Help for package minque

Type:

Package

Title:

Various Linear Mixed Model Analyses

Version:

2.0.0

Author:

Jixiang Wu

Maintainer:

Jixiang Wu <jixiang.wu@sdstate.edu>

Description:

This package offers three important components: (1) to construct a use-defined linear mixed model, (2) to employ one of linear mixed model approaches: minimum norm quadratic unbiased estimation (MINQUE) (Rao, 1971) for variance component estimation and random effect prediction; and (3) to employ a jackknife resampling technique to conduct various statistical tests. In addition, this package provides the function for model or data evaluations.This R package offers fast computations for large data sets analyses for various irregular data structures.

License:

GPL-3

Encoding:

UTF-8

LazyData:

yes

RoxygenNote:

7.0.2

NeedsCompilation:

Packaged:

2019-12-19 20:44:17 UTC; Jixiang.Wu

Repository:

CRAN

Date/Publication:

2019-12-19 22:00:06 UTC

Various Linear Mixed Model Analyses

Description

This package offers three important components: (1) to construct a use-defined linear mixed model, (2) to employ one of linear mixed model approaches: minimum norm quadratic unbiased estimation (MINQUE) (Rao, 1971) for variance component estimation and random effect prediction;(3) to employ a jackknife resampling technique to conduct various statistical tests; and (4) to conduct various model evaluations. This R package offers fast computations for large data sets analyses for various irregular data structures.

Details

Package:	minque
Type:	Package
Version:	2.0
Date:	2019-12-18
License:	GPL-3

An overview of how to use the package, including the most important functions

Author(s)

Jixiang Wu, Associate Professor of Quantitative Genetics/Biostatistics, \Jixiang Wu <jixiang.wu@sdstate.edu>

References

Miller, R. G. 1974. The jackknife - a review. Biometrika, 61:1- 15.

Patterson, H. D. and Thompson, R. 1971. Recovery of inter-block information when block sizes are unequal. Biometrika, 58: 545-554.

Rao, C.R. 1971. Estimation of variance and covariance components-MINQUE theory. J Multiva Ana 1:19

Rao, C. R. and Kleffe, J. 1980. Estimation of variance components. In Handbook of Statistics. Vol. l: 1-40. Krishnaiah, P. R. ed. New York. North-Holland.

Searle, S. R., Casella, G. and McCulloch, C. E. 1992. Variance Components. John Wiley & Sons, Inc. New York.

Wu J (2012) GenMod: An R package for various agricultural data analyses. ASA, CSSA, and SSSA 2012 International Annual Meetings, Cincinnati, OH, p 127

Wu J., Bondalapati K., Glover K., Berzonsky W., Jenkins J.N., McCarty J.C. 2013. Genetic analysis without replications: model evaluation and application in spring wheat. Euphytica. 190:447-458

Zhu J. 1989. Estimation of Genetic Variance Components in the General Mixed Model. Ph.D. Dissertation, NC State University, Raleigh, U.S.A

Zhu J. 1993. Methods of predicting genotype value and heterosis for offspring of hybrids. (Chinese). Journal of Biomathematics, 8(1): 32-44

Cotton boll retention rate data

Description

This data set contains boll retention of 10 cotton plants for 5 genotypes and 13 nodes. This data set can be analyzed in many ways: factorial factor design (genotype and position) or as split-plot design. For example, this data set can be analyzed by user-defined model as shown in the example.

Usage

data(brate)

Format

A data frame with 338 observations on the following 5 variables.

Year: year of 2009
Geno: genotypes from 1 to 5
Pos: plant nodes from 5 to 17
Rep: field blocks from 1 to 4
Brate: mean boll retention for the first position over 10 plants

Details

No other details are needed

Source

No references or URLs available.

References

No reference available

Examples


 library(minque)

 data(brate)
 head(brate)
 brate$Geno=factor(brate$Geno)
 brate$Pos=factor(brate$Pos)
 brate$Rep=factor(brate$Rep)

 res=lmm(Brate~1|Geno*Pos+Rep,data=brate)
 res$Var
 res$FixedEffect
 res$RandomEffect

 res=lmm.jack(Brate~1|Geno*Pos+Rep,data=brate,JacNum=10,JacRep=1,ALPHA=0.05)
 res$Var
 res$PVar
 res$FixedEffect
 res$RandomEffect
 ## end

Twenty four cotton genotypes with four agronomic traits

Description

Twentype four cotton genotypes were evaluated under two locations at the Mississippi State University Research Farm.

