A Review on Accelerated Failure Time Models
|
|
- Jeffery Blankenship
- 5 years ago
- Views:
Transcription
1 Iteratioal Joural of Statistics ad Systems ISSN Volume 12, Number 2 (2017), pp Research Idia Publicatios A Review o Accelerated Failure Time Models Riku Saikia 1 ad Maash Pratim Barma 2 1 Research Scholar, Departmet of Statistics, Dibrugarh Uiversity. Dibrugarh , Assam, Idia. 2 Assistat Professor, Departmet of Statistics, Dibrugarh Uiversity, Dibrugarh , Assam, Idia. Abstract Survival aalysis is the aalysis of statistical data i which the outcome variable of iterest is time util a evet occurs. I Statistical literature, it is observed that a good umber of models have bee developed for aalyzig survival data or life time data.the most popular amog them is the Cox Proportioal Hazard (PH) model. Accelerated Failure Time (AFT) model, which is maily used to study the reliability of idustrial products ca also be cosidered as a good alterative of Cox PH model i aalyzig survival data. I this paper, the attempt has bee made to preset a review o Accelerated Failure Time models. Here the historical developmets, techical developmets ad past research o AFT models are discussed. Keywords: Survival data, regressio model, AFT model, Cox PH model, evet 1. BACKGROUND OF THE STUDY: Survival aalysis is the aalysis of survival data i which the outcome variable of iterest is time util some evet occur. Evets are geerally referred as failure because the evet may be death, disease, icidet etc. Due to cesored data, various statistical methods for failure data are developed. They are o-parametric methods (Kapla-Meier method, log-rak test), semi-parametric method (Cox Proportioal Hazard (PH) model), parametric model (Parametric PH model ad Accelerated failure
2 312 Riku Saikia ad Maash Pratim Barma Time (AFT)) model etc. Cox PH model is the most commo approach for modelig survival data. Parametric AFT model provides a alterative to PH model for statistical modelig of survival data (Wei,1992). AFT model is basically used i idustrial fields ad seldom used i the case of survival data. If the appropriate parametric form of AFT model is used the it offers a potetial statistical approach i case of survival data which is based upo the survival curve rather tha the hazard fuctio. It is kow as Accelerated failure time model because the term failure idicates the death, disease etc. ad the term Accelerated idicates the resposible factor for which the rate of failure is icreased. That factor is called Acceleratio factor. The AFT model is also kow as the log-locatio scale model give by Lawless (1982). It is called log-locatio scale because the logarithm of time variable is cosidered. Details of this AFT model or log-locatio scale model will be discussed later. Accordig to the literature foud, Pike (1966) Proposed the AFT model i case of carciogeesis data. He developed the basic statistical methodology ad discussed likelihood estimatio for the Weibull distributio. But i his paper he ever metioed it the ame as Accelerated failure time model. Agai i 1972, Nelso ad Ha, preseted the failure time data i case of idustrial life testig. They cosidered the umber of hours to failure motorettes operatig uder various temperature. The ame Accelerated life test came from this type I cesorig study. The aim of their study was to determie the relatioship betwee failure time data ad temperature. I survival aalysis radom cesorig is cosidered. To modelig failure time data for radom cesorig i D.R. Cox (1972) itroduced a model kow as Cox Proportioal Hazard (PH) model where the effect of covariates act multiplicatively o the hazard fuctio. The Cox PH model is a semi-parametric model i which the baselie hazard fuctio is completely uspecified. Whe the exact form of the parametric model is ot kow the the Cox PH model preferred tha the other parametric models. But whe the correct form of the parametric model is idetified the the parametric models are more suitable tha the semi-parametric or o-parametric models (Kleibaum ad Klei, 2002). The Acceleratio failure time model is a parametric (AFT) model which was itroduced by Cox (1972). Kalbfleisch ad Pretice (2002), itroduced the semi- parametric class of survival model, which was the class of logliear models for time T. I AFT model, the covariate effects act multiplicatively o survival time. Both the PH ad AFT models are regressio models. Though the parametric models are liear regressio model but the differece betwee the liear regressio model ad the survival regressio model is that i case of survival model the cesored observatios are cosidered. The mai objective of this paper is to review o the AFT models ad its techical developmets ad past research i case of survival data.
3 A Review o Accelerated Failure Time Models INTRODUCTION OF THE MODEL: The Accelerated Failure Time model: The AFT model describes the relatioship betwee the respose variable ad the survival time. I this model, the logarithms of the survival time is cosidered as a respose variable ad icludes a error term which is assumed to follow a specific probability distributio. The assumptio of AFT model is that the effect of covariates act multiplicatively (proportioally) with respect to the survival time. The assumptio of AFT model ca be expressed as s(t/x) = s 0 (exp (β x)t) for t 0. (1) Where s(t/x) is the survival fuctio at the time t ad the s 0 (exp (β x)t) is the baselie survival fuctio at the time t. From this equatio (1), AFT model ca states that the survival fuctio of a idividual with covariate x at the time t is same as the baselie survival fuctio of the at the time (exp (β x)t), where β = (β 1, β p ). The factor exp (β x) is kow as the acceleratio factor. The acceleratio factor is the key measure of associatio obtaied i the AFT model. It is a ratio of survival times correspodig to ay fixed value of survival time. From the acceleratio factor oe may able to kow how a chage i covariate values chage i time scale from the baselie time scale. That is with the acceleratio factor oe ca evaluate the effect of predictor variables o survival time. Suppose cosiderig a compariso of survival fuctios amog the persos takig cacer directed treatmets ad ot takig ay cacer directed treatmets. The survival fuctio of cacer directed treatmets ad ot takig ay cacer directed treatmets are cosidered as s 1 (t) ad s 2 (t) respectively. The AFT assumptio ca be expressed as s 2 (t) = s 1 (exp (β x)t) for t 0 Where exp (β x) is the acceleratio factor which compares the patiets with cacer directed treatmets ad ot takig cacer directed treatmets. If exp(β x) > 1, the effect of covariate is decelerated Ad if exp(β x) < 1, the effect of covariate is accelerated. Cox(1972) itroduced the Cox PH model. The Weibull model ad the Expoetial model ca be derived from this model. But the other parametric models such as logormal, log-logistic etc. are ot derived from this PH model. The other parametric such as log-ormal, log-logistic etc. models ca be derived from the hazard fuctio. (Kalbfleisch ad Pretice, 2002). The AFT model i case of hazard fuctio ca be expressed by λ(t/x) = exp(β x) λ 0 (exp(β x) t) for all t.. (2)
4 314 Riku Saikia ad Maash Pratim Barma for example : I case of Expoetial AFT model, The hazard fuctio of expoetial model is Here the hazard fuctio is costat. λ(t) = λ, λ > 0 Now from the equatio (2), the hazard fuctio for Expoetial AFT model is give by The coditioal desity fuctio is λ(t; x) = λ exp(β x) f(t; x) = λ exp(β x) exp( λt exp(β x)). (3) Let Y=logT ad y = α + ε, ad α = logλ the f(e y ) = e α exp (β x)exp [ e α e y exp(β x)] = e α exp (β x)exp ( e y α exp(β x)) = e α exp (β x)exp [ e ε exp(β x)] Y = α β x + ε. (4) Where ε has a extreme value distributio. From this equatio (3),it is see that the covariates act multiplicatively with respect to the hazard fuctio Cox (1972).It is see that from the equatio (3) that the log-liear form i the equatio(4) ca be obtai ad this model is called the AFT model. The aother represetatio of the relatio betwee failure time ad explaatory / respose variable is the liear relatioship betwee the logarithm of survival time ad icludes a error term which is assumed to follow a specific distributio such as expoetial, weibull, log-ormal, log-logistic etc. The geeral log-liear represetatio of AFT model for ith idividual is give as logt i = μ + β 1 x β p x p + σε i (5) Where logt i represets the log-trasformed survival time, x 1,.. x p are the explaatory variables with the coefficiets β 1,.. β p ; ε i, is the residual or uexplaied variatio i the log- trasformed survival times, that is the deviatio of the values of logt i from the liear part of the model. ε i assumes a specific distributio ad μ is the itercept ad σ is the scale parameters respectively. The iitial step i fittig a AFT model is that for eachε i, there is a correspodig distributio for T i. If the ε i, has a extreme value distributio the T i follows the weibull distributio. Agai if ε i follows ormal distributio the the T i follows logormal distributio etc.
