IOSR Journal of Mathematics (IOSR-JM) vol.11 issue.1 version.2

© All Rights Reserved

6 views

IOSR Journal of Mathematics (IOSR-JM) vol.11 issue.1 version.2

© All Rights Reserved

- tmp1413.tmp
- An introduction to Bayesian methods for analyzing chemistry data Part 2.pdf
- gamma distribution in hydrology
- JQT - Planned Replacement - Some Theory and Its Application
- Logistic Parameters Estimation
- ch02
- A Space–Time Conditional Intensity Model for Evaluating a Wildﬁre Hazard Index
- Minitab Demo-Competing Causes
- Fault Localization Using Bayesian Belief Network(BBN)_new
- 1 ARCH Model 80 Pages
- CT3_Sol_0511.pdf
- li15f
- Risk Cube Method to Derive Cost Risk
- IE 211 Syllabus 2018-2019A
- 1-s2.0-S0164070411000413-main
- Recording Process110515
- Diversidad Mamniferos vs. Hidro Electricas 2019ABC_42-1_pp_99-112
- TR-514
- Validate
- ai_unit-4

You are on page 1of 10

e-ISSN: 2278-5728, p-ISSN: 2319-765X. Volume 11, Issue 1 Ver. II (Jan - Feb. 2015), PP 24-33

www.iosrjournals.org

Kipkoech W. Cheruiyot1, Abel Ouko2, Emily Kirimi3

1

Department of Mathematics and Physical Sciences

2

The East African University, Kenya

Department of Mathematics

3

Technical University of Kenya

Department of Mathematics and Statistics

Abstract: In this paper, Bayesian estimation using diffuse (vague) priors is carried out for the parameters of a

two parameter Weibull distribution. Expressions for the marginal posterior densities in this case are not

available in closed form. Approximate Bayesian methods based on Lindley (1980) formula and Tierney and

Kadane (1986) Laplace approach are used to obtain expressions for posterior densities. A comparison based on

posterior and asymptotic variances is done using simulated data. The results obtained indicate that, the

posterior variances for scale parameter obtained by Laplace method are smaller than both the Lindley

approximation and asymptotic variances of their MLE counterparts.

Keywords: Weibull distribution, Lindley approximation, Laplace approximation, Maximum Likelihood

Estimates

I.

Introduction

The Weibull distribution is one of the most widely used distributions in reliability and survival analysis

because of various shapes assumed by the probability density functions (p.d.f) and the hazard function. The

Weibull distribution has been used effectively in analyzing lifetime data particularly when the data are censored

which is very common in survival data and life testing experiments. The Weibull distribution was derived from

the problem of material strength and it has been widely used as a lifetime model. Weibull distribution

corresponds to a family of distribution that covers a wide range of distributions that goes from the normal model

to the exponential model making it applicable in different areas for instance in fatigue life, strength of materials,

genetic research, quality control and reliability analysis. The probability density function (p.d.f) for the two

parameter Weibull distribution is given by

x

fT ( x, , )

II.

exp

x0

(1.1)

Let X1 , X 2 ,..., X n be independent random samples of size n from Weibull distribution with the p.d.f given by

(1.1). Differentiating with respect to

and

n

n

n

dl

x

x

0 n ln ln( xi ) ( i ) ln( i ) 0

d

i

i 1

n n xi

dl

( ) 0

0

i 1

d

(2.1)

(2.2)

as

1 n

x

n i i

(2.3)

DOI: 10.9790/5728-11122433

only as given by

www.iosrjournals.org

24 | Page

x ln x

i

i 1

x

i 1

1 n

ln xi

n i 1

(2.4)

The asymptotic variance-covariance matrix of and are obtained by inverting information matrix with

elements that are negatives of expected values of second order derivatives of logarithms of the likelihood

functions. Cohen (1965) suggested that in the present situation it is appropriate to approximate the expected

values by their maximum likelihood estimates. Accordingly, we have as the approximate variance-covariance

matrix with elements

1

2l

2

2l

When

and

2l

var(

)

cov(

2l

2

cov( ) var( )

When

2

var( ) 2

n

III.