Usage

data(cot)

Format

A data frame with 288 observations on the following 7 variables.

LOC: location
Geno: genotypes
REP: field blocks
BN: Boll number
BS: Boll size
LP: Lint percentage
LY: Lint yield

Details

No other details are needed

Source

Not available

References

To be added

Examples

##Sample R codes used to analyze the data set: cot
 library(minque)
 data(cot)
 names(cot)
 cot$Geno=factor(cot$Geno)
 cot$Loc=factor(cot$LOC)
 cot$Rep=factor(cot$REP)

 res=lmm(LY~1|Geno*Loc+Loc:Rep,data=cot)
 res$Var
 res$FixedEffect
 res$RandomEffect

 res=lmm.jack(LY~1|Geno*Loc+Loc:Rep,data=cot,JacNum=10,JacRep=1,ALPHA=0.05)
 res$Var
 res$PVar
 res$FixedEffect
 res$RandomEffect



 ##End

An R function for linear mixed model analysis.

Description

An R function for linear mixed model analysis with REML and/or MINQUE approaches

Usage

lmm(formula,data = list(), method = NULL, ALPHA = NULL)

Arguments

formula

A linear mixed model formula.

data

Data frame. It can be default.

method

The default linear mixed model approach is MINQUE. Users can choose both or one of two linear mixed model approaches, REML and MINQUE.

ALPHA

A preset nominal probability level.

Details

No data frame is needed when more than one response variables are analyzed

Value

Return list of simulated results for variance components

Author(s)

Jixiang Wu <jixiang.wu@sdstate.edu>

References

Miller, R. G. 1974. The jackknife - a review. Biometrika, 61:1- 15.

Rao, C.R. 1971. Estimation of variance and covariance components-MINQUE theory. J Multiva Ana 1:19

Rao, C. R. and Kleffe, J. 1980. Estimation of variance components. In Handbook of Statistics. Vol. l: 1-40. Krishnaiah, P. R. ed. New York. North-Holland.

Searle, S. R., Casella, G. and McCulloch, C. E. 1992. Variance Components. John Wiley & Sons, Inc. New York.

Wu J (2012) GenMod: An R package for various agricultural data analyses. ASA, CSSA, and SSSA 2012 International Annual Meetings, Cincinnati, OH, p 127

Wu J., Bondalapati K., Glover K., Berzonsky W., Jenkins J.N., McCarty J.C. 2013. Genetic analysis without replications: model evaluation and application in spring wheat. Euphytica. 190:447-458

Zhu J. 1989. Estimation of Genetic Variance Components in the General Mixed Model. Ph.D. Dissertation, NC State University, Raleigh, U.S.A

Examples

  library(minque)
  data(ncii)
  res=lmm(Yld~1|Female*Male+Rep,data=ncii)
  res$Var
  res$FixedEffect
  res$RandomEffect
  #End

An R function to obtain information from a linear mixed model

Description

Sometimes users may need run some simulations for a given data structure and/or a model. This function will give users the information used for simulation.

Usage

lmm.check(formula, data = list())

Arguments

formula

A linear mixed model formula

data

A data frame used for modelling. It can be default

Value

Return the information that will be used to preset values for simulation

comp1

Number of variance components including one for random error

comp2

Names for all variance components not including the one for random error

comp3

Levels of effects for each fixed effect component

comp4

Names of all fixed effects

Author(s)

Jixiang Wu <jixiang.wu@sdstate.edu>

Examples


  library(minque)
  data(ncii)
  ncii$Female=factor(ncii$Female)
  lmm.inf=lmm.check(Yld~Female|Female*Male+Rep,data=ncii)
  lmm.inf

  #End

An R function for linear mixed model analysis

Description

An R function for linear mixed model analysis with integration two linear mixed model approaches (REML and MINQUE) and a jackknife technique.

