R

http://sites.google.com/site/UnityInDiversity99/r

E-Content For Pondicherry University M.Sc. (Agri.) 2015 Syllabus STA503 / COM501 Course

(By Mr.S.Saravanan & Mr.K.C.Ayyoob) July 2016

Introduction To R Software - https://sites.google.com/view/introductiontorsoftware/

Dear viewers

Feel free to email me about any correction / deletion / addition needed in the details I have given

S.Saravanan

Associate Professor (Computer Science)

PAJANCOA & RI

Karaikal

tssaravananone@gmail.com

http://www.pajancoa.ac.in/staff_aec.htm

For Advanced Doubts Related to Statistics & Statistical Softwares, Students Can Contact

Mr.Ayyoob.K.C, Assistant Professor (Statistics)

Through His Below Email

ayyoobsm@gmail.com

R Terminal Online

https://www.tutorialspoint.com/r_terminal_online.php

Note:

After Seeing $ Prompt, Type R and Press Enter

Other Programming / Coding in Online Through Browsers

https://www.tutorialspoint.com/codingground.htm

R - To open R Console

Dash > R

R - When R is ready to accept command, it will show below prompt

>

R - Command to quit R console without saving Workspace

q(save="no")

R - To get (display) the working directory

getwd()

R - Example of Assignment Operator = ( <- can also be used instead of = )

numdata=6

numdata

[1] 6

numdata*10

[1] 60

R - To list all objects available in the workspace

objects()

R - Example of saving a workspace (with all its objects) in a file test.RData

save.image("test.RData")

R - Example of loading (open) a workspace (with all its objects) saved in a file test.RData

load("test.RData”)

R - Example of diverting output of R to a file output.txt

sink("output.txt")

R - To cancel the divert enabled through above command

sink()

R - Example of Importing dataset from clipboard to a dataframe using read.table()

Step 1:

Type a table of data / dataset in LibreOffice Calc.

Select the data.

Right click over the selection.

Context menu appears.

Select Copy

Step 2:

Run the below command in R to import the dataset from clipboard to a dataframe (example numtable)

numtable = read.table("clipboard",header=F)

R - To Create dataframe Using data.frame()

Example dataframe to be created is dataframe1

> dataframe1=data.frame()

> dataframe1

data frame with 0 columns and 0 rows

---

R - To Edit Column Name, Column Data Type, Data of a dataframe

Example dataframe to be edited is dataframe1

> dataframe1=edit(dataframe1)

Above Command Opens dataframe1 in electronic spreadsheet like R Data Editor

Column headings have the names var1, var2, ...

To change column name, click over column name > Change Name

To change column data type, click over column name > Real / Character

> dataframe1

SNAME AGE

1 Sakthi 22

2 Joseph 21

3 Rafi 20

R - Example of Editing a dataframe using fix() function (data editor)

fix(numtable)

R - Plant Growth Data (dataframe)

PlantGrowth

weight group

1 4.17 ctrl

2 5.58 ctrl

3 5.18 ctrl

4 6.11 ctrl

5 4.50 ctrl

6 4.61 ctrl

7 5.17 ctrl

8 4.53 ctrl

9 5.33 ctrl

10 5.14 ctrl

11 4.81 trt1

12 4.17 trt1

13 4.41 trt1

14 3.59 trt1

15 5.87 trt1

16 3.83 trt1

17 6.03 trt1

18 4.89 trt1

19 4.32 trt1

20 4.69 trt1

21 6.31 trt2

22 5.12 trt2

23 5.54 trt2

24 5.50 trt2

25 5.37 trt2

26 5.29 trt2

27 4.92 trt2

28 6.15 trt2

29 5.80 trt2

30 5.26 trt2

R - To convert the above stacked form dataframe to unstacked form

UnstackedPlantGrowth = unstack(PlantGrowth)