Let X1 , X 2 ,..., X n be a random sample from a population with a two parameter Weibull distribution given by

f (x / , ) =

x 1

x

( ) exp {-( ) }

(3.1)

n

L( , ; x) n n xi 1 exp{ ( i ) }

x

i 1

i 1

n

i 1

i 1

x

Suppose that we are ignorant about the parameters ( , ) so that the diffuse (vague) prior used is

( , )

(3.2)

g ( , / x) L( x / ) ( , )

n

1 n n n

x

g ( , / x)

exp{

( i ) }

i 1

i 1

The marginal p.d.f of x is given by

f ( x)

x

n n

0 1 exp{ ( ) }d d

i

i 1

posterior expectations of and as

DOI: 10.9790/5728-11122433

(3.3)

i 1

and

are

(3.4)

www.iosrjournals.org

25 | Page

E ( / x) g ( / x)

L( x / ) ( )

L( x / ) ( )

(3.5)

and

E ( / x) g ( / x)

L( x / ) ( )

L( x / ) ( )

(3.6)

respectively

Since the Bayes estimate for and involve evaluating ratios of two mathematically intractable integrals,

appropriate Bayesian approximations are applied. Assuming is known, the likelihood function for is given

by

n

L( x / ) n exp{ ( i ) }

x

i 1

(3.7)

is given by

n

l log L n log ( i )

x

i 1

Since

is given by

1

( )

is given by

g ( / x) L( x / ) ( )

n

1

g ( / x) ( ) n exp{ xi }

i 1

is obtained by

E ( / x) g ( / x)d

E ( / x)

L( x / ) ( )

(3.8)

L( x / ) ( )

Since the Bayes estimate of involve ratio of two mathematically intractable integrals, Tierney and Kadane,

(1986) proposed to estimate (3.8) as follows

e

E ( / x)

e

nL

nL

(3.9)

where

L log ( )

l

n

n

1

x

log( ) log 1n ( i )

(3.10)

i 1

and

L log ( ) log

DOI: 10.9790/5728-11122433

l

n

www.iosrjournals.org

26 | Page

n

1

x

log log( ) log 1n ( i )

(3.11)

i 1

of L is obtained by differentiating L with respect to once and equating to zero, that is,

dL

0

d

1

n

( ) 0

xi

i 1

Giving

in terms of as

1

xi

n(1 ) i 1

to zero to get

1

n

(3.12)

and equating

( )

xi

i 1

( x ) 0

n i 1

n

Giving

in terms of as

1

1 n

xi

n i 1

The and

mode given by

2

(3.13)

are equal to the minus the inverse of the second derivative of the log posterior density at its

L" ( )

d 2 L 1 ( 1) n xi

2

( )

d 2

n 2 i 1

1 ( 1) n xi

L" ( ) 2

( )

n 2 i 1

Hence

2

n

n ( 1) xi

i 1

2

1

( 1)

(3.14)

Also

d 2 L

d 2

n ( 1) xi

12

DOI: 10.9790/5728-11122433

i 1

( 2)

L" ( )

www.iosrjournals.org

27 | Page

2

12

1 n

n xi

i 1

(3.15)

E ( / x) ( ) exp{n( L ( ) L( ))}

(3.16)

where

1

xi

n(1 ) i 1

and

1

1 n

xi

n i 1

2

L( x / ) ( )

2

E ( / x)

L( x / ) ( )

E (

e

/ x)

e

nL

nL

(3.17)

where

1

1 n x

L log( ) log ( i )

n i 1

and

1

1 n x

L log 2 log( ) log ( i )

n i 1

1

1

x

i

n(1 ) i 1

(3.18)

and

1

1

x

i

n( 1) i 1

(3.19)

respectively

The

1

12

L" ( )

1 ( 1) n xi

L" ( ) 2

( )

n 2 i 1

Hence

DOI: 10.9790/5728-11122433

www.iosrjournals.org

28 | Page

2

n

n ( 1) xi

i 1

2

1

( 1)

(3.20)

And

12

L1" ( )

1 ( 1) n xi

L1"

( )

n 2 i 1

Hence

2

12

x

n( 1) i

i 1

( 1)

(3.21)

(3.22)

is

V ( / x) E ( 2 / x) [ E ( / x)]2

(3.23)

Lindley (1980) developed a multidimensional linear Bayes estimate of an arbitrary function as an

approximation of an asymptotic expansion of the ratio of two integrals which cannot be expressed in a closed

form given by

E U ( ) / x

U ( )V ( ) exp L( ) d

V ( ) exp L( ) d

Expanding L( ) and U ( ) V ( ) by Taylors series about the MLE of , Lindley (1980) Bayesian

approximation of two parameter case is given by

1

1

E U ( ) / x U (U ij 2U j j ) Lijkl ijklU terms of order n 2 and smaller.