5 A Review o Accelerated Failure Time Models 315 The survival fuctio of T i ca be expressed by the survival fuctio of ε i. S ( t) P( T t) i P(logT log t) P( x... x log t) 1 1 log t x... x 1 1 p p ( i ) log t x... x 1 1 p p i ( ) S ( t) S ( t) i P S i p p i Agai the cumulative hazard fuctio of T i is H i (t) = log (s i (t)) = logs εi (t) = H εi (t) For example : Log-ormal AFT model : If ε i has a stadard ormal distributio the T i is log-ormally distributed. The desity fuctio of ormal distributio is f εi (ε) = 1 2π exp (log t μ β 2 1x 1. β p x p ) /2 σ The survival fuctio of ormal- distributio is S εi (ε) = 1 Φ(ε) The distributio fuctio of ormal distributio is The cumulative hazard fuctio is Ad the hazard fuctio is Φ(ε) = log t μ β 1x 1 β p x p. σ H εi (ε) = log {1 Φ(ε)} h εi (ε) = f εi(ε) S εi (ε) I this way the log-ormal AFT form ca be derived.
6 316 Riku Saikia ad Maash Pratim Barma 3. REVIEW ON AFT MODELS : The theory of AFT model has bee a field of active research for last few decades as this model has vast applicability i the reliability theory ad idustrial experimets as well as survivorship data. I the followig sectio, it is tried to have a bird s eye view o a lio s share of such developmets. Pike (1966) i his work suggest two distributioal forms developed the statistical methodology ad discussed the likelihood method of estimatio for the Weibull distributio. Johso ad Kotz (1970) discussed about the estimatio of parametric models ad icludig expoetial, weibull, log-ormal, gamma, log-logistic. Lawless(1982) preseted ad illustrated the statistical methods for modelig ad aalyzig life time data. He used the term log-locatio scale model istead of Accelerated failure time model because the logarithm of the survival time was cosidered. Vaderhoef (1982) i his work applied a parametric method which was preseted for the aalysis of curret status data based o AFT model ad maximum likelihood estimatio. I the paper it seemed that the Weibull distributio model provided a well fittig model. Cox ad Oakes (1984) showed that the Weibull distributio had both proportioal hazards ad accelerated failure time property ad Log-logistic distributio had proportioal odds ad accelerated failure time property.wei (1992) itroduced a o-parametric versio of AFT model, which did ot required the specificatio of a probability distributio for the survival data. Orbe et al. (2002) described that AFT model could be a iterestig alterative to the Cox PH model whe PH assumptio did ot hold. Implemetatio ad iterpretatio of the results of AFT was simple. He applied AFT to two real examples ad carried out a simulatio study ad AFT model lead to more precise results. Nardi ad Scheme (2003) compared Cox PH ad parametric models i three cliical trial studies maily performed at Viea Uiversity Medical School. They used Normal deviate residuals (Nardi,1999) to verify the parametric model assumptios. Their study showed that Weibull model was superior to other parametric models. Pourhoseigholi et al., (2007) compared Cox regressio ad Parametric models i the aalysis of the patiets with gastric carcioma ad foud that logormal model fitted better tha other models. Sayehmir et al.,(2008) studied progostics factors of survival time after hematopoietic stem cell trasplat i acute lymphoblastic leukemia patiets i Shariati Hospital, Tehara ad foud that Weibull AFT model was superior to Cox PH model. Qi (2009) compared PH ad AFT models ad suggested that the Cox PH model may ot be appropriate i some situatios ad that the AFT model could provide a more appropriate descriptio of the data. Ravagard et al.,(2011) compared Cox PH model ad the parametric models i studyig the legth of stay i a Tertiary Teachig Hospital i Tehra ad showed that Gamma AFT model was best fitted for that data. Khael et al., (2012) idetified the importat progostic factors of Acute Liver Failure patiets i Idia by applyig AFT models ad foud that Log-ormal
7 A Review o Accelerated Failure Time Models 317 AFT was well fitted for that data i compariso to log-logistics. Valliayagam et al., (2014) compared parametric models icludig Weibull ad Log-ormal with Cox PH model for boe- marrow trasplatatio data ad Log-ormal model was better fit tha the other models. Nawumbei et al., (2014) compared Cox PH ad AFT models i HIV/TB Co-ifectio survival data ad revealed that Gamma model was well fitted to the Co-ifectio data. 4. ESTIMATION OF ACCELERATED FAILURE TIME MODEL: AFT models are fitted by usig maximum likelihood estimatio (MLE) method. The likelihood of observed survival times t 1,.. t is L = {f i (t i )} δ i{s i (t i )} 1 δ i Where f i (t i ) ad s i (t i ) are the desity fuctio ad the survival fuctio for the ith idividual at the time t i respectively. δ i is the evet idicator for the ith idividual δ i = { 1, if the ith observatio is evet 0, if the ith observatio is cesored Now S i (t i ) = S εi (z i ) Where, z i = logt μ β 1x 1 β p x p σ The log-likelihood fuctio is give by logl = σt i δ i{fεi (z i )} δ i{s εi (z i )} 1 δ i logl = σ i log (σt i ) + δ i log{f εi (z i )} + (1 δ i )log{s εi (z i )} Where z i = logt μ β 1x 1.β p x p ad MLE of (P+2) ukow parameters, μ, σ ad σ β 1,.. β p are foud by maximizig the log-likelihood fuctio usig Newto Raphso procedure.