UnstackedPlantGrowth

ctrl trt1 trt2

1 4.17 4.81 6.31

2 5.58 4.17 5.12

3 5.18 4.41 5.54

4 6.11 3.59 5.50

5 4.50 5.87 5.37

6 4.61 3.83 5.29

7 5.17 6.03 4.92

8 4.53 4.89 6.15

9 5.33 4.32 5.80

10 5.14 4.69 5.26

R - To convert the above unstacked form dataframe to stacked form

NewStackedPlantGrowth = stack(UnstackedPlantGrowth)

NewStackedPlantGrowth

values ind

1 4.17 ctrl

2 5.58 ctrl

3 5.18 ctrl

4 6.11 ctrl

5 4.50 ctrl

6 4.61 ctrl

7 5.17 ctrl

8 4.53 ctrl

9 5.33 ctrl

10 5.14 ctrl

11 4.81 trt1

12 4.17 trt1

13 4.41 trt1

14 3.59 trt1

15 5.87 trt1

16 3.83 trt1

17 6.03 trt1

18 4.89 trt1

19 4.32 trt1

20 4.69 trt1

21 6.31 trt2

22 5.12 trt2

23 5.54 trt2

24 5.50 trt2

25 5.37 trt2

26 5.29 trt2

27 4.92 trt2

28 6.15 trt2

29 5.80 trt2

30 5.26 trt2

R - Student's Sleep Data

sleep

extra group ID

1 0.7 1 1

2 -1.6 1 2

3 -0.2 1 3

4 -1.2 1 4

5 -0.1 1 5

6 3.4 1 6

7 3.7 1 7

8 0.8 1 8

9 0.0 1 9

10 2.0 1 10

11 1.9 2 1

12 0.8 2 2

13 1.1 2 3

14 0.1 2 4

15 -0.1 2 5

16 4.4 2 6

17 5.5 2 7

18 1.6 2 8

19 4.6 2 9

20 3.4 2 10

R - Classical N, P, K Factorial Experiment Data

npk

block N P K yield

1 1 0 1 1 49.5

2 1 1 1 0 62.8

3 1 0 0 0 46.8

4 1 1 0 1 57.0

5 2 1 0 0 59.8

6 2 1 1 1 58.5

7 2 0 0 1 55.5

8 2 0 1 0 56.0

9 3 0 1 0 62.8

10 3 1 1 1 55.8

11 3 1 0 0 69.5

12 3 0 0 1 55.0

13 4 1 0 0 62.0

14 4 1 1 1 48.8

15 4 0 0 1 45.5

16 4 0 1 0 44.2

17 5 1 1 0 52.0

18 5 0 0 0 51.5

19 5 1 0 1 49.8

20 5 0 1 1 48.8

21 6 1 0 1 57.2

22 6 1 1 0 59.0

23 6 0 1 1 53.2

24 6 0 0 0 56.0

R - Example of Descriptive Statistics / Summary

summary(PlantGrowth)

weight group

Min. : 3.590 ctrl:10

1st Qu. : 4.550 trt1:10

Median : 5.155 trt2:10

Mean : 5.073

3rd Qu. : 5.530

Max. : 6.310

R - Example of Sum

sum(PlantGrowth$weight)

[1] 152.19

R - Example of Arithmetic Mean (Average)

mean(c(5,6,7))

[1] 6

R - Example of Median (Middle Value)

median(c(5,6,7,8))

[1] 6.5

R - Example of Mode (Most Occurred)

dataformode=c(8,4,5,4,0,0,0,6,6,3,6,6)

as.numeric(names(which.max(table(dataformode))))

[1] 6

R - Example of Range

range(3,4,5,8,1,2,12)

[1] 1 12

R - Example of Standard Deviation

sd(c(4,5,6,7))

[1] 1.290994

R - Example of Variance (Square of Standard Deviation)

var(c(4,5,6,7))

[1] 1.666667

- - -

(sd(c(4,5,6,7)))^2

[1] 1.666667

R - Example of Skewness

library("agricolae")

skewness(c(3,4,5,10))

[1] 1.597078

R - Example of Kurtosis

library("agricolae")

kurtosis(c(3,4,5,10))

[1] 2.703924

R - Syntax, Example for Simple Linear Regression (lm - Linear Model)