Usage

lmm.jack(formula, data=list(),method = NULL, JacNum = NULL,
 JacRep = NULL, ALPHA = NULL)

Arguments

formula

A linear mixed model formula.

data

A data frame used for analysis,it can be default.

method

The default linear mixed model approach is MINQUE. Users can choose both or one of two linear mixed model approaches, REML and MINQUE.

JacNum

The groups of jackknife to be used. The default number is 10.

JacRep

The times of jackknife process being repeated. The default is 1

ALPHA

The nomial alpha value being used for statistical tests. The default value is 0.05

Value

Return a list of matrices each including mean estimated variance components, standard error, and power

Author(s)

Jixiang Wu <jixiang.wu@sdstate.edu>

References

Miller, R. G. 1974. The jackknife - a review. Biometrika, 61:1- 15.

Rao, C.R. 1971. Estimation of variance and covariance components-MINQUE theory. J Multiva Ana 1:19

Rao, C. R. and Kleffe, J. 1980. Estimation of variance components. In Handbook of Statistics. Vol. l: 1-40. Krishnaiah, P. R. ed. New York. North-Holland.

Searle, S. R., Casella, G. and McCulloch, C. E. 1992. Variance Components. John Wiley & Sons, Inc. New York.

Wu J (2012) GenMod: An R package for various agricultural data analyses. ASA, CSSA, and SSSA 2012 International Annual Meetings, Cincinnati, OH, p 127

Wu J., Bondalapati K., Glover K., Berzonsky W., Jenkins J.N., McCarty J.C. 2013. Genetic analysis without replications: model evaluation and application in spring wheat. Euphytica. 190:447-458

Zhu J. 1989. Estimation of Genetic Variance Components in the General Mixed Model. Ph.D. Dissertation, NC State University, Raleigh, U.S.A

Examples

  library(minque)
  data(ncii)
  res=lmm.jack(Yld~1|Female*Male+Rep,data=ncii,
     JacNum=10,JacRep=1,ALPHA=0.05)
  res$Var
  res$PVar
  res$FixedEffect
  res$RandomEffect
  #End

An R function for linear mixed model analysis and permutation test

Description

An R function for linear mixed model analysis with integration two linear mixed model approaches (REML and MINQUE) and a permutation test.

Usage

lmm.perm(formula, data = list(), method = NULL, PermNum = NULL)

Arguments

formula

A linear mixed model formula.

data

Data frame. It can be default.

method

The default linear mixed model approach is MINQUE. Users can choose both or one of two linear mixed model approaches, REML and MINQUE.

PermNum

Permutation number. The default number is 100

Value

Return a list of matrices each including mean estimated variance components, standard error, and power

Author(s)

Jixiang Wu <jixiang.wu@sdstate.edu>

References

Miller, R. G. 1974. The jackknife - a review. Biometrika, 61:1- 15.

Rao, C.R. 1971. Estimation of variance and covariance components-MINQUE theory. J Multiva Ana 1:19

Rao, C. R. and Kleffe, J. 1980. Estimation of variance components. In Handbook of Statistics. Vol. l: 1-40. Krishnaiah, P. R. ed. New York. North-Holland.

Searle, S. R., Casella, G. and McCulloch, C. E. 1992. Variance Components. John Wiley & Sons, Inc. New York.

Wu J (2012) GenMod: An R package for various agricultural data analyses. ASA, CSSA, and SSSA 2012 International Annual Meetings, Cincinnati, OH, p 127

Wu J., Bondalapati K., Glover K., Berzonsky W., Jenkins J.N., McCarty J.C. 2013. Genetic analysis without replications: model evaluation and application in spring wheat. Euphytica. 190:447-458

Zhu J. 1989. Estimation of Genetic Variance Components in the General Mixed Model. Ph.D. Dissertation, NC State University, Raleigh, U.S.A

Examples

  library(minque)
  data(ncii)
  res=lmm.perm(Yld~1|Female*Male+Rep,data=ncii)
  res
  #End

An R function for linear mixed model simulation.

Description

An R function for linear mixed model simulation with generated data set and a given model.

Usage

lmm.simu(formula, method = NULL, ALPHA = NULL)

Arguments

formula

A linear mixed model formula.

method

The default linear mixed model approach is MINQUE. Users can choose both or one of two linear mixed model approaches, REML and MINQUE.

ALPHA

A preset nominal probability level.