8 318 Riku Saikia ad Maash Pratim Barma Estimatio of parameters for the Weibull AFT model without covariates. The desity fuctio of Weibull AFT model is Where < y <. f(y; μ, σ) = 1 exp(y μ) /σ exp ( exp (y μ)/σ) σ If the ε i follows the extreme value distributio the T i follows the Weibull distributio. The survival fuctio ad the desity fuctio of the extreme value distributio are respectively The likelihood fuctio is The log-likelihood fuctio is s(z i ) = exp ( exp(z i )) log(s(z i )) = exp (z i ) log(s(z i )) z i = exp (z i ) f(z i ) = exp(z i ) exp ( exp(z i )) logf(z i ) = z i exp (z i ) log(f(z i )) z i = 1 exp (z i ) L = 1 σ [ {f i(t i )} δ i{s i (t i )} 1 δ i ] logl = δ i log ( 1 σ ) + δ i log {f εi (z i )} + (1 δ i ) log{s εi (z i )} logl = rlogσ + δ i log {f εi (z i )} + (1 δ i ) log{s εi (z i )} = rlogσ + δ i log { exp(z i ) exp ( exp(z i ))} + (1 δ i ) log {exp ( exp(z i ))}
9 A Review o Accelerated Failure Time Models 319 = rlogσ + ( δ i z i exp (z i )). (6) Differetiatig this equatio (6) with respect to parameters μ ad σ oe ca get the parameters values of Weibull AFT model. I this way the parameters of the AFT models ca be estimated. 5. MODEL CHECKING: To check the appropriate distributio of the AFT model various methods have bee used. They are such as Akaike Iformatio Criterio ( AIC), Baysia Iformatio Criteria( BIC), etc. (i) AIC: To compare various semi-parametric ad parametric models Akaike Iformatio Criterio (AIC) is used. The AIC is proposed by Akaike (Akaike, 1974). It is a measure of goodess of fit of a estimated statistical model. For the model i this study, AIC is computed as follows AIC = 2(log likelihhod) + 2(P + K) Where P is the umber of parameters ad K is the umber of coefficiets (excludig costat) i the model. For P=1, for the expoetial, P=2, for Weibull, Log-logistic, Logormal etc. The model which as smallest AIC value is cosidered as best fitted model. (ii) BIC: The Baysia Iformatio Criteria (BIC) is give by Schwarz (Schwarz, 1978). It is computed as follows BIC = 2(log likelihood) + (P + K) log () Where P is the umber of parameters i the distributio, K is the umber of coefficiets ad log() is the umber of observatios. The distributio which has the lowest BIC value is cosidered as best fitted model. (iii) Cox Sell-Residual: the Cox Sell Residuals ca by used to check the goodess of fit of the model which was give by Cox ad Sell ( Cox ad Sell, 1968). The Cox- Sell residual for the ith idividual with observed time t is defied as r ci = S i (t) = S εi ( logt μ β 1x 1.β p x p ) σ where the parameters are already defied above. The Cox- Sell residual ca applied i ay of the parametric AFT model.
10 320 Riku Saikia ad Maash Pratim Barma 6. CONCLUSION: From the above discussio, it is observed that the AFT models which is widely used i aalyzig idustrial data ca also provide a good alterative of the Cox PH model. If the correct form of the parametric model is kow, the the AFT model has a vast scope for the future researchers. This model is comparatively easy to iterpret. A umber of research studies have already bee coducted by usig the AFT model which provides fruitful results. There is a scope for further developmet of the AFT model. Till ow, AFT model has bee fitted for distributios like expoetial, weibull, log-ormal, log-logistic, gamma etc. Oe ca use other distributios such as skew-ormal, geeralized expoetial etc. to model survival data. I AFT model, the depedet variable is log of the survival time T. The depedet variable ca also be used by other strictly icreasig fuctio which is also the further scope of the study. REFERENCES: [1] Akaike H(1974).: A New Look at the Statistical Model Idetificatio. IEEE. Trasactio ad Automatic Cotrol AC-19, pp [2] Cox D.R., ad Sell E.J(1968).: A Geeral Defiitio of Residuals (with discussio), Joural of the Royal Statistical Society, A.. [3] Cox, D.R(1972). : Regressio Models ad Life Tables, Joural of the Royal Statistical Society, Series B, (Methodological),,Vol 34, No. 2, [4] Cox ad Oakes(1984): Aalysis of Survival Data, Chapma ad Hall, Lodo New York. [5] Kleibaum,G.David ad Klei, Mitchel(1996) : Survival Aalysis : A Self- Learig Text, Secod Editio,, Spriger, New York. [6] Khaal Prasad, Shakhar, Sreeivas,V. ad Acharya,K. Subrat (2014) : Accelerated Failure Time Models: A Applicatio i the Survival of Acute Liver Failure Patiets i Idia, Iteratioal Joural of Sciece of Research (IJSR), ISSN: ,Impact Factor(2012):3.358,Volume 3, Issue 6,Jue 2014, pp [7] Kalbfleisch, Joh D. ad Pretice, Ross L.(2002) : The Statistical Aalysis of Failure Time Data, Joh Wiley & Sos, Ic. [8] Lawless, J. F.(1982) : Statistical Models ad Methods for Lifetime Data Aalysis, Wiley, New York.
11 A Review o Accelerated Failure Time Models 321 [9] Nelso, W.B. ad Hah, G.J.(1972) : Liear Estimatio of a Regressio Relatioship from Cesored data: 1,Simple Methods ad Their Applicatios (With Discussio), Techometrics,14, [10] Nardi, Alessadra ad Schemper, Michael(2003) : Comparig Cox ad Parametric models i Cliical Studies, Statistics i Medicie, Statist Med.; 22: [11] Nawumbei, Ngbador Derek, Luguterah, Albert ad Adampah, Timothy(2014): Performace of Cox Proportioal Hazard ad Accelerated Failure Time Models i the Aalysis of HIV/TB Co-ifectio Survival Data, Research o Humaities ad Social Scieces, ISSN (Paper) ISSN (Olie) (Olie), Vol.4, No.21, pp [12] Orbe Jesus, Ferreira Eva ad Nuez- Atio, Vicete (2002): Comparig Proportioal Hazards ad Accelerated Failure Time models for Survival Aalysis, Statistics i Medicie. 21: pp [13] Pike M.C.: A Method of Aalysis of a Certai Class of Experimets i Carciogeesis, Biometrics 22(1966), [14] Pourhoseigholi,M.A.,E. Hajizadeh,B.Moghimi Dehkordi, A. Safaee,A. Abadi ad M.R. Zali (2007) : Comparig Cox regressio ad parametric models for survival of patiets with gastric carcioma, Asia Pacific Joural of Cacer Prevetio ; 8 (3): [15] Qi,Jiezhi, (2009): Compariso of Proportioal Hazards ad Accelerated Failure Time Models, A Thesis Submitted to the College of Graduate Studies ad Research i Partial Fulfillmet of the Requiremets for the Degree of Master of Sciece i the Departmet of Mathematics ad Statistics Uiversity of Saskatchewa Saskatoo, Saskatchewa. [16] Ravagard, R., Arab M., Rashidia, A.,Akbarisari, A., Zare A., Zeraat, H. (2011): Compared Cox Model ad Parametric Models i the Study of Legth of Stay i a Tertiary Teachig Hospital i Tehra, Ira. Acta MedicaIraica, 49(10): Stacy(1962): [17] Schwarz, Gideo E.(1978) : Estimatig the Dimesio of a Model, The Aals of Statistics, vol 6, No.2, [18] Sayehmiri, K., Eshraghia R. M., Mohammad K., Alimoghaddam K., Foroushai R. A., Zeraati H., Golesta, A., Ghavamzadeh, A. (2008): Progostic Factors of Survival time after Hematopoietic Stem Cell Trasplat i acute Lymphoblastic Leukemia Patiets i Shariati Hospital, Tehra, Joural of Experimetal & Cliical Cacer Research, 27(1): 1-9.