2 i j

2 i j k l

1

U U11 11 U12 12 U 21 21 U 22 22 1 U1 11 U 2 21 2 U 2 22 U1 12

2

2

2

2

1 L30 (U1 11 U 2 11 12 ) L21[3U1 11 12 U 2 ( 11 22 2 12 )] L12 [3U 2 22 21 U1 ( 22 11 2 21 )]

(3.24)

(see, Lindley, 1980). For two parameter Weibull distribution we have,

( , ) is ( , )

( ) log V ( ) log ( )

i j L

Lij

i j

U

U

2U

Ui

; Uj

and Uij

The MLE of

DOI: 10.9790/5728-11122433

www.iosrjournals.org

29 | Page

ij (i, j )th

( , ), i, j 1, 2

The quantities Lij ' s are the higher order derivatives of log-likelihood function given by

l

n n xi

( ) L10

i 1

(3.25)

l n ( 1)

2 2 ( xi ) L20

2

i 1

2

(3.26)

l

2n

3 ( 1)(3 2) ( xi ) L30

3

i 1

3

(3.27)

l

n

( xi ) ln( xi ) 1 ( xi ) L11

i 1

i 1

2

(3.28)

l

n

2 2 ( xi ) (21) ( xi ) ln( xi ) ( 21) ( xi ) L21

2

i 1

i 1

i 1

3

(3.29)

l

2

2 ( xi ) 42 ( xi ) ln( xi ) 22 ( xi ) ln( xi ) 2 ( xi ) ln( xi ) 2 ( xi ) ln( xi ) L22

2

2

i 1

i 1

i 1

i 1

i 1

4

l

n

2 ( xi ) ln( xi )

2

i 1

L02

(3.32)

(3.31)

3

3l 2n n xi

xi

ln(

)

L03

3 3 i 1

n

n

2

3l

xi

xi

xi

xi

(

)

ln(

)

( ) ln( ) L12

2

i 1

i 1

(3.30)

n

n

l n

x

x

n ln ln( xi ) ( i ) ln( i ) L01

i

i

2

(3.33)

(3.34)

L

I 20

L11

L11

L02

Thus

I 1

L20

1

L11 11 12

L02 21 22

(3.35)

where

n

n

n n

x

L20 L02 L11L11 2 (21) ( i ) 2

i 1

i 1

xi

2

n n xi xi 1 n xi

(ln( )) ( ) ln( ) ( )

i 1

i 1

xi

Next, we have

log ( ) ln( )

Hence

1

Since

is known, we let

and 2

DOI: 10.9790/5728-11122433

www.iosrjournals.org

30 | Page

such that

1 ; U2

0 and U ij 0 ; i,j=1,2

The quantities Lij ' s are the higher order derivatives of log-likelihood function. Because is known, the

U1

l

2n

x

3 ( 1)(3 2) ( i ) L30

3

i 1

3

ij (i, j )th

is obtained by inverting minus second derivative of log likelihood function with respect to

evaluated at ( ), i 1, 2

Therefore, Bayes estimate of using (3.24) is given by

1

E ( / x) 11 L30 112

2

Then

(3.36)

E ( 2 / x) 2 2 11 L30 112 11

(3.37)

is given by

Var ( / x) E 2 / x E ( / x)

IV.

(3.38)

Results

Simulation experiments were carried out using R software to compare the performance of the Bayes

and MLE estimates of the two parameter Weibull distribution. We assumed the shape parameter is known.

We performed simulation experiment with different sample sizes (10, 30, 50 and 100), drawn from a Weibull

distribution for different values of shape parameter (1, 1.5, 2, 2.5, 3, 3.5, 4, 4.5, 5, 5.5 and 6). We specified

the true value of the scale parameter to be fixed at one ( 1) for all the sample sizes. We computed

estimates based on two different Bayesian methods, that is, Tierney and Kadane, (1986) Laplace approximation

method, Lindley (1980) approximation and the method of Maximum likelihood estimation.

DOI: 10.9790/5728-11122433

www.iosrjournals.org

1

31 | Page

Figure 4: Graph of variance for sample size 100 against values of Lambda ( ).