Syntax

summary(lm(<dependent variable>~<independent variable>, data=<data frame>))

Example

summary(lm(circumference~age, data=Orange))

Call:

lm(formula = circumference ~ age, data = Orange)

Residuals:

Min 1Q Median 3Q Max

-46.310 -14.946 -0.076 19.697 45.111

Coefficients:

Estimate Std. Error t value Pr(>|t|)

(Intercept) 17.399650 8.622660 2.018 0.0518 .

age 0.106770 0.008277 12.900 1.93e-14 ***

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 23.74 on 33 degrees of freedom

Multiple R-squared: 0.8345, Adjusted R-squared: 0.8295

F-statistic: 166.4 on 1 and 33 DF, p-value: 1.931e-14

R - Syntax, Example for Multiple Linear Regression (lm - Linear Model)

Syntax

summary(lm(<dependent variable>~<independent variable1 + independent variable2 + ... >, data=<data frame>))

Example

summary(lm(VanKilled~PetrolPrice + kms, data=Seatbelts))

Call:

lm(formula = VanKilled ~ PetrolPrice + kms, data = Seatbelts)

Residuals:

Min 1Q Median 3Q Max

-9.0120 -2.3903 0.3601 2.3563 6.5804

Coefficients:

Estimate Std. Error t value Pr(>|t|)

(Intercept) 2.102e+01 2.003e+00 10.495 < 2e-16 ***

PetrolPrice -3.411e+01 2.025e+01 -1.684 0.0938 .

kms -5.622e-04 8.393e-05 -6.699 2.34e-10 ***

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 3.147 on 189 degrees of freedom

Multiple R-squared: 0.2592, Adjusted R-squared: 0.2513

F-statistic: 33.06 on 2 and 189 DF, p-value: 4.888e-13

R - Example of Covariance

cov(Orange$circumference,Orange$age)

[1] 25831.02

R - Example of Correlation coefficient

cor(Orange$circumference,Orange$age)

[1] 0.9135189

R - Example of (Welch) (Two Samples) Unpaired (Independent) (Student's) t-test Assuming Unequal Variances

t.test(sleep$extra ~ sleep$group)

or

t.test(extra ~ group, data = sleep)

Welch Two Sample t-test

data: sleep$extra by sleep$group

t = -1.8608, df = 17.776, p-value = 0.07939

alternative hypothesis: true difference in means is not equal to 0

95 percent confidence interval:

-3.3654832 0.2054832

sample estimates:

mean in group 1 mean in group 2

0.75 2.33

R - Example of (Two Samples) Unpaired (Independent) (Student's) t-test Assuming Equal Variances

t.test(sleep$extra ~ sleep$group, var.equal=TRUE)

Two Sample t-test

data: sleep$extra by sleep$group

t = -1.8608, df = 18, p-value = 0.07919

alternative hypothesis: true difference in means is not equal to 0

95 percent confidence interval:

-3.363874 0.203874

sample estimates:

mean in group 1 mean in group 2

0.75 2.33

R - Example of (Two Samples) Paired (Student's) t-test

t.test(sleep$extra ~ sleep$group, paired=TRUE)

Paired t-test

data: sleep$extra by sleep$group

t = -4.0621, df = 9, p-value = 0.002833

alternative hypothesis: true difference in means is not equal to 0

95 percent confidence interval:

-2.4598858 -0.7001142

sample estimates:

mean of the differences

-1.58

R - Example of z-test

(Using PASWR - Probability And Statistics With R)

library("PASWR")

x=c(7.8, 6.6, 6.5, 7.4, 7.3, 7, 6.4, 7.1, 6.7, 7.6, 6.8)

y=c(4.5, 5.4, 6.1, 6.1, 5.4, 5, 4.1, 5.5)

z.test(x, sigma.x=0.5, y, sigma.y=0.5, conf.level=0.95)

Two-sample z-Test

data: x and y

z = 7.5568, p-value = 4.13e-14

alternative hypothesis: true difference in means is not equal to 0

95 percent confidence interval:

1.300323 2.211040

sample estimates:

mean of x mean of y

7.018182 5.262500

Note:

null hypothesis: true difference in means is equal to 0

If y = NULL, a one-sample z-test is carried out with ‘x’

R - Examples For Independent Variable(s) / Treatments (Whose Effects on Dependent Variable We Compare)

Varieties

Fertilizers

FeedTypes

SowingDates

IrrigationTypes

R - Example For Dependent Variable / Response

Yield

R - Example of Completely Randomized Design ANOVA (One-way ANOVA)

Syntax

aov(<dependent variable>~<independent variable>, data=<data frame>)

mango = data.frame(

yield=c(34, 45, 36, 54, 55, 45, 37, 33, 56),

variety=c("var1", "var1", "var1", "var2", "var2", "var2", "var3", "var3", "var3") )

mango

yield variety

1 34 var1

2 45 var1

3 36 var1

4 54 var2

5 55 var2

6 45 var2

7 37 var3

8 33 var3

9 56 var3

summary(aov(yield~variety, data=mango))

Df Sum Sq Mean Sq F value Pr(>F)

variety 2 269.6 134.78 1.875 0.233

Residuals 6 431.3 71.89

R - Example For Completely Randomized Design (CRD)

library(agricolae)

treatments=c("trt1", "trt2", "trt3", "trt4")

reps = 3

result = design.crd(treatments, reps, randomization=FALSE)

result

$parameters

$parameters$design

[1] "crd"

$parameters$trt

[1] "trt1" "trt2" "trt3" "trt4"

$parameters$r

[1] 3 3 3 3

$parameters$serie

[1] 2

$parameters$seed

[1] 946090695

$parameters$kinds

[1] "Super-Duper"

$parameters[[7]]

[1] FALSE

$book

plots r treatments

1 101 1 trt1

2 102 2 trt1

3 103 3 trt1

4 104 1 trt2

5 105 2 trt2

6 106 3 trt2

7 107 1 trt3

8 108 2 trt3

9 109 3 trt3

10 110 1 trt4

11 111 2 trt4

12 112 3 trt4

R - Example of Randomized (Complete) Block Design ANOVA

(Two-way ANOVA Without Interaction Between 2 Factors)

Syntax

aov(<dependent variable>~<independent variable1>+<independent variable2>, data=<data frame>)

Note:

<independent variable2> is the blocking factor

In RBD, each block have all the treatments.

In CRD, replications can occur in any part of the field and each treatment can have different number of replications.

lemon = data.frame(

yield = c(34, 45, 36, 38, 54, 55, 45, 48, 37, 33, 56, 55),

treatments = c("trt1", "trt1", "trt1", "trt1", "trt2", "trt2", "trt2", "trt2", "trt3", "trt3", "trt3", "trt3"),

repsblocks = c("blk1", "blk2", "blk3", "blk4", "blk1", "blk2", "blk3", "blk4", "blk1", "blk2", "blk3", "blk4") )

lemon

yield treatments repsblocks

1 34 trt1 blk1

2 45 trt1 blk2

3 36 trt1 blk3

4 38 trt1 blk4

5 54 trt2 blk1

6 55 trt2 blk2

7 45 trt2 blk3

8 48 trt2 blk4

9 37 trt3 blk1

10 33 trt3 blk2

11 56 trt3 blk3

12 55 trt3 blk4

summary(aov(yield~treatments+repsblocks, data=lemon))

Df Sum Sq Mean Sq F value Pr(>F)

treatments 2 302.2 151.08 1.744 0.253

repsblocks 3 46.7 15.56 0.180 0.906

Residuals 6 519.8 86.64

R - Example For Randomized (Complete) Block Design (RCBD / RBD)

library(agricolae)

treatments=c("trt1", "trt2", "trt3", "trt4")

repsblocks = 3

result = design.rcbd(treatments, repsblocks, randomization=FALSE)

result

$parameters

$parameters$design

[1] "rcbd"

$parameters$trt

[1] "trt1" "trt2" "trt3" "trt4"