12 322 Riku Saikia ad Maash Pratim Barma [19] Vaderhoeft, Camille ad Vaderhoeft, Camille (1982) : Accelerated Failure Time Models: A Applicatio To Curret Status Breast- Feedig Data From Pakista,Vol.38, No. 1 / 2 ( Geaio- Giugo), pp [20] Valliayagam, V., Prathap, S., ad Vekatesa, P. (2014): Parametric Regressio Models i the Aalysis of Breast Cacer Survival Data, Iteratioal Joural of Sciece ad Techology, 3(3) [21] Wei, L.J.: The Accelerated Failure Time Mode: A Useful Alterative To the Cox Regressio Model i Survival Aalysis, Statistics i Medicie,11, 1992,
Bootstrap Intervals of the Parameters of Lognormal Distribution Using Power Rule Model and Accelerated Life Tests
Joural of Moder Applied Statistical Methods Volume 5 Issue Article --5 Bootstrap Itervals of the Parameters of Logormal Distributio Usig Power Rule Model ad Accelerated Life Tests Mohammed Al-Ha Ebrahem
More informationMathematical Modeling of Optimum 3 Step Stress Accelerated Life Testing for Generalized Pareto Distribution
America Joural of Theoretical ad Applied Statistics 05; 4(: 6-69 Published olie May 8, 05 (http://www.sciecepublishiggroup.com/j/ajtas doi: 0.648/j.ajtas.05040. ISSN: 6-8999 (Prit; ISSN: 6-9006 (Olie Mathematical
More informationSTA6938-Logistic Regression Model
Dr. Yig Zhag STA6938-Logistic Regressio Model Topic -Simple (Uivariate) Logistic Regressio Model Outlies:. Itroductio. A Example-Does the liear regressio model always work? 3. Maximum Likelihood Curve
More informationConfidence interval for the two-parameter exponentiated Gumbel distribution based on record values
Iteratioal Joural of Applied Operatioal Research Vol. 4 No. 1 pp. 61-68 Witer 2014 Joural homepage: www.ijorlu.ir Cofidece iterval for the two-parameter expoetiated Gumbel distributio based o record values
More information1 Inferential Methods for Correlation and Regression Analysis
1 Iferetial Methods for Correlatio ad Regressio Aalysis I the chapter o Correlatio ad Regressio Aalysis tools for describig bivariate cotiuous data were itroduced. The sample Pearso Correlatio Coefficiet
More informationBayesian and E- Bayesian Method of Estimation of Parameter of Rayleigh Distribution- A Bayesian Approach under Linex Loss Function
Iteratioal Joural of Statistics ad Systems ISSN 973-2675 Volume 12, Number 4 (217), pp. 791-796 Research Idia Publicatios http://www.ripublicatio.com Bayesia ad E- Bayesia Method of Estimatio of Parameter
More informationThe Sampling Distribution of the Maximum. Likelihood Estimators for the Parameters of. Beta-Binomial Distribution
Iteratioal Mathematical Forum, Vol. 8, 2013, o. 26, 1263-1277 HIKARI Ltd, www.m-hikari.com http://d.doi.org/10.12988/imf.2013.3475 The Samplig Distributio of the Maimum Likelihood Estimators for the Parameters
More informationGoodness-Of-Fit For The Generalized Exponential Distribution. Abstract
Goodess-Of-Fit For The Geeralized Expoetial Distributio By Amal S. Hassa stitute of Statistical Studies & Research Cairo Uiversity Abstract Recetly a ew distributio called geeralized expoetial or expoetiated
More informationSample Size Estimation in the Proportional Hazards Model for K-sample or Regression Settings Scott S. Emerson, M.D., Ph.D.
ample ie Estimatio i the Proportioal Haards Model for K-sample or Regressio ettigs cott. Emerso, M.D., Ph.D. ample ie Formula for a Normally Distributed tatistic uppose a statistic is kow to be ormally
More informationComparison of Methods for Estimation of Sample Sizes under the Weibull Distribution
Iteratioal Joural of Applied Egieerig Research ISSN 0973-4562 Volume 12, Number 24 (2017) pp. 14273-14278 Research Idia Publicatios. http://www.ripublicatio.com Compariso of Methods for Estimatio of Sample
More informationMaximum likelihood estimation from record-breaking data for the generalized Pareto distribution
METRON - Iteratioal Joural of Statistics 004, vol. LXII,. 3, pp. 377-389 NAGI S. ABD-EL-HAKIM KHALAF S. SULTAN Maximum likelihood estimatio from record-breakig data for the geeralized Pareto distributio
More informationMOMENT-METHOD ESTIMATION BASED ON CENSORED SAMPLE
Vol. 8 o. Joural of Systems Sciece ad Complexity Apr., 5 MOMET-METHOD ESTIMATIO BASED O CESORED SAMPLE I Zhogxi Departmet of Mathematics, East Chia Uiversity of Sciece ad Techology, Shaghai 37, Chia. Email:
More informationCEE 522 Autumn Uncertainty Concepts for Geotechnical Engineering
CEE 5 Autum 005 Ucertaity Cocepts for Geotechical Egieerig Basic Termiology Set A set is a collectio of (mutually exclusive) objects or evets. The sample space is the (collectively exhaustive) collectio
More informationLinear Regression Models
Liear Regressio Models Dr. Joh Mellor-Crummey Departmet of Computer Sciece Rice Uiversity johmc@cs.rice.edu COMP 528 Lecture 9 15 February 2005 Goals for Today Uderstad how to Use scatter diagrams to ispect
More informationProbability and statistics: basic terms
Probability ad statistics: basic terms M. Veeraraghava August 203 A radom variable is a rule that assigs a umerical value to each possible outcome of a experimet. Outcomes of a experimet form the sample
More informationANOTHER WEIGHTED WEIBULL DISTRIBUTION FROM AZZALINI S FAMILY
ANOTHER WEIGHTED WEIBULL DISTRIBUTION FROM AZZALINI S FAMILY Sulema Nasiru, MSc. Departmet of Statistics, Faculty of Mathematical Scieces, Uiversity for Developmet Studies, Navrogo, Upper East Regio, Ghaa,
More informationControl chart for number of customers in the system of M [X] / M / 1 Queueing system
Iteratioal Joural of Iovative Research i Sciece, Egieerig ad Techology (A ISO 3297: 07 Certified Orgaiatio) Cotrol chart for umber of customers i the system of M [X] / M / Queueig system T.Poogodi, Dr.