Details

No data frame is needed when more than one response variables are analyzed

Value

Return list of simulated results for variance components

Author(s)

Jixiang Wu <jixiang.wu@sdstate.edu>

References

Miller, R. G. 1974. The jackknife - a review. Biometrika, 61:1- 15.

Rao, C.R. 1971. Estimation of variance and covariance components-MINQUE theory. J Multiva Ana 1:19

Rao, C. R. and Kleffe, J. 1980. Estimation of variance components. In Handbook of Statistics. Vol. l: 1-40. Krishnaiah, P. R. ed. New York. North-Holland.

Searle, S. R., Casella, G. and McCulloch, C. E. 1992. Variance Components. John Wiley & Sons, Inc. New York.

Wu J (2012) GenMod: An R package for various agricultural data analyses. ASA, CSSA, and SSSA 2012 International Annual Meetings, Cincinnati, OH, p 127

Wu J., Bondalapati K., Glover K., Berzonsky W., Jenkins J.N., McCarty J.C. 2013. Genetic analysis without replications: model evaluation and application in spring wheat. Euphytica. 190:447-458

Zhu J. 1989. Estimation of Genetic Variance Components in the General Mixed Model. Ph.D. Dissertation, NC State University, Raleigh, U.S.A

Examples

  library(minque)
  data(ncii)

  lmm.inf=lmm.check(Yld~1|Female*Male+Rep,data=ncii)

  lmm.inf  ##there are five variance components
  v=c(20,20,20,20,20) ##there are five variance components
  b=as.vector(100)    ##there is only population mean as fixed effect
  Y=lmm.simudata(Yld~1|Female*Male+Rep,data=ncii,v=v,b=b,SimuNum=50)
  Female=factor(ncii$Female)
  Male=factor(ncii$Male)
  Rep=factor(ncii$Rep)
  res=lmm.simu(Y~1|Female*Male+Rep)
  res
  #End

An R function for linear mixed model simulation.

Description

An R function for linear mixed model simulation with integration two linear mixed model approaches (REML and MINQUE) and a jackknife technique.

Usage

lmm.simu.jack(formula, method = NULL, JacNum = NULL, JacRep = NULL, ALPHA = NULL)

Arguments

formula

A linear mixed model formula.

method

The default linear mixed model approach is MINQUE. Users can choose both or one of two linear mixed model approaches, REML and MINQUE.

JacNum

The groups of jackknife to be used. The default number is 10.

JacRep

The times of jackknife process being repeated. The default is 1

ALPHA

The nomial alpha value being used for statistical tests. The default value is 0.05

Value

Return a list of matrices each including mean estimated variance components, standard error, and power

Author(s)

Jixiang Wu <jixiang.wu@sdstate.edu>

References

Miller, R. G. 1974. The jackknife - a review. Biometrika, 61:1- 15.

Rao, C.R. 1971. Estimation of variance and covariance components-MINQUE theory. J Multiva Ana 1:19

Rao, C. R. and Kleffe, J. 1980. Estimation of variance components. In Handbook of Statistics. Vol. l: 1-40. Krishnaiah, P. R. ed. New York. North-Holland.

Searle, S. R., Casella, G. and McCulloch, C. E. 1992. Variance Components. John Wiley & Sons, Inc. New York.

Wu J (2012) GenMod: An R package for various agricultural data analyses. ASA, CSSA, and SSSA 2012 International Annual Meetings, Cincinnati, OH, p 127

Wu J., Bondalapati K., Glover K., Berzonsky W., Jenkins J.N., McCarty J.C. 2013. Genetic analysis without replications: model evaluation and application in spring wheat. Euphytica. 190:447-458

Zhu J. 1989. Estimation of Genetic Variance Components in the General Mixed Model. Ph.D. Dissertation, NC State University, Raleigh, U.S.A

Examples

  library(minque)
  data(ncii)

  lmm.inf=lmm.check(Yld~1|Female*Male+Rep,data=ncii)

  lmm.inf  ##there are five variance components
  v=c(20,20,20,20,20) ##there are five variance components
  b=as.vector(100)    ##there is only population mean as fixed effect
  Y=lmm.simudata(Yld~1|Female*Male+Rep,data=ncii,v=v,b=b,SimuNum=50)
  Female=factor(ncii$Female)
  Male=factor(ncii$Male)
  Rep=factor(ncii$Rep)
  res=lmm.simu.jack(Y~1|Female*Male+Rep)
  res

  #End

An R function to generate a simulated data set

Description

An R function to generate a simulated data set with given parameters, model, and data structure.