DOI: 10.9790/5728-11122433

www.iosrjournals.org

32 | Page

V.

Discussions

Figure 1 show the estimates of under varying size of , Bayes estimates obtained by Lindley (1980)

and Tierney and Kadane, (1986) Laplace approximation are found to be larger than the MLE counter parts.

Lindley (1980) approximation is found to overestimate the scale parameter ; however the three methods

demonstrate the tendency for their estimates and variances to perform better for larger sample size. This is

shown in Figure 2 when the sample size is increased to 100. As the sample size increases the MLE and Bayes

estimates becomes more consistent and accurate.

Figure 3 show the variances of the estimates of for varying size of shape parameter for a sample of

10. It is observed that posterior variances of estimates of are smaller than the asymptotic variances of MLE

hence more precise and accurate. However, both variances tend to converge to zero as the value of get larger.

For the sample of 10 Tierney and Kadane, (1986) Laplace approximation is seen to perform slightly better than

Lindley (1980), since it stabilizes faster.

Figure 4 show that Tierney and Kadane, (1986) Laplace approximation performed better for larger

sample of 100. The variance of MLE are observed to stabilize faster when the sample size and shape parameter

increase.

It is also observed that the Bayesian method generally performed better for both small and larger value

of than the MLE counter parts. Lindley (1980) and Laplace methods tend to perform almost similarly for

smaller . But the Tierney and Kadane, (1986) Laplace approximation is found to produce better results than

both MLE and Lindley (1980) for larger

VI.

Conclusion

We have shown Bayesian techniques for estimating the scale parameter of the two parameter Weibull

distribution which produces estimates with smaller variances than the MLE. Tierney and Kadane, (1986)

Laplace approximation which requires the second derivatives in its computation is found to be more accurate

than the Lindley (1980) which requires third derivatives in its computation. This is in line with Tierney et al

(1989) findings, that Laplace method is more accurate than the third derivative method of Lindley (1980). Even

though the two Bayesian methods are better than the MLE counter parts, they have their own limitations.

Lindley (1980) approximation requires existence of MLE in its computation. This appears as if it is an

adjustment to the MLE to reduce variability. On the other hand, Laplace approximation requires existence of a

unimodal distribution in its computation, hence difficult to use in cases of a multi modal distribution.

VII.

Recommendation

In this study, it is noted that the posterior variances of Bayes estimates are smaller than asymptotic

variances. Comparing the two Bayesian methods, Tierney and Kadane, (1986) Laplace approximation method

has smaller variance than the Lindley (1980) approximation technique hence more precise and accurate. Laplace

approximation does not require explicit third order derivatives in its computation which are required in Lindley

(1980) approximation method hence simple to compute. We therefore recommend further work to be done on

two parameter Weibull distribution when both scale and shape parameters are unknown to investigate accuracy

of the two Bayesian methods.

References

[1].

[2].

[3].

[4].

Cohen, A.C. (1965): Maximum Likelihood Estimation in the Weibull Distribution Based on Complete and Censored Samples.

Technometrics, 7, 579-588.

Lindley, D.V. (1980). Approximate Bayesian Method, Trabajos Estadistica, 31, 223-237.

Tierney L, Kass, R.E. and Kadane, J.B. (1989): Fully exponential Laplace approximations to expectations and variances of nonpositive functions. Journal of American Statistical Association, 84, 710-716.

Tierney L. and Kadane, J.B. (1986): Accurate Approximations for Posterior Moments and Marginal Densities. Journal of American

Statistical Association, 81, 82-86.