More informationPOWER AKASH DISTRIBUTION AND ITS APPLICATION
POWER AKASH DISTRIBUTION AND ITS APPLICATION Rama SHANKER PhD, Uiversity Professor, Departmet of Statistics, College of Sciece, Eritrea Istitute of Techology, Asmara, Eritrea E-mail: shakerrama009@gmail.com
More informationEstimation for Complete Data
Estimatio for Complete Data complete data: there is o loss of iformatio durig study. complete idividual complete data= grouped data A complete idividual data is the oe i which the complete iformatio of
More informationDouble Stage Shrinkage Estimator of Two Parameters. Generalized Exponential Distribution
Iteratioal Mathematical Forum, Vol., 3, o. 3, 3-53 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/.9/imf.3.335 Double Stage Shrikage Estimator of Two Parameters Geeralized Expoetial Distributio Alaa M.
More informationStatistical Inference (Chapter 10) Statistical inference = learn about a population based on the information provided by a sample.
Statistical Iferece (Chapter 10) Statistical iferece = lear about a populatio based o the iformatio provided by a sample. Populatio: The set of all values of a radom variable X of iterest. Characterized
More informationProperties and Hypothesis Testing
Chapter 3 Properties ad Hypothesis Testig 3.1 Types of data The regressio techiques developed i previous chapters ca be applied to three differet kids of data. 1. Cross-sectioal data. 2. Time series data.
More informationADVANCED SOFTWARE ENGINEERING
ADVANCED SOFTWARE ENGINEERING COMP 3705 Exercise Usage-based Testig ad Reliability Versio 1.0-040406 Departmet of Computer Ssciece Sada Narayaappa, Aeliese Adrews Versio 1.1-050405 Departmet of Commuicatio
More informationInvestigating the Significance of a Correlation Coefficient using Jackknife Estimates
Iteratioal Joural of Scieces: Basic ad Applied Research (IJSBAR) ISSN 2307-4531 (Prit & Olie) http://gssrr.org/idex.php?joural=jouralofbasicadapplied ---------------------------------------------------------------------------------------------------------------------------
More informationA proposed discrete distribution for the statistical modeling of
It. Statistical Ist.: Proc. 58th World Statistical Cogress, 0, Dubli (Sessio CPS047) p.5059 A proposed discrete distributio for the statistical modelig of Likert data Kidd, Marti Cetre for Statistical
More informationModeling and Estimation of a Bivariate Pareto Distribution using the Principle of Maximum Entropy
Sri Laka Joural of Applied Statistics, Vol (5-3) Modelig ad Estimatio of a Bivariate Pareto Distributio usig the Priciple of Maximum Etropy Jagathath Krisha K.M. * Ecoomics Research Divisio, CSIR-Cetral
More informationSample Size Determination (Two or More Samples)
Sample Sie Determiatio (Two or More Samples) STATGRAPHICS Rev. 963 Summary... Data Iput... Aalysis Summary... 5 Power Curve... 5 Calculatios... 6 Summary This procedure determies a suitable sample sie
More informationResponse Variable denoted by y it is the variable that is to be predicted measure of the outcome of an experiment also called the dependent variable
Statistics Chapter 4 Correlatio ad Regressio If we have two (or more) variables we are usually iterested i the relatioship betwee the variables. Associatio betwee Variables Two variables are associated
More informationThe new class of Kummer beta generalized distributions
The ew class of Kummer beta geeralized distributios Rodrigo Rossetto Pescim 12 Clarice Garcia Borges Demétrio 1 Gauss Moutiho Cordeiro 3 Saralees Nadarajah 4 Edwi Moisés Marcos Ortega 1 1 Itroductio Geeralized
More informationCONTROL CHARTS FOR THE LOGNORMAL DISTRIBUTION
CONTROL CHARTS FOR THE LOGNORMAL DISTRIBUTION Petros Maravelakis, Joh Paaretos ad Stelios Psarakis Departmet of Statistics Athes Uiversity of Ecoomics ad Busiess 76 Patisio St., 4 34, Athes, GREECE. Itroductio
More informationEstimation of Gumbel Parameters under Ranked Set Sampling
Joural of Moder Applied Statistical Methods Volume 13 Issue 2 Article 11-2014 Estimatio of Gumbel Parameters uder Raked Set Samplig Omar M. Yousef Al Balqa' Applied Uiversity, Zarqa, Jorda, abuyaza_o@yahoo.com
More information11 Correlation and Regression
11 Correlatio Regressio 11.1 Multivariate Data Ofte we look at data where several variables are recorded for the same idividuals or samplig uits. For example, at a coastal weather statio, we might record
More informationConfidence Intervals For P(X less than Y) In The Exponential Case With Common Location Parameter
Joural of Moder Applied Statistical Methods Volume Issue Article 7 --3 Cofidece Itervals For P(X less tha Y I he Expoetial Case With Commo Locatio Parameter Ayma Baklizi Yarmouk Uiversity, Irbid, Jorda,
More informationFirst, note that the LS residuals are orthogonal to the regressors. X Xb X y = 0 ( normal equations ; (k 1) ) So,
0 2. OLS Part II The OLS residuals are orthogoal to the regressors. If the model icludes a itercept, the orthogoality of the residuals ad regressors gives rise to three results, which have limited practical
More informationPower Comparison of Some Goodness-of-fit Tests
Florida Iteratioal Uiversity FIU Digital Commos FIU Electroic Theses ad Dissertatios Uiversity Graduate School 7-6-2016 Power Compariso of Some Goodess-of-fit Tests Tiayi Liu tliu019@fiu.edu DOI: 10.25148/etd.FIDC000750
More informationA Block Cipher Using Linear Congruences
Joural of Computer Sciece 3 (7): 556-560, 2007 ISSN 1549-3636 2007 Sciece Publicatios A Block Cipher Usig Liear Cogrueces 1 V.U.K. Sastry ad 2 V. Jaaki 1 Academic Affairs, Sreeidhi Istitute of Sciece &
More informationR. van Zyl 1, A.J. van der Merwe 2. Quintiles International, University of the Free State
Bayesia Cotrol Charts for the Two-parameter Expoetial Distributio if the Locatio Parameter Ca Take o Ay Value Betwee Mius Iity ad Plus Iity R. va Zyl, A.J. va der Merwe 2 Quitiles Iteratioal, ruaavz@gmail.com
More informationLecture 22: Review for Exam 2. 1 Basic Model Assumptions (without Gaussian Noise)
Lecture 22: Review for Exam 2 Basic Model Assumptios (without Gaussia Noise) We model oe cotiuous respose variable Y, as a liear fuctio of p umerical predictors, plus oise: Y = β 0 + β X +... β p X p +
More informationLINEAR REGRESSION ANALYSIS. MODULE IX Lecture Multicollinearity
LINEAR REGRESSION ANALYSIS MODULE IX Lecture - 9 Multicolliearity Dr Shalabh Departmet of Mathematics ad Statistics Idia Istitute of Techology Kapur Multicolliearity diagostics A importat questio that
More informationGoodness-Of-Fit For The Generalized Exponential Distribution. Abstract
