered. Numercal values were assgned to, the group centrod separator factor and Mahalanobs dstance determnant. These are, 3, 5 and 7 respectvely. The number of varables n the mult-normal dstrbutons to be generated s predetermned as 4, 6 and 8 followng Murray (977) that consdered the selecton of varables n
4 A. ADEBANJI, S. NOKOE AND O. IYANIWURA 3 Dscrmnant Analyss. By makng 00 replcates we am at attanng an accurate estmate of the msclassfcaton rate by reducng the between sample varablty. Hence 00 samples of random varates of the requred specfcaton are generated, and the analyss s carred out on the 00 samples. Thus resultng n,00 samples for each sample rato consderaton and four values of. Ths gves a total of 400x4 (6,800) samples of varous szes. The error rate estmates are then averaged over the number of replcates. The SAS V8 (996) package was used for generatng the matrces from a N (0,) dstrbuton for the predetermned models. Independent seres of normal devates of requred length are drawn and then transformed (standardzed) to have unt varance and zero covarance. Smlar smulaton experments had been constructed by Marks and Dunn (976) and He and Fung (000). These dd not consder varable effects and number of replcates and sample szes not ths many. Results of smulaton The total probablty of msclassfcaton, standard devaton and coeffcent of varaton are presented as decmals. The results of the smulaton are presented n a seres of fgures The frst set (. to.6) present the results for the four varable model wth equal pror probablty scheme presented n fgs. to.3 for dfferent values of. Fgures. to.3 are the total error rates, the standard devaton (SD) and coeffcent of varaton (CV) respectvely. Fgures.4 to.6 present the same results for the unequal pror probablty (n : n = J. Nat. Sc. Engr. Tech. 00, 9():6-3 9 :). The second seres of fgures are for the sx (6) varable model and are presented n the same format (that s equal and unequal pror probabltes) as fgures. to.3 and.4 to.6 respectvely. The last seres of fgures are for the eght (8) varable model and are presented n the same sequence as fgures 3. to 3.6 respectvely. In the equal pror scenaro, for the four varable model, error rates are less stable for the smaller sample szes than for the larger sample szes as evdenced n the coeffcents of varaton recorded. Stablty n the error rates deterorates remarkably asymptotcally as ncreased from to 7 and worsens when =7 when the samples are so far apart that t does not justfy the use of a classfcaton functon. Changng the number of varables n the model to sx resulted n some observable dfference n the performance of the LDF. A reducton n error rate for the respectve values was recorded. When =, the values recorded for the standard devaton were consstently lower than those for the mean total error rate. The reducton of the CV s rapd. The hghest value of 35.8% error rate was observed for sample sze 50 (rato :) and the smallest recorded was 8.59% for sample sze 6000 (rato :4). Reducton n error rates was more rapd for rato : than for :. When compared wth = (p=4 varables), the mnmum and maxmum recorded values are qute close. The four varable model (p=4) had values and 8.6% for maxmum and mnmum msclassfcatons respectvely.
5 ERROR RATES STABILITY OF THE HOMOSCEDASTIC... J. Nat. Sc. Engr. Tech. 00, 9():6-3 0
6 A. ADEBANJI, S. NOKOE AND O. IYANIWURA 3 J. Nat. Sc. Engr. Tech. 00, 9():6-3
7 When =3, the relatonshp between the mean error rates and CV s reversed (CV records hgher values). The maxmum error rate of 8.6% was recorded for sample sze 50 (rato :) and the CV results recorded a maxmum of 0.9% for sample sze 800 (rato :).The recorded error rates are however much lower than was earler recorded for lower values of (especally when vewed n comparson wth the four varable lnear models). When =7, the values of CV are much hgher than earler recorded as a result of the hgh reducton n mean error rate; although lttle mprovement was observed across sample szes, the functon recorded near zero msclassfcaton rates. When the number of varables s ncreased to eght (p=8), the observed pattern s smlar to the pattern observed for P=6 wth the mean error rates recordng hgher values than the CV for lower values of.the maxmum value of mean error rate observed s 36.67% for sample sze 50 (rato :) and reducton n CV s not as rapd as earler recorded and the reducton n mean error rate s much more gradual than earler observed. At =3, the values of CV are larger than the mean error rate except at the tal end of the curves. A maxmum error rate of 8.