Easyanova

Package ‘easyanova’
November 16, 2017

Type Package
Title Analysis of Variance and Other Important Complementary Analyses
Version 5.0
Date 2017-11-14
Author Emmanuel Arnhold
Maintainer Emmanuel Arnhold <emmanuelarnhold@yahoo.com.br>
Description Perform analysis of variance and other important complementary
analyses. The functions are easy to use. Performs analysis in various
designs, with balanced and unbalanced data.
Depends R (>= 3.0.0)
Imports car, nlme
License GPL-2
NeedsCompilation no
Repository CRAN
Date/Publication 2017-11-16 22:11:35 UTC
R topics documented:
easyanova-package . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
data1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
data10 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
data11 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
data12 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
data13 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
data14 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
data15 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
data16 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
data17 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
data18 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
data19 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
data2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
data3 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 12
1
2 easyanova-package
data4 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
data5 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
data6 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
data7 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
data8 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
data9 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
ea1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 17
ea2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
ec . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
Index 25
easyanova-package Analysis of Variance and Other Important Complementary Analyzes
Description
Perform analysis of variance and other important complementary analyzes. The functions are easy
to use. Performs analysis in various designs, with balanced and unbalanced data.
Details
Package: easyanova
Type: Package
Version: 5.0
Date: 2017-11-14
License: GPL-2
Author(s)
Emmanuel Arnhold <emmanuelarnhold@yahoo.com.br>
References
CRUZ, C.D. and CARNEIRO, P.C.S. Modelos biometricos aplicados ao melhoramento genetico.
2nd Edition. Vicosa, UFV, v.2, 2006. 585p.
KAPS, M. and LAMBERSON, W. R. Biostatistics for Animal Science: an introductory text. 2nd
Edition. CABI Publishing, Wallingford, Oxfordshire, UK, 2009. 504p.
SAMPAIO, I. B. M. Estatistica aplicada a experimentacao animal. 3nd Edition. Belo Horizonte:
Editora FEPMVZ, Fundacao de Ensino e Pesquisa em Medicina Veterinaria e Zootecnia, 2010.
264p.
SANDERS W.L. and GAYNOR, P.J. Analysis of switchback data using Statistical Analysis System,
Inc. Software. Journal of Dairy Science, 70.2186-2191. 1987.
easyanova-package 3
PIMENTEL-GOMES, F. and GARCIA C.H. Estatistica aplicada a experimentos agronomicos e

florestais: exposicao com exemplos e orientacoes para uso de aplicativos. Editora Fealq, v.11,
2002. 309p.
RAMALHO, M. A. P.; FERREIRA, D. F. and OLIVEIRA, A. C. Experimentacao em Genetica e
Melhoramento de Plantas. Editora UFLA, 2005, 322p.
See Also
ea1, ea2, ec
Examples
# Kaps and Lamberson(2009)

data(data1)
data(data2)
data(data3)
data(data4)
# analysis in completely randomized design

r1<-ea1(data1, design=1)
names(r1)
r1
# analysis in randomized block design

# analysis in latin square design

# analysis in several latin squares design

r1[1]
r2[1]
r3[1]
r4[1]
# analysis in unbalanced randomized block design

response<-ifelse(data2$Gain>850, NA, data2$Gain)
ndata<-data.frame(data2[-3],response)
ndata
r5<-ea1(ndata, design=2 )
r5
# multivariable response (list argument = TRUE)

t<-c('a','a','a','b','b','b','c','c','c')
r1<-c(10,12,12.8,4,6,8,14,15,16)
4 data1
r2<-c(102,105,106,125,123,124,99,95,96)
r3<-c(560,589,590,658,678,629,369,389,378)
d<-data.frame(t,r1,r2,r3)
results=ea1(d, design=1, list=TRUE)

names(results)
results
results[1][[1]]
names(results[1][[1]])
data1 data1: Kaps and Lamberson(2009): page 252
Description
The experiment compared three diets for pigs in a completely randomized design
Usage
data(data1)
Format
A data frame with 15 observations on the following 2 variables.
Diet a factor with levels d1 d2 d3