Usage

lmm.simudata(formula, data = list(), v, b, SimuNum = NULL)

Arguments

formula

A linear mixed model formula

data

A data frame. It can be default.

v

A vector of preset variance components

b

A vector of present fixed effects.

SimuNum

The number of simulations. The default number is 200.

Value

Return a simulated data set which is a matrix.

Author(s)

Jixiang Wu <jixiang.wu@sdstate.edu>

References

Rao, C.R. 1971. Estimation of variance and covariance components-MINQUE theory. J Multiva Ana 1:19

Rao, C. R. and Kleffe, J. 1980. Estimation of variance components. In Handbook of Statistics. Vol. l: 1-40. Krishnaiah, P. R. ed. New York. North-Holland.

Searle, S. R., Casella, G. and McCulloch, C. E. 1992. Variance Components. John Wiley & Sons, Inc. New York.

Wu J (2012) GenMod: An R package for various agricultural data analyses. ASA, CSSA, and SSSA 2012 International Annual Meetings, Cincinnati, OH, p 127

Wu J., Bondalapati K., Glover K., Berzonsky W., Jenkins J.N., McCarty J.C. 2013. Genetic analysis without replications: model evaluation and application in spring wheat. Euphytica. 190:447-458

Zhu J. 1989. Estimation of Genetic Variance Components in the General Mixed Model. Ph.D. Dissertation, NC State University, Raleigh, U.S.A

Examples

  library(minque)
  data(ncii)

  lmm.inf=lmm.check(Yld~1|Female*Male+Rep,data=ncii)

  lmm.inf  ##there are five variance components
  v=c(20,20,20,20,20) ##there are five variance components
  b=as.vector(100)    ##there is only population mean as fixed effect
  Y=lmm.simudata(Yld~1|Female*Male+Rep,data=ncii,v=v,b=b,SimuNum=50)



  #End

Maize variety trial

Description

Maize variety trial with two years and multi-locations in China.

Usage

data(maize)

Format

A data frame with 260 observations (rows) on the following 4 variables (columns).

Cultivar: cultivar names
Year: testing year
Location: testing locations
Yld: maize yield

Details

No other details available

Source

Fan X.M., Kang M.S., Chen H.M., Zhang Y.D., Tan J., Xu C.X. (2007) Yield stability of maize hybrids evaluated in multi-environment trials in Yunnan, China. Agronomy Journal.99:220-228

References

Fan X.M., Kang M.S., Chen H.M., Zhang Y.D., Tan J., Xu C.X. (2007) Yield stability of maize hybrids evaluated in multi-environment trials in Yunnan, China. Agronomy Journal.99:220-228

Examples


 library(minque)
 data(maize)
 #names(maize)

 res=lmm(Yld~1|Cultivar*Year+Cultivar*Location+Year*Location,data=maize)
 res$Var
 res$FixedEffect
 res$RandomEffect

 res=lmm.jack(Yld~1|Cultivar*Year+Cultivar*Location+Year*Location,
    data=maize,JacNum=10,JacRep=1,ALPHA=0.05)
 res$Var
 res$PVar
 res$FixedEffect
 res$RandomEffect

 ##End

NC design II F1 data

Description

A genetic data set can be analyzed by ANOVA or MIQNUE approaches.

Usage

data(ncii)

Format

A data frame with 60 observations on the following 4 variables.

Female: female parents
Male: male parents
Rep: replications
Yld: yield

Details

No other details available

Source

Not available

References

To be added

Examples

 library(minque)
 data(ncii)

 res=lmm(Yld~1|Female*Male+Rep,data=ncii)
 res$Var
 res$FixedEffect
 res$RandomEffect

 res=lmm.jack(Yld~1|Female*Male+Rep,data=ncii,
    JacNum=10,JacRep=1,ALPHA=0.05)
 res$Var
 res$PVar

 res$FixedEffect
 res$RandomEffect