$parameters$r

[1] 3

$parameters$serie

[1] 2

$parameters$seed

[1] -434065305

$parameters$kinds

[1] "Super-Duper"

$parameters[[7]]

[1] FALSE

$sketch

[,1] [,2] [,3] [,4]

[1,] "trt1" "trt2" "trt3" "trt4"

[2,] "trt1" "trt2" "trt3" "trt4"

[3,] "trt1" "trt2" "trt3" "trt4"

$book

plots block treatments

1 101 1 trt1

2 102 1 trt2

3 103 1 trt3

4 104 1 trt4

5 201 2 trt1

6 202 2 trt2

7 203 2 trt3

8 204 2 trt4

9 301 3 trt1

10 302 3 trt2

11 303 3 trt3

12 304 3 trt4

R - Example of ANOVA with Interactions between N, P & K

summary(aov(yield ~ block + N*P*K, data=npk))

Df Sum Sq Mean Sq F value Pr(>F)

block 5 343.3 68.66 4.447 0.01594 *

N 1 189.3 189.28 12.259 0.00437 **

P 1 8.4 8.40 0.544 0.47490

K 1 95.2 95.20 6.166 0.02880 *

N:P 1 21.3 21.28 1.378 0.26317

N:K 1 33.1 33.13 2.146 0.16865

P:K 1 0.5 0.48 0.031 0.86275

Residuals 12 185.3 15.44

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

R - Example of ANOVA without any Interactions between N, P & K

summary(aov(yield ~ block + N+P+K, data=npk))

Df Sum Sq Mean Sq F value Pr(>F)

block 5 343.3 68.66 4.288 0.01272 *

N 1 189.3 189.28 11.821 0.00366 **

P 1 8.4 8.40 0.525 0.47999

K 1 95.2 95.20 5.946 0.02767 *

Residuals 15 240.2 16.01

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

R - Example For Latin Square Design (LSD)

varieties = c("malgova", "banganapalli", "alphonsa", "senthura", "kalapadi")

result = design.lsd(varieties)

result

$parameters

$parameters$design

[1] "lsd"

$parameters$trt

[1] "malgova" "banganapalli" "alphonsa" "senthura" "kalapadi"

$parameters$r

[1] 5

$parameters$serie

[1] 2

$parameters$seed

[1] 1527168179

$parameters$kinds

[1] "Super-Duper"

$parameters[[7]]

[1] TRUE

$sketch

[,1] [,2] [,3] [,4] [,5]

[1,] "senthura" "alphonsa" "malgova" "banganapalli" "kalapadi"

[2,] "alphonsa" "banganapalli" "kalapadi" "malgova" "senthura"

[3,] "kalapadi" "senthura" "banganapalli" "alphonsa" "malgova"

[4,] "malgova" "kalapadi" "alphonsa" "senthura" "banganapalli"

[5,] "banganapalli" "malgova" "senthura" "kalapadi" "alphonsa"

$book

plots row col varieties

1 101 1 1 senthura

2 102 1 2 alphonsa

3 103 1 3 malgova

4 104 1 4 banganapalli

5 105 1 5 kalapadi

6 201 2 1 alphonsa

7 202 2 2 banganapalli

8 203 2 3 kalapadi

9 204 2 4 malgova

10 205 2 5 senthura

11 301 3 1 kalapadi

12 302 3 2 senthura

13 303 3 3 banganapalli

14 304 3 4 alphonsa

15 305 3 5 malgova

16 401 4 1 malgova

17 402 4 2 kalapadi

18 403 4 3 alphonsa

19 404 4 4 senthura

20 405 4 5 banganapalli

21 501 5 1 banganapalli

22 502 5 2 malgova

23 503 5 3 senthura

24 504 5 4 kalapadi

25 505 5 5 alphonsa

R - Example For Split Plot Design

trtinplots = c("trt1", "trt2", "trt3")

trtinsubplots = c("trtsub1", "trtsub2", "trtsub3", "trtsub4")

repsblocks = 2

result = design.split(trtinplots, trtinsubplots, repsblocks, randomization = FALSE)

result

$parameters

$parameters$design

[1] "split"