Gain a numeric vector
References
Examples
data(data1)
summary(data1)
data10 5
data10 data10: Kaps and Lamberson (2009): page 395
Description
Completely randomized design with a covariate.The effect of three diets on daily gain of steers
was investigated. The design was a completely randomized design. Weight at the beginning of the
experiment (initial weight) was recorded, but not used in the assignment of animals to diet.
Usage
data(data10)
Format
Diets a factor with levels A B C

Initial_weight a numeric vector
Repetitions a numeric vector
References
Examples
data(data10)
summary(data10)
data11 data11: Pimentel Gomes and Garcia (2002): page 199
Description
Incomplete block design
Usage
data(data11)
6 data12
Format
treatments a numeric vector
rep a numeric vector
blocks a numeric vector
yield a numeric vector
References
2002. 309p.
Examples
data(data11)
summary(data11)
Description
Usage
data(data12)
Format
References
2002. 309p.
Examples
data(data12)
summary(data12)
data13 7
data13 data13: Cruz and Carneiro (2006): page 575
Description
Usage
data(data13)
Format
genotypes a factor with levels f1 f10 f11 f12 f13 f14 f2 f3 f4 f5 f6 f7 f8 f9 test1 test2
test3
blocks a factor with levels b1 b2 b3
References
Examples
data(data13)
summary(data13)
data14 data14: Sampaio (2009): page173
Description
Incomplete block design in animals
Usage
data(data14)
8 data15
Format
treatment a factor with levels A B C D E F G
animal a factor with levels A1 A2 A3 A4 A5 A6 A7
period a factor with levels P1 P2 P3 P4
response a numeric vector
References
264p.
Examples
data(data14)
summary(data14)
Description
Lattice design
Usage
data(data15)
Format
References
2002. 309p.
Examples
data(data15)
summary(data15)
data16 9
data16 data16: Sampaio (2010): page164
Description
Switchback design
Usage
data(data16)
Format
treatment a factor with levels A B C

period a numeric vector
animal a numeric vector
gain a numeric vector
References
264p.
Examples
data(data16)
summary(data16)
data17 data17: Sanders and Gaynor (1987)
Description
Switchback design
Usage
data(data17)
10 data18
Format
blocks a factor with levels b1 b2 b3
animal a numeric vector
References
Examples
data(data17)
summary(data17)
data18 data18: Ramalho et al. (2005): page 115
Description
Repetition of experiments in block design
Usage
data(data18)
Format
experiments a numeric vector
References
Examples
data(data18)
summary(data18)
data19 11
data19 data19: Sampaio (2010): page 155
Description
Repetition of latin square design
Usage
data(data19)
Format
treatments a factor with levels A B C D

squares a factor with levels 1 2
rows a factor with levels 1 2 3 4
columns a factor with levels 1 2 3 4
References
264p.
Examples
data(data19)
summary(data19)
data2 data2: Kaps and Lamberson (2009): page 313: randomizad block
design
Description
Complete randomized block design to determine the average daily gain of steers
Usage
data(data2)
12 data3
Format
Treatments a factor with levels t1 t2 t3
Blocks a factor with levels b1 b2 b3 b4
References
Examples
data(data2)
summary(data2)
Description
Latin square design for test four different treatments on hay intake of fattening steers
Usage
data(data3)
Format
treatment a factor with levels A B C D
period a factor with levels p1 p2 p3 p4
steer a factor with levels a1 a2 a3 a4
References
Examples
data(data3)
summary(data3)
data4 13
Description
Two latin squares design for test four different treatments on hay intake of fattening steers
Usage
data(data4)
Format
diet a factor with levels A B C D