% s recorded for sample sze 50 (rato :) However, the asymptotc reducton n CV s no longer observed for =5. Here, an ntal reducton s observed after whch the values stablzes. The mean error rates are close to zero. ERROR RATES STABILITY OF THE HOMOSCEDASTIC... Improvement n the performance of the functon s more pronounced for the eght varable model than the four varable case. Maxmum error rate of 0.56% was observed for sample sze 00 (rato :3) and mnmum value of 0.0% for sample sze 50 (rato :) was observed for =6 for =7, the values were 0.044% for sample sze 50 (rato :4) and mnmum value of 0.04% for sample sze 50 (rato :). DISCUSSION There appears a turnng pont n the reducton n the mean error (or msclassfcaton) rates as well as mprovement n ther stablty beyond p = 6. Ths s suggestng that not more than sx varables should be ncluded n dscrmnant analyss even when the sample sze s as large as A reasonable corollary to ths fndng s the plausble concluson that the smaller your sample szes the fewer should be the number of varables. Ths declne n stablty of observed error rates s observable for hgher values of wth =7 recordng much hgher nstablty than =5. Also, ncreasng the sample sze wll cease to result n an mprovement n the performance of the functon once a thresh-hold s reached, beyond whch, there s nothng to be ganed by any further ncrease even to values that gve sample estmates that would equal the populaton parameters. J. Nat. Sc. Engr. Tech. 00, 9():6-3
8 A. ADEBANJI, S. NOKOE AND O. IYANIWURA 3 CONCLUSION These nconsstences n the behavour of average error rates are the observed deteroraton n the stablty of the error rates as p changes from 6 to 8 suggest that there s a turnng pont between p = 6 and p = 8 n the relatonshp between the number of varables and the magntude of error rates and ther varaton. Ths s most plausble at p = 7. Ths pattern was observed for the dfferent values of that we consdered. Joossens, K Robust Dscrmnant Analyss; Ph.D. Thess of Katholeke Unverstet, Leuven. Lachenbruch, P.A., Mckey, M.R Estmaton of error rates n dscrmnant analyss. Technometrcs, 0: -. Marks, S., Dunn, O.J Dscrmnant Functons when covarance matrces are unequal; Journal of the Amercan Statstc Assocaton, 69: ACKNOWLEDGEMENT Ths study was supported by the Thrd World Organzaton for Women n Scences (TWOWS) fellowshp. REFERENCES Adebanj, A.O., Nokoe, S Evaluatng the Quadratc Classfer; Proceedngs of the Thrd Internatonal Workshop on contemporary problems n Mathematcal Physcs, P Gr N.C Multvarate Statstcal Analyss. DEKKER Seres 004 P He, X.M., Fung, W.K Hgh breakdown estmaton for multple populatons wth applcatons to dscrmnant analyss; Journal of Multvarate Analyss, 7: 5-6. McFarlan, R.H., Rchards, D. 00. Exact Msclassfcaton Problems for Plug-n Normal Dscrmnant Functons. Equal Mean Case. Journal of Multvarate Analyss, 77: - 53 McLachlan, G. 99 Dscrmnant Analyss and Statstcal Pattern Recognton. Wley Seres n Probablty and Mathematcal Statstcs. P Murray, G.D A Cautonary Note on Selecton of Varables n Dscrmnant Analyss. Appled Statstcs, 6(3): Okomato, M An Asymptotc Expanson for the Dstrbuton of the Lnear Dscrmnant Functon. Annals of Math Stat., 34: Johnson, R.A., Wchern, D.W Appled Multvarate Statstcal Analyss, 4 th Edton. Prentce Hall Inc. USA. P (Manuscrpt receved: 6th January, 00; accepted: 4th June, 00). J. Nat. Sc. Engr. Tech. 00, 9():6-3 3
P R. Lecture 4. Theory and Applications of Pattern Recognition. Dept. of Electrical and Computer Engineering /
Theory and Applcatons of Pattern Recognton 003, Rob Polkar, Rowan Unversty, Glassboro, NJ Lecture 4 Bayes Classfcaton Rule Dept. of Electrcal and Computer Engneerng 0909.40.0 / 0909.504.04 Theory & Applcatons
More informationUNIVERSITY OF TORONTO Faculty of Arts and Science. December 2005 Examinations STA437H1F/STA1005HF. Duration - 3 hours
UNIVERSITY OF TORONTO Faculty of Arts and Scence December 005 Examnatons STA47HF/STA005HF Duraton - hours AIDS ALLOWED: (to be suppled by the student) Non-programmable calculator One handwrtten 8.5'' x
More informationSimulated Power of the Discrete Cramér-von Mises Goodness-of-Fit Tests
Smulated of the Cramér-von Mses Goodness-of-Ft Tests Steele, M., Chaselng, J. and 3 Hurst, C. School of Mathematcal and Physcal Scences, James Cook Unversty, Australan School of Envronmental Studes, Grffth
More informationThe Gaussian classifier. Nuno Vasconcelos ECE Department, UCSD
he Gaussan classfer Nuno Vasconcelos ECE Department, UCSD Bayesan decson theory recall that we have state of the world X observatons g decson functon L[g,y] loss of predctng y wth g Bayes decson rule s
More informationMIMA Group. Chapter 2 Bayesian Decision Theory. School of Computer Science and Technology, Shandong University. Xin-Shun SDU
Group M D L M Chapter Bayesan Decson heory Xn-Shun Xu @ SDU School of Computer Scence and echnology, Shandong Unversty Bayesan Decson heory Bayesan decson theory s a statstcal approach to data mnng/pattern
More informationCOMPARISON OF SOME RELIABILITY CHARACTERISTICS BETWEEN REDUNDANT SYSTEMS REQUIRING SUPPORTING UNITS FOR THEIR OPERATIONS
Avalable onlne at http://sck.org J. Math. Comput. Sc. 3 (3), No., 6-3 ISSN: 97-537 COMPARISON OF SOME RELIABILITY CHARACTERISTICS BETWEEN REDUNDANT SYSTEMS REQUIRING SUPPORTING UNITS FOR THEIR OPERATIONS