$parameters[[2]]

[1] TRUE

$parameters$trt1

[1] "trt1" "trt2" "trt3"

$parameters$applied

[1] "rcbd"

$parameters$r

[1] 2

$parameters$serie

[1] 2

$parameters$seed

[1] -1781763121

$parameters$kinds

[1] "Super-Duper"

$book

plots splots block trtinplots trtinsubplots

1 101 1 1 trt2 trtsub1

2 101 2 1 trt2 trtsub2

3 101 3 1 trt2 trtsub3

4 101 4 1 trt2 trtsub4

5 102 1 1 trt3 trtsub1

6 102 2 1 trt3 trtsub2

7 102 3 1 trt3 trtsub3

8 102 4 1 trt3 trtsub4

9 103 1 1 trt1 trtsub1

10 103 2 1 trt1 trtsub2

11 103 3 1 trt1 trtsub3

12 103 4 1 trt1 trtsub4

13 201 1 2 trt2 trtsub1

14 201 2 2 trt2 trtsub2

15 201 3 2 trt2 trtsub3

16 201 4 2 trt2 trtsub4

17 202 1 2 trt1 trtsub1

18 202 2 2 trt1 trtsub2

19 202 3 2 trt1 trtsub3

20 202 4 2 trt1 trtsub4

21 203 1 2 trt3 trtsub1

22 203 2 2 trt3 trtsub2

23 203 3 2 trt3 trtsub3

24 203 4 2 trt3 trtsub4

R - Example For Split Plot Design ANOVA

Syntax

sp.plot(repsblocks, mainplotfactor, subplotfactor, response)

Example

library("agricolae")

data(plots,package="agricolae")

plots

block plot A B yield

1 1 p1 a1 b1 4

2 1 p1 a1 b2 1

3 1 p1 a1 b3 9

4 1 p2 a2 b1 6

5 1 p2 a2 b2 10

6 1 p2 a2 b3 2

7 2 p3 a1 b1 5

8 2 p3 a1 b2 3

9 2 p3 a1 b3 10

10 2 p4 a2 b1 4

11 2 p4 a2 b2 14

12 2 p4 a2 b3 1

13 3 p5 a1 b1 2

14 3 p5 a1 b2 2

15 3 p5 a1 b3 15

16 3 p6 a2 b1 3

17 3 p6 a2 b2 12

18 3 p6 a2 b3 1

sp.plot(plots$block, plots$A, plots$B, plots$yield)

ANALYSIS SPLIT PLOT: plots$yield

Class level information

plots$A : a1 a2

plots$B : b1 b2 b3

plots$block : 1 2 3

Number of observations: 18

Analysis of Variance Table

Response: plots$yield

Df Sum Sq Mean Sq F value Pr(>F)

plots$block 2 2.111 1.056 0.5135 0.6607143

plots$A 1 0.222 0.222 0.1081 0.7735446

Ea 2 4.111 2.056

plots$B 2 29.778 14.889 3.4581 0.0827438 .

plots$A:plots$B 2 300.444 150.222 34.8903 0.0001119 ***

Eb 8 34.444 4.306

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

cv(a) = 24.8 %, cv(b) = 35.9 %, Mean = 5.777778

R - Example For Split Split Plot Design ANOVA

Syntax

ssp.plot(repsblocks, mainplotfactor, subplotfactor, subsubplotfactor, response)

Note: Split Split Plot Design is an Extension of the Split Plot Design to Accommodate a Third Factor