Goodess-Of-Fit For The Geeralized Expoetial Distributio By Amal S. Hassa stitute of Statistical Studies & Research Cairo Uiversity Abstract Recetly a ew distributio called geeralized expoetial or expoetiated
More informationSTA Learning Objectives. Population Proportions. Module 10 Comparing Two Proportions. Upon completing this module, you should be able to:
STA 2023 Module 10 Comparig Two Proportios Learig Objectives Upo completig this module, you should be able to: 1. Perform large-sample ifereces (hypothesis test ad cofidece itervals) to compare two populatio
More informationREGRESSION (Physics 1210 Notes, Partial Modified Appendix A)
REGRESSION (Physics 0 Notes, Partial Modified Appedix A) HOW TO PERFORM A LINEAR REGRESSION Cosider the followig data poits ad their graph (Table I ad Figure ): X Y 0 3 5 3 7 4 9 5 Table : Example Data
More informationThe Random Walk For Dummies
The Radom Walk For Dummies Richard A Mote Abstract We look at the priciples goverig the oe-dimesioal discrete radom walk First we review five basic cocepts of probability theory The we cosider the Beroulli
More information1 Models for Matched Pairs
1 Models for Matched Pairs Matched pairs occur whe we aalyse samples such that for each measuremet i oe of the samples there is a measuremet i the other sample that directly relates to the measuremet i
More informationAkaike Information Criterion and Fourth-Order Kernel Method for Line Transect Sampling (LTS)
Appl. Math. If. Sci. 10, No. 1, 267-271 (2016 267 Applied Mathematics & Iformatio Scieces A Iteratioal Joural http://dx.doi.org/10.18576/amis/100127 Akaike Iformatio Criterio ad Fourth-Order Kerel Method
More informationAsymptotic distribution of products of sums of independent random variables
Proc. Idia Acad. Sci. Math. Sci. Vol. 3, No., May 03, pp. 83 9. c Idia Academy of Scieces Asymptotic distributio of products of sums of idepedet radom variables YANLING WANG, SUXIA YAO ad HONGXIA DU ollege
More informationTABLES AND FORMULAS FOR MOORE Basic Practice of Statistics
TABLES AND FORMULAS FOR MOORE Basic Practice of Statistics Explorig Data: Distributios Look for overall patter (shape, ceter, spread) ad deviatios (outliers). Mea (use a calculator): x = x 1 + x 2 + +
More informationFACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING. Lectures
FACULTY OF MATHEMATICAL STUDIES MATHEMATICS FOR PART I ENGINEERING Lectures MODULE 5 STATISTICS II. Mea ad stadard error of sample data. Biomial distributio. Normal distributio 4. Samplig 5. Cofidece itervals
More informationReliability Measures of a Series System with Weibull Failure Laws
Iteratioal Joural of Statistics ad Systems ISSN 973-2675 Volume, Number 2 (26), pp. 73-86 Research Idia Publicatios http://www.ripublicatio.com Reliability Measures of a Series System with Weibull Failure
More informationA Distributional Approach Using Propensity Scores
A Distributioal Approach Usig Propesity Scores Zhiqiag Ta Departmet of Biostatistics Johs Hopkis School of Public Health http://www.biostat.jhsph.edu/ zta Jue 20, 2005 Outlie Itroductio Couterfactual framework
More information10. Comparative Tests among Spatial Regression Models. Here we revisit the example in Section 8.1 of estimating the mean of a normal random
Part III. Areal Data Aalysis 0. Comparative Tests amog Spatial Regressio Models While the otio of relative likelihood values for differet models is somewhat difficult to iterpret directly (as metioed above),
More informationOpen book and notes. 120 minutes. Cover page and six pages of exam. No calculators.
IE 330 Seat # Ope book ad otes 120 miutes Cover page ad six pages of exam No calculators Score Fial Exam (example) Schmeiser Ope book ad otes No calculator 120 miutes 1 True or false (for each, 2 poits
More informationMATH 320: Probability and Statistics 9. Estimation and Testing of Parameters. Readings: Pruim, Chapter 4
MATH 30: Probability ad Statistics 9. Estimatio ad Testig of Parameters Estimatio ad Testig of Parameters We have bee dealig situatios i which we have full kowledge of the distributio of a radom variable.
More informationChapter 6 Sampling Distributions
Chapter 6 Samplig Distributios 1 I most experimets, we have more tha oe measuremet for ay give variable, each measuremet beig associated with oe radomly selected a member of a populatio. Hece we eed to
More informationA NEW CLASS OF 2-STEP RATIONAL MULTISTEP METHODS
Jural Karya Asli Loreka Ahli Matematik Vol. No. (010) page 6-9. Jural Karya Asli Loreka Ahli Matematik A NEW CLASS OF -STEP RATIONAL MULTISTEP METHODS 1 Nazeeruddi Yaacob Teh Yua Yig Norma Alias 1 Departmet
More informationLecture 11 Simple Linear Regression
Lecture 11 Simple Liear Regressio Fall 2013 Prof. Yao Xie, yao.xie@isye.gatech.edu H. Milto Stewart School of Idustrial Systems & Egieerig Georgia Tech Midterm 2 mea: 91.2 media: 93.75 std: 6.5 2 Meddicorp
More informationBayesian inference for Parameter and Reliability function of Inverse Rayleigh Distribution Under Modified Squared Error Loss Function
Australia Joural of Basic ad Applied Scieces, (6) November 26, Pages: 24-248 AUSTRALIAN JOURNAL OF BASIC AND APPLIED SCIENCES ISSN:99-878 EISSN: 239-844 Joural home page: www.ajbasweb.com Bayesia iferece
More information5. Likelihood Ratio Tests
1 of 5 7/29/2009 3:16 PM Virtual Laboratories > 9. Hy pothesis Testig > 1 2 3 4 5 6 7 5. Likelihood Ratio Tests Prelimiaries As usual, our startig poit is a radom experimet with a uderlyig sample space,
More informationChi-Squared Tests Math 6070, Spring 2006
Chi-Squared Tests Math 6070, Sprig 2006 Davar Khoshevisa Uiversity of Utah February XXX, 2006 Cotets MLE for Goodess-of Fit 2 2 The Multiomial Distributio 3 3 Applicatio to Goodess-of-Fit 6 3 Testig for
More informationAlgebra of Least Squares
October 19, 2018 Algebra of Least Squares Geometry of Least Squares Recall that out data is like a table [Y X] where Y collects observatios o the depedet variable Y ad X collects observatios o the k-dimesioal
More informationSimple Linear Regression
Chapter 2 Simple Liear Regressio 2.1 Simple liear model The simple liear regressio model shows how oe kow depedet variable is determied by a sigle explaatory variable (regressor). Is is writte as: Y i
More informationApproximating the ruin probability of finite-time surplus process with Adaptive Moving Total Exponential Least Square
WSEAS TRANSACTONS o BUSNESS ad ECONOMCS S. Khotama, S. Boothiem, W. Klogdee Approimatig the rui probability of fiite-time surplus process with Adaptive Movig Total Epoetial Least Square S. KHOTAMA, S.