square a numeric vector
steer a numeric vector
References
Examples
data(data4)
summary(data4)
Description
Factorial in randomized design for testing two vitamins in feed of pigs
Usage
data(data5)
14 data6
Format
Vitamin_1 a numeric vector
Vitamin_2 a numeric vector
Gains a numeric vector
References
Examples
data(data5)
summary(data5)
Description
Factorial in randomized block design
Usage
data(data6)
Format
factor1 a numeric vector
factor2 a numeric vector
block a numeric vector
References
2002. 309p.
Examples
data(data6)
summary(data6)
data7 15
Description
The aim of this experiment was to test the difference between two treatments on gain of kids. A
sample of 18 kids was chosen, nine for each treatment. One kid in treatment 1 was removed from the
experiment due to illness. The experiment began at the age of 8 weeks. Weekly gain was measured
at ages 9, 10, 11 and 12 weeks.
Usage
data(data7)
Format
treatment a character vector

week a character vector
References
Examples
data(data7)
summary(data7)
Description
Split-plot Design. Main Plots in Randomized Blocks. An experiment was conducted in order to
investigate four different treatments of pasture and two mineral supplements on milk yield. The
total number of cows available was 24. The experiment was designed as a split-plot, with pasture
treatments (factor A) assigned to the main plots and mineral supplements (factor B) assigned to
split-plots. The experiment was replicated in three blocks.
16 data9
Usage
data(data8)
Format
pasture a factor with levels p1 p2 p3 p4

block a numeric vector
mineral a factor with levels m1 m2
milk a numeric vector
References
Examples
data(data8)
summary(data8)
data9 data9: Sampaio (2010): page 67
Description
Factorial design to evaluate egg quality according to the lineage of chicken, packaging and storage
time.
Usage
data(data9)
Format
lineage a factor with levels A B

packing a factor with levels Ce Co S
time a numeric vector
repetitions a numeric vector
ea1 17
References
264p.
Examples
data(data9)
summary(data9)
ea1 Analysis of variance in simple designs
Description
Perform analysis of variance and other important complementary analyzes. The function are easy
to use. Performs analysis in various simples designs, with balanced and unbalanced data. Too
performs analysis the kruskal-Wallis and Friedman (designs 14 and 15).
Usage
ea1(data, design = 1, alpha = 0.05, list = FALSE, p.adjust=1, plot=2)
Arguments
data data is a data.frame
see how the input data in the examples
design 1 = completely randomized design
2 = randomized block design
3 = latin square design
4 = several latin squares
5 = analysis with a covariate (completely randomized design)
6 = analysis with a covariate (randomized block design)
7 = incomplete blocks type I and II
8 = incomplete blocks type III or augmented blocks
9 = incomplete blocks type III in animal experiments
10 = lattice (intra-block analysis)
11 = lattice (inter-block analysis)
12 = switchback design
13 = switchback design in blocks
14 = Kruskal-Wallis rank sum test
15 = Friedman rank sum test
alpha significance level for multiple comparisons
18 ea1
list FALSE = a single response variable

TRUE = multivariable response
p.adjust 1="none"; 2="holm"; 3="hochberg"; 4="hommel"; 5="bonferroni"; 6="BH",
7="BY"; 8="fdr"; for more details see function "p.adjust"
plot 1 = box plot for residuals; 2 = standardized residuals vs sequence data; 3 =
standardized residuals vs theoretical quantiles
Details
The response variable must be numeric. Other variables can be numeric or factors.
Value
Returns analysis of variance, means (adjusted means), multiple comparison test (tukey, snk, dun-
can, t and scott knott) and residual analysis. Too returns analysis the kruskal-Wallis and Friedman
(designs 14 and 15).
Author(s)
References
264p.
2002. 309p.
See Also
ea2, ec
Examples
# Kaps and Lamberson(2009)

data(data1)
data(data2)
data(data3)
data(data4)
ea1 19

names(r1)
r1
# analysis in randomized block design

# analysis in latin square design

# analysis in several latin squares design

r1[1]
r2[1]
r3[1]
r4[1]
# analysis in unbalanced randomized block design

response<-ifelse(data2$Gain>850, NA, data2$Gain)
ndata<-data.frame(data2[-3],response)
ndata
r5<-ea1(ndata, design=2 )
r5
# multivariable response (list argument = TRUE)

t<-c('a','a','a','b','b','b','c','c','c')
r1<-c(10,12,12.8,4,6,8,14,15,16)
r2<-c(102,105,106,125,123,124,99,95,96)
r3<-c(560,589,590,658,678,629,369,389,378)
d<-data.frame(t,r1,r2,r3)
results=ea1(d, design=1, list=TRUE)

names(results)
results
results[1][[1]]
names(results[1][[1]])
# analysis with a covariate