More informationHeteroscedastic Variance Covariance Matrices for. Unbiased Two Groups Linear Classification Methods
Appled Mathematcal Scences, Vol. 7, 03, no. 38, 6855-6865 HIKARI Ltd, www.m-hkar.com http://dx.do.org/0.988/ams.03.39486 Heteroscedastc Varance Covarance Matrces for Unbased Two Groups Lnear Classfcaton
More informationLecture 12: Classification
Lecture : Classfcaton g Dscrmnant functons g The optmal Bayes classfer g Quadratc classfers g Eucldean and Mahalanobs metrcs g K Nearest Neghbor Classfers Intellgent Sensor Systems Rcardo Guterrez-Osuna
More informationStatistics for Managers Using Microsoft Excel/SPSS Chapter 13 The Simple Linear Regression Model and Correlation
Statstcs for Managers Usng Mcrosoft Excel/SPSS Chapter 13 The Smple Lnear Regresson Model and Correlaton 1999 Prentce-Hall, Inc. Chap. 13-1 Chapter Topcs Types of Regresson Models Determnng the Smple Lnear
More informationComparison of Regression Lines
STATGRAPHICS Rev. 9/13/2013 Comparson of Regresson Lnes Summary... 1 Data Input... 3 Analyss Summary... 4 Plot of Ftted Model... 6 Condtonal Sums of Squares... 6 Analyss Optons... 7 Forecasts... 8 Confdence
More informationLINEAR REGRESSION ANALYSIS. MODULE IX Lecture Multicollinearity
LINEAR REGRESSION ANALYSIS MODULE IX Lecture - 30 Multcollnearty Dr. Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur 2 Remedes for multcollnearty Varous technques have
More informationRegularized Discriminant Analysis for Face Recognition
1 Regularzed Dscrmnant Analyss for Face Recognton Itz Pma, Mayer Aladem Department of Electrcal and Computer Engneerng, Ben-Guron Unversty of the Negev P.O.Box 653, Beer-Sheva, 845, Israel. Abstract Ths
More informationStatistical Evaluation of WATFLOOD
tatstcal Evaluaton of WATFLD By: Angela MacLean, Dept. of Cvl & Envronmental Engneerng, Unversty of Waterloo, n. ctober, 005 The statstcs program assocated wth WATFLD uses spl.csv fle that s produced wth
More informationComputation of Higher Order Moments from Two Multinomial Overdispersion Likelihood Models
Computaton of Hgher Order Moments from Two Multnomal Overdsperson Lkelhood Models BY J. T. NEWCOMER, N. K. NEERCHAL Department of Mathematcs and Statstcs, Unversty of Maryland, Baltmore County, Baltmore,
More informationSee Book Chapter 11 2 nd Edition (Chapter 10 1 st Edition)
Count Data Models See Book Chapter 11 2 nd Edton (Chapter 10 1 st Edton) Count data consst of non-negatve nteger values Examples: number of drver route changes per week, the number of trp departure changes
More information/ n ) are compared. The logic is: if the two
STAT C141, Sprng 2005 Lecture 13 Two sample tests One sample tests: examples of goodness of ft tests, where we are testng whether our data supports predctons. Two sample tests: called as tests of ndependence
More informationx = , so that calculated
Stat 4, secton Sngle Factor ANOVA notes by Tm Plachowsk n chapter 8 we conducted hypothess tests n whch we compared a sngle sample s mean or proporton to some hypotheszed value Chapter 9 expanded ths to
More informationA Bayes Algorithm for the Multitask Pattern Recognition Problem Direct Approach
A Bayes Algorthm for the Multtask Pattern Recognton Problem Drect Approach Edward Puchala Wroclaw Unversty of Technology, Char of Systems and Computer etworks, Wybrzeze Wyspanskego 7, 50-370 Wroclaw, Poland
More informationLINEAR REGRESSION ANALYSIS. MODULE IX Lecture Multicollinearity
LINEAR REGRESSION ANALYSIS MODULE IX Lecture - 31 Multcollnearty Dr. Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur 6. Rdge regresson The OLSE s the best lnear unbased
More informationPsychology 282 Lecture #24 Outline Regression Diagnostics: Outliers
Psychology 282 Lecture #24 Outlne Regresson Dagnostcs: Outlers In an earler lecture we studed the statstcal assumptons underlyng the regresson model, ncludng the followng ponts: Formal statement of assumptons.
More informationA Robust Method for Calculating the Correlation Coefficient
A Robust Method for Calculatng the Correlaton Coeffcent E.B. Nven and C. V. Deutsch Relatonshps between prmary and secondary data are frequently quantfed usng the correlaton coeffcent; however, the tradtonal
More informationStatistics II Final Exam 26/6/18
Statstcs II Fnal Exam 26/6/18 Academc Year 2017/18 Solutons Exam duraton: 2 h 30 mn 1. (3 ponts) A town hall s conductng a study to determne the amount of leftover food produced by the restaurants n the
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Experment-I MODULE VII LECTURE - 3 ANALYSIS OF COVARIANCE Dr Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur Any scentfc experment s performed
More informationNegative Binomial Regression
STATGRAPHICS Rev. 9/16/2013 Negatve Bnomal Regresson Summary... 1 Data Input... 3 Statstcal Model... 3 Analyss Summary... 4 Analyss Optons... 7 Plot of Ftted Model... 8 Observed Versus Predcted... 10 Predctons...