More informationCastiel, Supernatural, Season 6, Episode 18
13 Differetial Equatios the aswer to your questio ca best be epressed as a series of partial differetial equatios... Castiel, Superatural, Seaso 6, Episode 18 A differetial equatio is a mathematical equatio
More informationGoodness-of-Fit Tests and Categorical Data Analysis (Devore Chapter Fourteen)
Goodess-of-Fit Tests ad Categorical Data Aalysis (Devore Chapter Fourtee) MATH-252-01: Probability ad Statistics II Sprig 2019 Cotets 1 Chi-Squared Tests with Kow Probabilities 1 1.1 Chi-Squared Testig................
More informationA Comparison of Bayesian and Classical Approach for Estimating Markov Based Logistic Model
America Joural of Mathematics ad Statistics 5, 5(4): 78-83 DOI:.593/j.ajms.554. A Compariso of Bayesia ad Classical Approach for Estimatig Markov Based Logistic Model Jaarda Mahata,*, Soma Chowdhury Biswas,
More informationBIOSTATISTICS. Lecture 5 Interval Estimations for Mean and Proportion. dr. Petr Nazarov
Microarray Ceter BIOSTATISTICS Lecture 5 Iterval Estimatios for Mea ad Proportio dr. Petr Nazarov 15-03-013 petr.azarov@crp-sate.lu Lecture 5. Iterval estimatio for mea ad proportio OUTLINE Iterval estimatios
More informationChapter 12 Correlation
Chapter Correlatio Correlatio is very similar to regressio with oe very importat differece. Regressio is used to explore the relatioship betwee a idepedet variable ad a depedet variable, whereas correlatio
More informationComparison of Minimum Initial Capital with Investment and Non-investment Discrete Time Surplus Processes
The 22 d Aual Meetig i Mathematics (AMM 207) Departmet of Mathematics, Faculty of Sciece Chiag Mai Uiversity, Chiag Mai, Thailad Compariso of Miimum Iitial Capital with Ivestmet ad -ivestmet Discrete Time
More informationControl Charts for Mean for Non-Normally Correlated Data
Joural of Moder Applied Statistical Methods Volume 16 Issue 1 Article 5 5-1-017 Cotrol Charts for Mea for No-Normally Correlated Data J. R. Sigh Vikram Uiversity, Ujjai, Idia Ab Latif Dar School of Studies
More informationEconomics 241B Relation to Method of Moments and Maximum Likelihood OLSE as a Maximum Likelihood Estimator
Ecoomics 24B Relatio to Method of Momets ad Maximum Likelihood OLSE as a Maximum Likelihood Estimator Uder Assumptio 5 we have speci ed the distributio of the error, so we ca estimate the model parameters
More informationTopic 9: Sampling Distributions of Estimators
Topic 9: Samplig Distributios of Estimators Course 003, 2018 Page 0 Samplig distributios of estimators Sice our estimators are statistics (particular fuctios of radom variables), their distributio ca be
More informationLecture 7: Properties of Random Samples
Lecture 7: Properties of Radom Samples 1 Cotiued From Last Class Theorem 1.1. Let X 1, X,...X be a radom sample from a populatio with mea µ ad variace σ
More informationAnalysis of Experimental Data
Aalysis of Experimetal Data 6544597.0479 ± 0.000005 g Quatitative Ucertaity Accuracy vs. Precisio Whe we make a measuremet i the laboratory, we eed to kow how good it is. We wat our measuremets to be both
More informationTopic 9: Sampling Distributions of Estimators
Topic 9: Samplig Distributios of Estimators Course 003, 2016 Page 0 Samplig distributios of estimators Sice our estimators are statistics (particular fuctios of radom variables), their distributio ca be
More informationSimilarity Solutions to Unsteady Pseudoplastic. Flow Near a Moving Wall
Iteratioal Mathematical Forum, Vol. 9, 04, o. 3, 465-475 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/0.988/imf.04.48 Similarity Solutios to Usteady Pseudoplastic Flow Near a Movig Wall W. Robi Egieerig
More informationG. R. Pasha Department of Statistics Bahauddin Zakariya University Multan, Pakistan
Deviatio of the Variaces of Classical Estimators ad Negative Iteger Momet Estimator from Miimum Variace Boud with Referece to Maxwell Distributio G. R. Pasha Departmet of Statistics Bahauddi Zakariya Uiversity
More informationComparing Two Populations. Topic 15 - Two Sample Inference I. Comparing Two Means. Comparing Two Pop Means. Background Reading
Topic 15 - Two Sample Iferece I STAT 511 Professor Bruce Craig Comparig Two Populatios Research ofte ivolves the compariso of two or more samples from differet populatios Graphical summaries provide visual
More informationCHAPTER 10 INFINITE SEQUENCES AND SERIES
CHAPTER 10 INFINITE SEQUENCES AND SERIES 10.1 Sequeces 10.2 Ifiite Series 10.3 The Itegral Tests 10.4 Compariso Tests 10.5 The Ratio ad Root Tests 10.6 Alteratig Series: Absolute ad Coditioal Covergece
More informationResampling Methods. X (1/2), i.e., Pr (X i m) = 1/2. We order the data: X (1) X (2) X (n). Define the sample median: ( n.