# Kaps and Lamberson (2009)
# data(data10)

20 ea1
# r6<-ea1(data10[-3], design=5)
# r6
# incomplete blocks type I and II

# Pimentel Gomes and Garcia (2002)
# data(data11)
# data(data12)
#r7<-ea1(data11,design=7)
#r8<-ea1(data12,design=7)
#r7;r8
# incomplete blocks type III or augmented blocks

# Cruz and Carneiro (2006)
# data(data13)
#r9<-ea1(data13, design=8)
#r9
# incomplete blocks type III in animal experiments

# Sampaio (2010)
# data(data14)
# r10<-ea1(data14, design=9)
# r10
# lattice
# Pimentel Gomes and Garcia (2002)
# data(data15)
#r11<-ea1(data15, design=10) # intra-block analysis

#r12<-ea1(data15, design=11) # inter-block analysis
#r11
#r12
# switchback design
# Sampaio (2010)
# data(data16)
# r13
# switchback design in blocks

# Sanders and Gaynor (1987)
# data(data17)
# r14
ea2 21
#Kruskal-Wallis Rank Sum Test

r15
#Friedman Rank Sum Test

r16
ea2 Analysis of variance in factorial and split plot
Description
Perform analysis of variance and other important complementary analyzes in factorial and split plot
scheme, with balanced and unbalanced data.
Usage
ea2(data, design = 1, alpha = 0.05, cov = 4, list = FALSE, p.adjust=1, plot=2)
Arguments
data data is a data.frame
see how the input data in the examples
design 1 = double factorial in completely randomized design
2 = double factorial in randomized block design
3 = double factorial in latin square design
4 = split plot in completely randomized design
5 = split plot in randomized block design
6 = split plot in latin square design
7 = triple factorial in completely randomized design
8 = triple factorial in randomized block design
9 = double factorial in split plot (completely randomized)
10 = double factorial in split plot (randomized in block)
11 = joint analysis of experiments with hierarchical blocks
12 = joint analysis of repetitions of latin squares (hierarchical rows)
13 = joint analysis of repetitions of latin squares (hierarchical rows and columns)
alpha significance level for multiple comparisons
cov for split plot designs
1 = Autoregressive
2 = Heterogenius Autoregressive
3 = Continuous Autoregressive Process
4 = Compound Symetry
5 = Unstructured
22 ea2
list FALSE = a single response variable

TRUE = multivariable response
p.adjust 1="none"; 2="holm"; 3="hochberg"; 4="hommel"; 5="bonferroni"; 6="BH",
7="BY"; 8="fdr"; for more details see function "p.adjust"
plot 1 = box plot for residuals; 2 = standardized residuals vs sequence data; 3 =
standardized residuals vs theoretical quantiles
Details
The response variable must be numeric. Other variables can be numeric or factors.
Value
Returns analysis of variance, means (adjusted means), multiple comparison test (tukey, snk, duncan,
t and scott knott) and residual analysis.
Author(s)
References
264p.
2002. 309p.
See Also
ea1, ec
Examples
# double factorial
# completely randomized design

data(data5)
r1=ea2(data5, design=1)
r1
# randomized block design

# data(data6)
ec 23
# r2=ea2(data6, design=2)
# r2
# names(r1)
# names(r2)
# triple factorial

# data(data9)
# r3=ea2(data9[,-4], design=7)
# r3[1]
# split plot

# data(data7)
# r4
# randomized block design

# data(data8)
# r5
# hierarchical blocks
# Ramalho et al. (2005)
# data(data18)
# data18
# r6
# hierarchical latin squares