More information4 Analysis of Variance (ANOVA) 5 ANOVA. 5.1 Introduction. 5.2 Fixed Effects ANOVA
4 Analyss of Varance (ANOVA) 5 ANOVA 51 Introducton ANOVA ANOVA s a way to estmate and test the means of multple populatons We wll start wth one-way ANOVA If the populatons ncluded n the study are selected
More informationChapter 12 Analysis of Covariance
Chapter Analyss of Covarance Any scentfc experment s performed to know somethng that s unknown about a group of treatments and to test certan hypothess about the correspondng treatment effect When varablty
More informationFirst Year Examination Department of Statistics, University of Florida
Frst Year Examnaton Department of Statstcs, Unversty of Florda May 7, 010, 8:00 am - 1:00 noon Instructons: 1. You have four hours to answer questons n ths examnaton.. You must show your work to receve
More information2E Pattern Recognition Solutions to Introduction to Pattern Recognition, Chapter 2: Bayesian pattern classification
E395 - Pattern Recognton Solutons to Introducton to Pattern Recognton, Chapter : Bayesan pattern classfcaton Preface Ths document s a soluton manual for selected exercses from Introducton to Pattern Recognton
More information2016 Wiley. Study Session 2: Ethical and Professional Standards Application
6 Wley Study Sesson : Ethcal and Professonal Standards Applcaton LESSON : CORRECTION ANALYSIS Readng 9: Correlaton and Regresson LOS 9a: Calculate and nterpret a sample covarance and a sample correlaton
More informationBOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS. M. Krishna Reddy, B. Naveen Kumar and Y. Ramu
BOOTSTRAP METHOD FOR TESTING OF EQUALITY OF SEVERAL MEANS M. Krshna Reddy, B. Naveen Kumar and Y. Ramu Department of Statstcs, Osmana Unversty, Hyderabad -500 007, Inda. nanbyrozu@gmal.com, ramu0@gmal.com
More informationComparison of the Population Variance Estimators. of 2-Parameter Exponential Distribution Based on. Multiple Criteria Decision Making Method
Appled Mathematcal Scences, Vol. 7, 0, no. 47, 07-0 HIARI Ltd, www.m-hkar.com Comparson of the Populaton Varance Estmators of -Parameter Exponental Dstrbuton Based on Multple Crtera Decson Makng Method
More informationANSWERS. Problem 1. and the moment generating function (mgf) by. defined for any real t. Use this to show that E( U) var( U)
Econ 413 Exam 13 H ANSWERS Settet er nndelt 9 deloppgaver, A,B,C, som alle anbefales å telle lkt for å gøre det ltt lettere å stå. Svar er gtt . Unfortunately, there s a prntng error n the hnt of
More informationGlobal Sensitivity. Tuesday 20 th February, 2018
Global Senstvty Tuesday 2 th February, 28 ) Local Senstvty Most senstvty analyses [] are based on local estmates of senstvty, typcally by expandng the response n a Taylor seres about some specfc values
More informationLinear Regression Analysis: Terminology and Notation
ECON 35* -- Secton : Basc Concepts of Regresson Analyss (Page ) Lnear Regresson Analyss: Termnology and Notaton Consder the generc verson of the smple (two-varable) lnear regresson model. It s represented
More informationTurbulence classification of load data by the frequency and severity of wind gusts. Oscar Moñux, DEWI GmbH Kevin Bleibler, DEWI GmbH
Turbulence classfcaton of load data by the frequency and severty of wnd gusts Introducton Oscar Moñux, DEWI GmbH Kevn Blebler, DEWI GmbH Durng the wnd turbne developng process, one of the most mportant
More informationComposite Hypotheses testing
Composte ypotheses testng In many hypothess testng problems there are many possble dstrbutons that can occur under each of the hypotheses. The output of the source s a set of parameters (ponts n a parameter
More informationNon-Mixture Cure Model for Interval Censored Data: Simulation Study ABSTRACT
Malaysan Journal of Mathematcal Scences 8(S): 37-44 (2014) Specal Issue: Internatonal Conference on Mathematcal Scences and Statstcs 2013 (ICMSS2013) MALAYSIAN JOURNAL OF MATHEMATICAL SCIENCES Journal
More informationUncertainty as the Overlap of Alternate Conditional Distributions
Uncertanty as the Overlap of Alternate Condtonal Dstrbutons Olena Babak and Clayton V. Deutsch Centre for Computatonal Geostatstcs Department of Cvl & Envronmental Engneerng Unversty of Alberta An mportant
More informationLOW BIAS INTEGRATED PATH ESTIMATORS. James M. Calvin
Proceedngs of the 007 Wnter Smulaton Conference S G Henderson, B Bller, M-H Hseh, J Shortle, J D Tew, and R R Barton, eds LOW BIAS INTEGRATED PATH ESTIMATORS James M Calvn Department of Computer Scence
More informationChapter 13: Multiple Regression
Chapter 13: Multple Regresson 13.1 Developng the multple-regresson Model The general model can be descrbed as: It smplfes for two ndependent varables: The sample ft parameter b 0, b 1, and b are used to
More informationDepartment of Quantitative Methods & Information Systems. Time Series and Their Components QMIS 320. Chapter 6
Department of Quanttatve Methods & Informaton Systems Tme Seres and Ther Components QMIS 30 Chapter 6 Fall 00 Dr. Mohammad Zanal These sldes were modfed from ther orgnal source for educatonal purpose only.