DOI: 10.9790/5728-11122433

www.iosrjournals.org

33 | Page

- tmp1413.tmpUploaded byFrontiers
- An introduction to Bayesian methods for analyzing chemistry data Part 2.pdfUploaded bydiana fenichiu
- gamma distribution in hydrologyUploaded bysarkawt hamarahim muhammad
- JQT - Planned Replacement - Some Theory and Its ApplicationUploaded bybriandpc
- Logistic Parameters EstimationUploaded bySameer Al-Subh
- ch02Uploaded byLucky Chougale
- A Space–Time Conditional Intensity Model for Evaluating a Wildﬁre Hazard IndexUploaded byrdpeng
- Minitab Demo-Competing CausesUploaded byJason Chen
- Fault Localization Using Bayesian Belief Network(BBN)_newUploaded byBhaskar Roy
- 1 ARCH Model 80 PagesUploaded byPuPu Shing Shing
- CT3_Sol_0511.pdfUploaded byeuticus
- li15fUploaded bygassun2999
- Risk Cube Method to Derive Cost RiskUploaded byPreuz
- IE 211 Syllabus 2018-2019AUploaded byJoe Ramos
- 1-s2.0-S0164070411000413-mainUploaded byAfrishiyan Dhita Ratu Hanura
- Recording Process110515Uploaded byvincenzoferrazzano
- Diversidad Mamniferos vs. Hidro Electricas 2019ABC_42-1_pp_99-112Uploaded byPaula Andrea Paz
- TR-514Uploaded byHida Q
- ValidateUploaded byLuis Castillo
- ai_unit-4Uploaded byGanesh Kumar
- push pullUploaded byYanie Suhaili
- resm2015.30me1205Uploaded bykhudhayer1970
- SessionVUploaded byoshka
- A_DTestUploaded byjcamero
- Chapter 1Uploaded byusman446
- chap 01Uploaded byTahir Naeem Jatt
- probabilityandstatisticsprojectUploaded byapi-252908727
- Averaging Ratios: Characteristics of the Error of ApproximationUploaded byTI Journals Publishing
- Math.pdfUploaded byMagdalena Medrzycki
- StsUploaded byAdji Prasetyo

- Effects of Formative Assessment on Mathematics Test Anxiety and Performance of Senior Secondary School Students in Jos, NigeriaUploaded byInternational Organization of Scientific Research (IOSR)
- Study the Changes in Al-ahwaz Marshal using Principal Component Analysis and Classification TechniqueUploaded byInternational Organization of Scientific Research (IOSR)
- The Effect of Instructional Methods and Locus of Control on Students’ Speaking Ability (An Experimental Study in State Senior High School 01, Cibinong Bogor, West Java)Uploaded byInternational Organization of Scientific Research (IOSR)
- Philosophical Analysis of the Theories of Punishment in the Context of Nigerian Educational SystemUploaded byInternational Organization of Scientific Research (IOSR)
- Comparison of Psychological Variables within different positions of players of the state Junior boys ball Badminton players of ManipurUploaded byInternational Organization of Scientific Research (IOSR)
- Comparison of Explosive Strength between Football and Volley Ball Players of Jamboni BlockUploaded byInternational Organization of Scientific Research (IOSR)
- Necessary Evils of Private Tuition: A Case StudyUploaded byInternational Organization of Scientific Research (IOSR)
- Project Based Learning Tools Development on Salt Hydrolysis Materials through Scientific ApproachUploaded byInternational Organization of Scientific Research (IOSR)
- Microencapsulation for Textile FinishingUploaded byInternational Organization of Scientific Research (IOSR)
- Geohydrological study of weathered basement aquifers in Oban Massif and environs Southeastern Nigeria: using Remote Sensing and Geographic Information System TechniquesUploaded byInternational Organization of Scientific Research (IOSR)
- Students’ Perceptions of Grammar Teaching and Learning in English Language Classrooms in LibyaUploaded byInternational Organization of Scientific Research (IOSR)
- Enhancing Pupils’ Knowledge of Mathematical Concepts through Game and PoemUploaded byInternational Organization of Scientific Research (IOSR)
- Factors Affecting Success of Construction ProjectUploaded byInternational Organization of Scientific Research (IOSR)
- Development of Dacum as Identification Technique on Job Competence Based-Curriculum in High Vocational EducationUploaded byInternational Organization of Scientific Research (IOSR)
- Youth Entrepreneurship: Opportunities and Challenges in IndiaUploaded byInternational Organization of Scientific Research (IOSR)
- Child Mortality among Teenage Mothers in OJU MetropolisUploaded byInternational Organization of Scientific Research (IOSR)
- Core Components of the Metabolic Syndrome in Nonalcohlic Fatty Liver DiseaseUploaded byInternational Organization of Scientific Research (IOSR)
- Auxin induced germination and plantlet regeneration via Rhizome section culture in Spiranthes sinensis (Pers.) Ames: A Vulnerable medicinal Orchid of Kashmir HimalayaUploaded byInternational Organization of Scientific Research (IOSR)
- Need of Non- Technical Content in Engineering EducationUploaded byInternational Organization of Scientific Research (IOSR)
- Comparison of Selected Anthropometric and Physical Fitness Variables between Offencive and Defencive Players of Kho-KhoUploaded byInternational Organization of Scientific Research (IOSR)
- Parametric Optimization of Single Cylinder Diesel Engine for Specific Fuel Consumption Using Palm Seed Oil as a BlendUploaded byInternational Organization of Scientific Research (IOSR)
- Mathematical Modeling of SFC Using RSM for CI Engine Fuled with Soybean Biodiesel and Diesel BlendUploaded byInternational Organization of Scientific Research (IOSR)
- Study of Effect of Rotor Speed, Combing-Roll Speed and Type of Recycled Waste on Rotor Yarn Quality Using Response Surface MethodologyUploaded byInternational Organization of Scientific Research (IOSR)
- Advancing Statistical Education using Technology and Mobile DevicesUploaded byInternational Organization of Scientific Research (IOSR)
- Lipoproteins and Lipid Peroxidation in Thyroid disordersUploaded byInternational Organization of Scientific Research (IOSR)
- Research Analysis on Sustainability Opportunities and Challenges of Bio-Fuels Industry in IndiaUploaded byInternational Organization of Scientific Research (IOSR)
- Application of Xylanase produced by Bacillus megaterium in Saccharification, Juice clarification and oil extraction from Jatropha seed kernelUploaded byInternational Organization of Scientific Research (IOSR)
- Comparative Effect of Daily Administration of Allium sativum and Allium cepa Extracts on Alloxan Induced Diabetic RatsUploaded byInternational Organization of Scientific Research (IOSR)
- A Review on Refrigerants, And Effects on Global Warming For Making Green EnvironmentUploaded byInternational Organization of Scientific Research (IOSR)
- Investigation of Wear Loss in Aluminium Silicon Carbide Mica Hybrid Metal Matrix CompositeUploaded byInternational Organization of Scientific Research (IOSR)