Jauary 1, 2019 Resamplig Methods Motivatio We have so may estimators with the property θ θ d N 0, σ 2 We ca also write θ a N θ, σ 2 /, where a meas approximately distributed as Oce we have a cosistet estimator
More informationThe target reliability and design working life
Safety ad Security Egieerig IV 161 The target reliability ad desig workig life M. Holický Kloker Istitute, CTU i Prague, Czech Republic Abstract Desig workig life ad target reliability levels recommeded
More informationBinomial Distribution
0.0 0.5 1.0 1.5 2.0 2.5 3.0 0 1 2 3 4 5 6 7 0.0 0.5 1.0 1.5 2.0 2.5 3.0 Overview Example: coi tossed three times Defiitio Formula Recall that a r.v. is discrete if there are either a fiite umber of possible
More informationLinear regression. Daniel Hsu (COMS 4771) (y i x T i β)2 2πσ. 2 2σ 2. 1 n. (x T i β y i ) 2. 1 ˆβ arg min. β R n d
Liear regressio Daiel Hsu (COMS 477) Maximum likelihood estimatio Oe of the simplest liear regressio models is the followig: (X, Y ),..., (X, Y ), (X, Y ) are iid radom pairs takig values i R d R, ad Y
More informationPOWER COMPARISON OF EMPIRICAL LIKELIHOOD RATIO TESTS: SMALL SAMPLE PROPERTIES THROUGH MONTE CARLO STUDIES*
Kobe Uiversity Ecoomic Review 50(2004) 3 POWER COMPARISON OF EMPIRICAL LIKELIHOOD RATIO TESTS: SMALL SAMPLE PROPERTIES THROUGH MONTE CARLO STUDIES* By HISASHI TANIZAKI There are various kids of oparametric
More informationEXAMINATIONS OF THE ROYAL STATISTICAL SOCIETY
EXAMINATIONS OF THE ROYAL STATISTICAL SOCIETY GRADUATE DIPLOMA, 016 MODULE : Statistical Iferece Time allowed: Three hours Cadidates should aswer FIVE questios. All questios carry equal marks. The umber
More informationImproved Class of Ratio -Cum- Product Estimators of Finite Population Mean in two Phase Sampling
Global Joural of Sciece Frotier Research: F Mathematics ad Decisio Scieces Volume 4 Issue 2 Versio.0 Year 204 Type : Double Blid Peer Reviewed Iteratioal Research Joural Publisher: Global Jourals Ic. (USA
More informationPREDICTION INTERVALS FOR FUTURE SAMPLE MEAN FROM INVERSE GAUSSIAN DISTRIBUTION
Qatar Uiv. Sci. J. (1991), 11: 19-26 PREDICTION INTERVALS FOR FUTURE SAMPLE MEAN FROM INVERSE GAUSSIAN DISTRIBUTION By MUHAMMAD S. ABU-SALIH ad RAFIQ K. AL-BAITAT Departmet of Statistics, Yarmouk Uiversity,
More informationBayesian Methods: Introduction to Multi-parameter Models
Bayesia Methods: Itroductio to Multi-parameter Models Parameter: θ = ( θ, θ) Give Likelihood p(y θ) ad prior p(θ ), the posterior p proportioal to p(y θ) x p(θ ) Margial posterior ( θ, θ y) is Iterested
More informationIssues in Study Design
Power ad Sample Size: Issues i Study Desig Joh McGready Departmet of Biostatistics, Bloomberg School Lecture Topics Re-visit cocept of statistical power Factors ifluecig power Sample size determiatio whe
More informationStat 421-SP2012 Interval Estimation Section
Stat 41-SP01 Iterval Estimatio Sectio 11.1-11. We ow uderstad (Chapter 10) how to fid poit estimators of a ukow parameter. o However, a poit estimate does ot provide ay iformatio about the ucertaity (possible
More informationA New Multivariate Markov Chain Model with Applications to Sales Demand Forecasting
Iteratioal Coferece o Idustrial Egieerig ad Systems Maagemet IESM 2007 May 30 - Jue 2 BEIJING - CHINA A New Multivariate Markov Chai Model with Applicatios to Sales Demad Forecastig Wai-Ki CHING a, Li-Mi
More informationMinimax Estimation of the Parameter of Maxwell Distribution Under Different Loss Functions
America Joural of heoretical ad Applied Statistics 6; 5(4): -7 http://www.sciecepublishiggroup.com/j/ajtas doi:.648/j.ajtas.654.6 ISSN: 6-8999 (Prit); ISSN: 6-96 (Olie) Miimax Estimatio of the Parameter
More informationThe standard deviation of the mean
Physics 6C Fall 20 The stadard deviatio of the mea These otes provide some clarificatio o the distictio betwee the stadard deviatio ad the stadard deviatio of the mea.. The sample mea ad variace Cosider
More informationConfidence Interval for Standard Deviation of Normal Distribution with Known Coefficients of Variation
Cofidece Iterval for tadard Deviatio of Normal Distributio with Kow Coefficiets of Variatio uparat Niwitpog Departmet of Applied tatistics, Faculty of Applied ciece Kig Mogkut s Uiversity of Techology
More informationt distribution [34] : used to test a mean against an hypothesized value (H 0 : µ = µ 0 ) or the difference
EXST30 Backgroud material Page From the textbook The Statistical Sleuth Mea [0]: I your text the word mea deotes a populatio mea (µ) while the work average deotes a sample average ( ). Variace [0]: The
More informationDiscriminating between Generalized Exponential and Gamma Distributions
Joural of Probability ad Statistical Sciece 4, 4-47, Aug 6 Discrimiatig betwee Geeralized Expoetial ad Gamma Distributios Orawa Supapueg Kamo Budsaba Adrei I Volodi Praee Nilkor Thammasat Uiversity Uiversity
More informationRecurrence Relations
Recurrece Relatios Aalysis of recursive algorithms, such as: it factorial (it ) { if (==0) retur ; else retur ( * factorial(-)); } Let t be the umber of multiplicatios eeded to calculate factorial(). The
More informationII. Descriptive Statistics D. Linear Correlation and Regression. 1. Linear Correlation
II. Descriptive Statistics D. Liear Correlatio ad Regressio I this sectio Liear Correlatio Cause ad Effect Liear Regressio 1. Liear Correlatio Quatifyig Liear Correlatio The Pearso product-momet correlatio
More informationRandom Variables, Sampling and Estimation
Chapter 1 Radom Variables, Samplig ad Estimatio 1.1 Itroductio This chapter will cover the most importat basic statistical theory you eed i order to uderstad the ecoometric material that will be comig
More informationA Note on Box-Cox Quantile Regression Estimation of the Parameters of the Generalized Pareto Distribution
A Note o Box-Cox Quatile Regressio Estimatio of the Parameters of the Geeralized Pareto Distributio JM va Zyl Abstract: Makig use of the quatile equatio, Box-Cox regressio ad Laplace distributed disturbaces,
More informationANALYSIS OF EXPERIMENTAL ERRORS
ANALYSIS OF EXPERIMENTAL ERRORS All physical measuremets ecoutered i the verificatio of physics theories ad cocepts are subject to ucertaities that deped o the measurig istrumets used ad the coditios uder
More information