More informationDr. Shalabh Department of Mathematics and Statistics Indian Institute of Technology Kanpur
Analyss of Varance and Desgn of Experment-I MODULE VIII LECTURE - 34 ANALYSIS OF VARIANCE IN RANDOM-EFFECTS MODEL AND MIXED-EFFECTS EFFECTS MODEL Dr Shalabh Department of Mathematcs and Statstcs Indan
More informationEcon107 Applied Econometrics Topic 3: Classical Model (Studenmund, Chapter 4)
I. Classcal Assumptons Econ7 Appled Econometrcs Topc 3: Classcal Model (Studenmund, Chapter 4) We have defned OLS and studed some algebrac propertes of OLS. In ths topc we wll study statstcal propertes
More informationCluster Validation Determining Number of Clusters. Umut ORHAN, PhD.
Cluster Analyss Cluster Valdaton Determnng Number of Clusters 1 Cluster Valdaton The procedure of evaluatng the results of a clusterng algorthm s known under the term cluster valdty. How do we evaluate
More informationThe Multiple Classical Linear Regression Model (CLRM): Specification and Assumptions. 1. Introduction
ECONOMICS 5* -- NOTE (Summary) ECON 5* -- NOTE The Multple Classcal Lnear Regresson Model (CLRM): Specfcaton and Assumptons. Introducton CLRM stands for the Classcal Lnear Regresson Model. The CLRM s also
More informationWhy Bayesian? 3. Bayes and Normal Models. State of nature: class. Decision rule. Rev. Thomas Bayes ( ) Bayes Theorem (yes, the famous one)
Why Bayesan? 3. Bayes and Normal Models Alex M. Martnez alex@ece.osu.edu Handouts Handoutsfor forece ECE874 874Sp Sp007 If all our research (n PR was to dsappear and you could only save one theory, whch
More informationMLE and Bayesian Estimation. Jie Tang Department of Computer Science & Technology Tsinghua University 2012
MLE and Bayesan Estmaton Je Tang Department of Computer Scence & Technology Tsnghua Unversty 01 1 Lnear Regresson? As the frst step, we need to decde how we re gong to represent the functon f. One example:
More informationA Note on Test of Homogeneity Against Umbrella Scale Alternative Based on U-Statistics
J Stat Appl Pro No 3 93- () 93 NSP Journal of Statstcs Applcatons & Probablty --- An Internatonal Journal @ NSP Natural Scences Publshng Cor A Note on Test of Homogenety Aganst Umbrella Scale Alternatve
More informationDETERMINATION OF UNCERTAINTY ASSOCIATED WITH QUANTIZATION ERRORS USING THE BAYESIAN APPROACH
Proceedngs, XVII IMEKO World Congress, June 7, 3, Dubrovn, Croata Proceedngs, XVII IMEKO World Congress, June 7, 3, Dubrovn, Croata TC XVII IMEKO World Congress Metrology n the 3rd Mllennum June 7, 3,
More information3.1 Expectation of Functions of Several Random Variables. )' be a k-dimensional discrete or continuous random vector, with joint PMF p (, E X E X1 E X
Statstcs 1: Probablty Theory II 37 3 EPECTATION OF SEVERAL RANDOM VARIABLES As n Probablty Theory I, the nterest n most stuatons les not on the actual dstrbuton of a random vector, but rather on a number
More informationMultivariate Ratio Estimator of the Population Total under Stratified Random Sampling
Open Journal of Statstcs, 0,, 300-304 ttp://dx.do.org/0.436/ojs.0.3036 Publsed Onlne July 0 (ttp://www.scrp.org/journal/ojs) Multvarate Rato Estmator of te Populaton Total under Stratfed Random Samplng
More informationStatistics for Business and Economics
Statstcs for Busness and Economcs Chapter 11 Smple Regresson Copyrght 010 Pearson Educaton, Inc. Publshng as Prentce Hall Ch. 11-1 11.1 Overvew of Lnear Models n An equaton can be ft to show the best lnear
More informationStatistics for Economics & Business
Statstcs for Economcs & Busness Smple Lnear Regresson Learnng Objectves In ths chapter, you learn: How to use regresson analyss to predct the value of a dependent varable based on an ndependent varable
More information7.1. Single classification analysis of variance (ANOVA) Why not use multiple 2-sample 2. When to use ANOVA
Sngle classfcaton analyss of varance (ANOVA) When to use ANOVA ANOVA models and parttonng sums of squares ANOVA: hypothess testng ANOVA: assumptons A non-parametrc alternatve: Kruskal-Walls ANOVA Power
More informationCokriging Partial Grades - Application to Block Modeling of Copper Deposits
Cokrgng Partal Grades - Applcaton to Block Modelng of Copper Deposts Serge Séguret 1, Julo Benscell 2 and Pablo Carrasco 2 Abstract Ths work concerns mneral deposts made of geologcal bodes such as breccas