- Simple RegressionUploaded byKhawaja Naveed Haider
- Carver and Miller, 2006, Relations of Serotonin Function to Personality - Current Views and a Key Methodological IssueUploaded byDiana Chen
- Key Instruction WordsUploaded bydinhchungxd
- Predictive Modeling Sample ProgramUploaded bysiva5256
- HRM NOTES.docxUploaded byshashankgulati
- Centre of Pressure Lab Report TemplateUploaded byVv4H
- Pios Goi Mhrd as May 25 2017Uploaded byAnonymous n4UccmT6q
- Hooke Law ExperimentUploaded byCgzam Zam
- ADA502182.pdfUploaded bycofs.ranger5788
- Skull Colleen 201306 DMA ThesisUploaded byMiguel Barata Gonçalves
- 10th-english-socialscience -1.pdfUploaded bysatyandhra kumar
- sugar skull lessonUploaded byapi-233374589
- Chapter 11-12 Org 301Uploaded byXXXX
- stewart sccm hfov poster 2016 finalUploaded byapi-260357356
- Effective Advertising and Its Influence on Consumer BuyingUploaded byLouana David
- Leadership.pdfUploaded byShantanu Nanda
- TEXT MINING: PROMISES AND CHALLENGESUploaded byNining Suryani
- Handout_10279_OG10279-Point Cloud to AutoCAD Plant 3DUploaded byvivek
- Handout - Are We Fulfilling Our PromiseUploaded byCharles Rei
- THE-AID-OF-STUDYING-SPECIALIZED-SUBJECTS-FOR-GRADE-12-GAS-STUDENTS-OF-CARLOS-F.-GONZALES-HIGH-SCHOOL.docxUploaded byThedy Luctu Pacheco
- Writing Phrases.docxUploaded byLucía Nina
- Control Chart ReviewUploaded byDr.Raj Mohan
- Occup Med (Lond) 2009 Drayton 135 6Uploaded byNeuroPsychology
- Introduction to Consumer BehaviourUploaded bySujata Mansukhani
- Process Validation of Polyherbal Cough Syrup FormulationUploaded byBhavesh Nayak
- Competitive AnalysisUploaded byAmanda Farias
- cochrane risk of bias tool 1.pdfUploaded byRadhikaManam
- Project Perspectives 2011Uploaded bywhynot08
- Dev Raj ThakurUploaded byKunal Kumar
- Stress of Result and Time Shortage Leads to PlagiarismUploaded byaahmed93