# Sampaio (2010)
# data(data19)
# data19
# hierarchical rows
# r7
# hierarchical rows and columns

# r8
ec Easy contrast
24 ec
Description
Performs contrasts of means
Usage
ec(mg1, mg2, sdg1, sdg2, df)
Arguments
mg1 Means of the group 1
mg2 Means of the group 2
sdg1 Standard error of the group 1
sdg2 Standard error of the group 2
df Degree of freedom from error
Value
Returns t test for contrast
Author(s)
References
See Also
ea1,ea2
Examples
# Kaps and Lamberson(2009, pg 254)
data(data1)
r<-ea1(data1, design=1)
r[2]
# first contrast
mg1=312;mg2=c(278,280); sdg1=7.7028;sdg2=c(7.7028,7.7028); df=12
ec(mg1,mg2,sdg1,sdg2,df)
# second contrast
mg1=280;mg2=278; sdg1=7.7028;sdg2=7.7028; df=12
ec(mg1,mg2,sdg1,sdg2,df)
Index
data1, 4
data10, 5
data11, 5
data12, 6
data13, 7
data14, 7
data15, 8
data16, 9
data17, 9
data18, 10
data19, 11
data2, 11
data3, 12
data4, 13
data5, 13
data6, 14
data7, 15
data8, 15
data9, 16
ea1, 17
ea2, 21
easyanova (easyanova-package), 2
easyanova-package, 2
ec, 23
25

Easyanova

Uploaded by

Copyright:

Available Formats

Easyanova

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Easyanova

Uploaded by

Copyright:

Available Formats

Package ‘easyanova’

November 16, 2017

easyanova-package Analysis of Variance and Other Important Complementary Analyzes

PIMENTEL-GOMES, F. and GARCIA C.H. Estatistica aplicada a experimentos agronomicos e

# Kaps and Lamberson(2009)

# analysis in completely randomized design

# analysis in randomized block design

# analysis in latin square design

# analysis in several latin squares design

# analysis in unbalanced randomized block design

# multivariable response (list argument = TRUE)

results=ea1(d, design=1, list=TRUE)

data1 data1: Kaps and Lamberson(2009): page 252

A data frame with 15 observations on the following 2 variables.

Diet a factor with levels d1 d2 d3

data10 data10: Kaps and Lamberson (2009): page 395

Diets a factor with levels A B C

data11 data11: Pimentel Gomes and Garcia (2002): page 199

data12 data12: Pimentel Gomes and Garcia (2002): page 202

data13 data13: Cruz and Carneiro (2006): page 575

Incomplete block design

A data frame with 23 observations on the following 3 variables.

data14 data14: Sampaio (2009): page173

Incomplete block design in animals

data15 data15: Pimentel Gomes and Garcia (2002): page 211

data16 data16: Sampaio (2010): page164

treatment a factor with levels A B C

data17 data17: Sanders and Gaynor (1987)

data18 data18: Ramalho et al. (2005): page 115

data19 data19: Sampaio (2010): page 155

treatments a factor with levels A B C D

data3 data3: Kaps and Lamberson (2009): page 347

data4 data4: Kaps and Lamberson (2009): page 349

diet a factor with levels A B C D

data5 data5: Kaps and Lamberson (2009): page 361

data6 data6: Pimentel Gomes and Garcia (2002): page 127

data7 data7: Kaps and Lamberson (2009): page 409

treatment a character vector

data8 data8: Kaps and Lamberson (2009): page 386

pasture a factor with levels p1 p2 p3 p4

data9 data9: Sampaio (2010): page 67

lineage a factor with levels A B

ea1 Analysis of variance in simple designs

list FALSE = a single response variable

# Kaps and Lamberson(2009)

# analysis in completely randomized design

# analysis in randomized block design

# analysis in latin square design

# analysis in several latin squares design

# analysis in unbalanced randomized block design

# multivariable response (list argument = TRUE)

results=ea1(d, design=1, list=TRUE)

# analysis with a covariate

# analysis in completely randomized design

# incomplete blocks type I and II

# incomplete blocks type III or augmented blocks

# incomplete blocks type III in animal experiments

#r11<-ea1(data15, design=10) # intra-block analysis