More informationASYMPTOTIC PROPERTIES OF ESTIMATES FOR THE PARAMETERS IN THE LOGISTIC REGRESSION MODEL
Asymptotc Asan-Afrcan Propertes Journal of Estmates Economcs for and the Econometrcs, Parameters n Vol. the Logstc, No., Regresson 20: 65-74 Model 65 ASYMPTOTIC PROPERTIES OF ESTIMATES FOR THE PARAMETERS
More informationChat eld, C. and A.J.Collins, Introduction to multivariate analysis. Chapman & Hall, 1980
MT07: Multvarate Statstcal Methods Mke Tso: emal mke.tso@manchester.ac.uk Webpage for notes: http://www.maths.manchester.ac.uk/~mkt/new_teachng.htm. Introducton to multvarate data. Books Chat eld, C. and
More informationBIO Lab 2: TWO-LEVEL NORMAL MODELS with school children popularity data
Lab : TWO-LEVEL NORMAL MODELS wth school chldren popularty data Purpose: Introduce basc two-level models for normally dstrbuted responses usng STATA. In partcular, we dscuss Random ntercept models wthout
More informationKernel Methods and SVMs Extension
Kernel Methods and SVMs Extenson The purpose of ths document s to revew materal covered n Machne Learnng 1 Supervsed Learnng regardng support vector machnes (SVMs). Ths document also provdes a general
More informationStatistical pattern recognition
Statstcal pattern recognton Bayes theorem Problem: decdng f a patent has a partcular condton based on a partcular test However, the test s mperfect Someone wth the condton may go undetected (false negatve
More informationRELIABILITY ASSESSMENT
CHAPTER Rsk Analyss n Engneerng and Economcs RELIABILITY ASSESSMENT A. J. Clark School of Engneerng Department of Cvl and Envronmental Engneerng 4a CHAPMAN HALL/CRC Rsk Analyss for Engneerng Department
More informationESTIMATES OF VARIANCE COMPONENTS IN RANDOM EFFECTS META-ANALYSIS: SENSITIVITY TO VIOLATIONS OF NORMALITY AND VARIANCE HOMOGENEITY
ESTIMATES OF VARIANCE COMPONENTS IN RANDOM EFFECTS META-ANALYSIS: SENSITIVITY TO VIOLATIONS OF NORMALITY AND VARIANCE HOMOGENEITY Jeffrey D. Kromrey and Krstne Y. Hogarty Department of Educatonal Measurement
More informationChapter 15 Student Lecture Notes 15-1
Chapter 15 Student Lecture Notes 15-1 Basc Busness Statstcs (9 th Edton) Chapter 15 Multple Regresson Model Buldng 004 Prentce-Hall, Inc. Chap 15-1 Chapter Topcs The Quadratc Regresson Model Usng Transformatons
More informationBayesian predictive Configural Frequency Analysis
Psychologcal Test and Assessment Modelng, Volume 54, 2012 (3), 285-292 Bayesan predctve Confgural Frequency Analyss Eduardo Gutérrez-Peña 1 Abstract Confgural Frequency Analyss s a method for cell-wse
More informationNON-CENTRAL 7-POINT FORMULA IN THE METHOD OF LINES FOR PARABOLIC AND BURGERS' EQUATIONS
IJRRAS 8 (3 September 011 www.arpapress.com/volumes/vol8issue3/ijrras_8_3_08.pdf NON-CENTRAL 7-POINT FORMULA IN THE METHOD OF LINES FOR PARABOLIC AND BURGERS' EQUATIONS H.O. Bakodah Dept. of Mathematc
More informationPolynomial Regression Models
LINEAR REGRESSION ANALYSIS MODULE XII Lecture - 6 Polynomal Regresson Models Dr. Shalabh Department of Mathematcs and Statstcs Indan Insttute of Technology Kanpur Test of sgnfcance To test the sgnfcance
More informationSTAT 3008 Applied Regression Analysis
STAT 3008 Appled Regresson Analyss Tutoral : Smple Lnear Regresson LAI Chun He Department of Statstcs, The Chnese Unversty of Hong Kong 1 Model Assumpton To quantfy the relatonshp between two factors,
More informationUsing the estimated penetrances to determine the range of the underlying genetic model in casecontrol
Georgetown Unversty From the SelectedWorks of Mark J Meyer 8 Usng the estmated penetrances to determne the range of the underlyng genetc model n casecontrol desgn Mark J Meyer Neal Jeffres Gang Zheng Avalable
More informationComputing MLE Bias Empirically
Computng MLE Bas Emprcally Kar Wa Lm Australan atonal Unversty January 3, 27 Abstract Ths note studes the bas arses from the MLE estmate of the rate parameter and the mean parameter of an exponental dstrbuton.
More informationPredictive Analytics : QM901.1x Prof U Dinesh Kumar, IIMB. All Rights Reserved, Indian Institute of Management Bangalore
Sesson Outlne Introducton to classfcaton problems and dscrete choce models. Introducton to Logstcs Regresson. Logstc functon and Logt functon. Maxmum Lkelhood Estmator (MLE) for estmaton of LR parameters.