Example

library("agricolae")

yield<-c(3.320,3.766,4.660,3.188,3.625,5.232,5.468,5.759,6.215,

4.246,5.255,6.829,3.132,5.389,5.217,3.864,4.311,5.915,4.752,

4.809,5.170,5.788,6.130,7.106,4.842,5.742,5.869,4.375,4.315,

5.389,4.507,4.875,5.400,4.756,5.295,6.046,4.422,5.308,6.318,

4.863,5.345,6.011,4.678,5.896,7.309,6.101,5.096,6.573,5.595,

6.357,7.016,5.442,6.398,6.953,6.209,6.992,7.565,6.860,6.857,

7.254,5.122,4.873,5.495,6.780,5.925,7.442,5.988,6.533,6.914,

6.768,7.856,7.626,6.894,6.974,7.812,4.815,4.166,4.225,5.390,

5.163,4.478,6.509,6.569,7.991,5.779,6.164,7.362,6.573,7.422,

8.950,5.355,7.442,7.018,6.706,8.592,8.480,8.452,8.662,9.112,

8.042,9.080,9.660,9.314,9.224,10.360,5.536,6.462,8.020,6.546,

7.646,9.942,6.698,8.526,9.140,7.414,9.016,8.966,8.508,9.680,

9.896,5.244,5.584,7.642,7.092,7.212,8.714,8.650,8.514,9.320,

6.902,7.778,9.128,8.032,9.294,9.712)

repsblocks<-rep(gl(3,15),3)

nitrogen<-rep(c(rep(0,3),rep(50,3),rep(80,3),rep(110,3),rep(140,3)),9)

management<-rep(c("m1","m2","m3"),45)

variety<-gl(3,45)

yield

[1] 3.320 3.766 4.660 3.188 3.625 5.232 5.468 5.759 6.215 4.246

[11] 5.255 6.829 3.132 5.389 5.217 3.864 4.311 5.915 4.752 4.809

[21] 5.170 5.788 6.130 7.106 4.842 5.742 5.869 4.375 4.315 5.389

[31] 4.507 4.875 5.400 4.756 5.295 6.046 4.422 5.308 6.318 4.863

[41] 5.345 6.011 4.678 5.896 7.309 6.101 5.096 6.573 5.595 6.357

[51] 7.016 5.442 6.398 6.953 6.209 6.992 7.565 6.860 6.857 7.254

[61] 5.122 4.873 5.495 6.780 5.925 7.442 5.988 6.533 6.914 6.768

[71] 7.856 7.626 6.894 6.974 7.812 4.815 4.166 4.225 5.390 5.163

[81] 4.478 6.509 6.569 7.991 5.779 6.164 7.362 6.573 7.422 8.950

[91] 5.355 7.442 7.018 6.706 8.592 8.480 8.452 8.662 9.112 8.042

[101] 9.080 9.660 9.314 9.224 10.360 5.536 6.462 8.020 6.546 7.646

[111] 9.942 6.698 8.526 9.140 7.414 9.016 8.966 8.508 9.680 9.896

[121] 5.244 5.584 7.642 7.092 7.212 8.714 8.650 8.514 9.320 6.902

[131] 7.778 9.128 8.032 9.294 9.712

repsblocks

[1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3

[38] 3 3 3 3 3 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2

[75] 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2

[112] 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3

Levels: 1 2 3

nitrogen

[1] 0 0 0 50 50 50 80 80 80 110 110 110 140 140 140 0 0 0

[19] 50 50 50 80 80 80 110 110 110 140 140 140 0 0 0 50 50 50

[37] 80 80 80 110 110 110 140 140 140 0 0 0 50 50 50 80 80 80

[55] 110 110 110 140 140 140 0 0 0 50 50 50 80 80 80 110 110 110

[73] 140 140 140 0 0 0 50 50 50 80 80 80 110 110 110 140 140 140

[91] 0 0 0 50 50 50 80 80 80 110 110 110 140 140 140 0 0 0

[109] 50 50 50 80 80 80 110 110 110 140 140 140 0 0 0 50 50 50

[127] 80 80 80 110 110 110 140 140 140

management

[1] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

[16] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

[31] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

[46] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

[61] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

[76] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

[91] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

[106] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

[121] "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3" "m1" "m2" "m3"

variety

[1] 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1

[38] 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2

[75] 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3

[112] 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3 3

Levels: 1 2 3

ssp.plot(repsblocks,nitrogen,management,variety,yield)