More informationA Hybrid Variational Iteration Method for Blasius Equation
Avalable at http://pvamu.edu/aam Appl. Appl. Math. ISSN: 1932-9466 Vol. 10, Issue 1 (June 2015), pp. 223-229 Applcatons and Appled Mathematcs: An Internatonal Journal (AAM) A Hybrd Varatonal Iteraton Method
More informationAn (almost) unbiased estimator for the S-Gini index
An (almost unbased estmator for the S-Gn ndex Thomas Demuynck February 25, 2009 Abstract Ths note provdes an unbased estmator for the absolute S-Gn and an almost unbased estmator for the relatve S-Gn for
More informationLecture 6: Introduction to Linear Regression
Lecture 6: Introducton to Lnear Regresson An Manchakul amancha@jhsph.edu 24 Aprl 27 Lnear regresson: man dea Lnear regresson can be used to study an outcome as a lnear functon of a predctor Example: 6
More informationHomework Assignment 3 Due in class, Thursday October 15
Homework Assgnment 3 Due n class, Thursday October 15 SDS 383C Statstcal Modelng I 1 Rdge regresson and Lasso 1. Get the Prostrate cancer data from http://statweb.stanford.edu/~tbs/elemstatlearn/ datasets/prostate.data.
More informationSIMPLE LINEAR REGRESSION
Smple Lnear Regresson and Correlaton Introducton Prevousl, our attenton has been focused on one varable whch we desgnated b x. Frequentl, t s desrable to learn somethng about the relatonshp between two
More informationA note on regression estimation with unknown population size
Statstcs Publcatons Statstcs 6-016 A note on regresson estmaton wth unknown populaton sze Mchael A. Hdroglou Statstcs Canada Jae Kwang Km Iowa State Unversty jkm@astate.edu Chrstan Olver Nambeu Statstcs
More informationA PROBABILITY-DRIVEN SEARCH ALGORITHM FOR SOLVING MULTI-OBJECTIVE OPTIMIZATION PROBLEMS
HCMC Unversty of Pedagogy Thong Nguyen Huu et al. A PROBABILITY-DRIVEN SEARCH ALGORITHM FOR SOLVING MULTI-OBJECTIVE OPTIMIZATION PROBLEMS Thong Nguyen Huu and Hao Tran Van Department of mathematcs-nformaton,
More informationDurban Watson for Testing the Lack-of-Fit of Polynomial Regression Models without Replications
Durban Watson for Testng the Lack-of-Ft of Polynomal Regresson Models wthout Replcatons Ruba A. Alyaf, Maha A. Omar, Abdullah A. Al-Shha ralyaf@ksu.edu.sa, maomar@ksu.edu.sa, aalshha@ksu.edu.sa Department
More informationj) = 1 (note sigma notation) ii. Continuous random variable (e.g. Normal distribution) 1. density function: f ( x) 0 and f ( x) dx = 1
Random varables Measure of central tendences and varablty (means and varances) Jont densty functons and ndependence Measures of assocaton (covarance and correlaton) Interestng result Condtonal dstrbutons
More informationLecture 6 More on Complete Randomized Block Design (RBD)
Lecture 6 More on Complete Randomzed Block Desgn (RBD) Multple test Multple test The multple comparsons or multple testng problem occurs when one consders a set of statstcal nferences smultaneously. For
More informationA Bound for the Relative Bias of the Design Effect
A Bound for the Relatve Bas of the Desgn Effect Alberto Padlla Banco de Méxco Abstract Desgn effects are typcally used to compute sample szes or standard errors from complex surveys. In ths paper, we show
More informationOutline. Multivariate Parametric Methods. Multivariate Data. Basic Multivariate Statistics. Steven J Zeil
Outlne Multvarate Parametrc Methods Steven J Zel Old Domnon Unv. Fall 2010 1 Multvarate Data 2 Multvarate ormal Dstrbuton 3 Multvarate Classfcaton Dscrmnants Tunng Complexty Dscrete Features 4 Multvarate
More informationMaximizing Overlap of Large Primary Sampling Units in Repeated Sampling: A comparison of Ernst s Method with Ohlsson s Method
Maxmzng Overlap of Large Prmary Samplng Unts n Repeated Samplng: A comparson of Ernst s Method wth Ohlsson s Method Red Rottach and Padrac Murphy 1 U.S. Census Bureau 4600 Slver Hll Road, Washngton DC
More information1. Inference on Regression Parameters a. Finding Mean, s.d and covariance amongst estimates. 2. Confidence Intervals and Working Hotelling Bands
Content. Inference on Regresson Parameters a. Fndng Mean, s.d and covarance amongst estmates.. Confdence Intervals and Workng Hotellng Bands 3. Cochran s Theorem 4. General Lnear Testng 5. Measures of
More informationChapter 3 Describing Data Using Numerical Measures
Chapter 3 Student Lecture Notes 3-1 Chapter 3 Descrbng Data Usng Numercal Measures Fall 2006 Fundamentals of Busness Statstcs 1 Chapter Goals To establsh the usefulness of summary measures of data. The
More informationOn the Influential Points in the Functional Circular Relationship Models
On the Influental Ponts n the Functonal Crcular Relatonshp Models Department of Mathematcs, Faculty of Scence Al-Azhar Unversty-Gaza, Gaza, Palestne alzad33@yahoo.com Abstract If the nterest s to calbrate
More informationLinear Approximation with Regularization and Moving Least Squares
Lnear Approxmaton wth Regularzaton and Movng Least Squares Igor Grešovn May 007 Revson 4.6 (Revson : March 004). 5 4 3 0.5 3 3.5 4 Contents: Lnear Fttng...4. Weghted Least Squares n Functon Approxmaton...
More information10-701/ Machine Learning, Fall 2005 Homework 3
10-701/15-781 Machne Learnng, Fall 2005 Homework 3 Out: 10/20/05 Due: begnnng of the class 11/01/05 Instructons Contact questons-10701@autonlaborg for queston Problem 1 Regresson and Cross-valdaton [40
More informationEstimation of misclassification probability for multi-class classification based on the Euclidean distance in high-dimensional data
Estmaton of msclassfcaton probablty for mult-class classfcaton based on the Eucldean dstance n hgh-dmensonal data Masash Hyodo Yu Yamada and Hrosh Furuawa Toyo Unversty of Scence Aprl 8 05 Abstract The
More informationAssignment 5. Simulation for Logistics. Monti, N.E. Yunita, T.
Assgnment 5 Smulaton for Logstcs Mont, N.E. Yunta, T. November 26, 2007 1. Smulaton Desgn The frst objectve of ths assgnment s to derve a 90% two-sded Confdence Interval (CI) for the average watng tme
More informationColor Rendering Uncertainty
Australan Journal of Basc and Appled Scences 4(10): 4601-4608 010 ISSN 1991-8178 Color Renderng Uncertanty 1 A.el Bally M.M. El-Ganany 3 A. Al-amel 1 Physcs Department Photometry department- NIS Abstract:
More informationStatistical tables are provided Two Hours UNIVERSITY OF MANCHESTER. Date: Wednesday 4 th June 2008 Time: 1400 to 1600
Statstcal tables are provded Two Hours UNIVERSITY OF MNCHESTER Medcal Statstcs Date: Wednesday 4 th June 008 Tme: 1400 to 1600 MT3807 Electronc calculators may be used provded that they conform to Unversty
More informationClassification as a Regression Problem
Target varable y C C, C,, ; Classfcaton as a Regresson Problem { }, 3 L C K To treat classfcaton as a regresson problem we should transform the target y nto numercal values; The choce of numercal class
More informationDouble Acceptance Sampling Plan for Time Truncated Life Tests Based on Transmuted Generalized Inverse Weibull Distribution
J. Stat. Appl. Pro. 6, No. 1, 1-6 2017 1 Journal of Statstcs Applcatons & Probablty An Internatonal Journal http://dx.do.org/10.18576/jsap/060101 Double Acceptance Samplng Plan for Tme Truncated Lfe Tests
More informationISQS 6348 Final Open notes, no books. Points out of 100 in parentheses. Y 1 ε 2
ISQS 6348 Fnal Open notes, no books. Ponts out of 100 n parentheses. 1. The followng path dagram s gven: ε 1 Y 1 ε F Y 1.A. (10) Wrte down the usual model and assumptons that are mpled by ths dagram. Soluton:
More informationImprovement in Estimating the Population Mean Using Exponential Estimator in Simple Random Sampling
Bulletn of Statstcs & Economcs Autumn 009; Volume 3; Number A09; Bull. Stat. Econ. ISSN 0973-70; Copyrght 009 by BSE CESER Improvement n Estmatng the Populaton Mean Usng Eponental Estmator n Smple Random
More informationFuzzy Boundaries of Sample Selection Model
Proceedngs of the 9th WSES Internatonal Conference on ppled Mathematcs, Istanbul, Turkey, May 7-9, 006 (pp309-34) Fuzzy Boundares of Sample Selecton Model L. MUHMD SFIIH, NTON BDULBSH KMIL, M. T. BU OSMN
More informationTHE EFFECT OF TORSIONAL RIGIDITY BETWEEN ELEMENTS ON FREE VIBRATIONS OF A TELESCOPIC HYDRAULIC CYLINDER SUBJECTED TO EULER S LOAD
Journal of Appled Mathematcs and Computatonal Mechancs 7, 6(3), 7- www.amcm.pcz.pl p-issn 99-9965 DOI:.75/jamcm.7.3. e-issn 353-588 THE EFFECT OF TORSIONAL RIGIDITY BETWEEN ELEMENTS ON FREE VIBRATIONS
More informationPhase I Monitoring of Nonlinear Profiles
Phase I Montorng of Nonlnear Profles James D. Wllams Wllam H. Woodall Jeffrey B. Brch May, 003 J.D. Wllams, Bll Woodall, Jeff Brch, Vrgna Tech 003 Qualty & Productvty Research Conference, Yorktown Heghts,
More informationDERIVATION OF THE PROBABILITY PLOT CORRELATION COEFFICIENT TEST STATISTICS FOR THE GENERALIZED LOGISTIC DISTRIBUTION
Internatonal Worshop ADVANCES IN STATISTICAL HYDROLOGY May 3-5, Taormna, Italy DERIVATION OF THE PROBABILITY PLOT CORRELATION COEFFICIENT TEST STATISTICS FOR THE GENERALIZED LOGISTIC DISTRIBUTION by Sooyoung
More information