ANALYSIS SPLIT-SPLIT PLOT: yield

Class level information

nitrogen : 0 50 80 110 140

management : m1 m2 m3

variety : 1 2 3

repsblocks : 1 2 3

Number of observations: 135

Analysis of Variance Table

Response: yield

Df Sum Sq Mean Sq F value Pr(>F)

repsblocks 2 0.732 0.366 0.6578 0.543910

nitrogen 4 61.641 15.410 27.6953 9.734e-05 ***

Ea 8 4.451 0.556

management 2 42.936 21.468 81.9965 2.303e-10 ***

nitrogen:management 8 1.103 0.138 0.5266 0.822648

Eb 20 5.236 0.262

variety 2 206.013 103.007 207.8667 < 2.2e-16 ***

variety:nitrogen 8 14.145 1.768 3.5679 0.001916 **

variety:management 4 3.852 0.963 1.9432 0.114899

variety:nitrogen:management 16 3.699 0.231 0.4666 0.953759

Ec 60 29.732 0.496

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

cv(a) = 11.4 %, cv(b) = 7.8 %, cv(c) = 10.7 %, Mean = 6.554415

R - Example For Strip Plot (Split Block) Design

rowtrts = c("rtrt1", "rtrt2", "rtrt3", "rtrt4")

coltrts = c("ctrt1", "ctrt2", "ctrt3")

repsblocks = 2

result = design.strip(rowtrts, coltrts, repsblocks, randomization = FALSE)

result

$parameters

$parameters$design

[1] "strip"

$parameters$trt1

[1] "rtrt1" "rtrt2" "rtrt3" "rtrt4"

$parameters$trt2

[1] "ctrt1" "ctrt2" "ctrt3"

$parameters$r

[1] 2

$parameters$serie

[1] 2

$parameters$seed

[1] -1745342809

$parameters$kinds

[1] "Super-Duper"

$book

plots block rowtrts coltrts

1 101 1 rtrt1 ctrt1

2 102 1 rtrt1 ctrt2

3 103 1 rtrt1 ctrt3

4 104 1 rtrt2 ctrt1

5 105 1 rtrt2 ctrt2

6 106 1 rtrt2 ctrt3

7 107 1 rtrt3 ctrt1

8 108 1 rtrt3 ctrt2

9 109 1 rtrt3 ctrt3

10 110 1 rtrt4 ctrt1

11 111 1 rtrt4 ctrt2

12 112 1 rtrt4 ctrt3

13 201 2 rtrt1 ctrt1

14 202 2 rtrt1 ctrt2

15 203 2 rtrt1 ctrt3

16 204 2 rtrt2 ctrt1

17 205 2 rtrt2 ctrt2

18 206 2 rtrt2 ctrt3

19 207 2 rtrt3 ctrt1

20 208 2 rtrt3 ctrt2

21 209 2 rtrt3 ctrt3

22 210 2 rtrt4 ctrt1

23 211 2 rtrt4 ctrt2

24 212 2 rtrt4 ctrt3

R - Example For Strip Plot (Split Block) Design ANOVA

Syntax

strip.plot(repsblocks, columnfactor, rowfactor, response)

Note: Strip Plot Design ANOVA is suitable for measuring the interaction effects between column factor & row factor

Example

library("agricolae")

data(huasahuasi, package="agricolae")

huasahuasi$YIELD

block trt clon y1da y2da y3da

1 I 40mm C387164.4 22.75 5.50 4.14

2 I 40mm C386209.10 10.80 8.00 6.10

3 I 40mm Cruza148 1.60 11.70 4.15

4 I 40mm Yungay 10.92 9.90 5.20

5 I 40mm Musuq 3.50 5.10 2.40

6 I 7-days C387164.4 21.98 7.00 7.60

7 I 7-days C386209.10 10.50 12.50 3.60

8 I 7-days Cruza148 2.80 9.15 4.90

9 I 7-days Yungay 18.00 8.80 5.90

10 I 7-days Musuq 2.55 4.60 3.50

11 I Non-application C387164.4 29.30 2.50 6.50

12 I Non-application C386209.10 10.75 2.85 2.50

13 I Non-application Cruza148 10.50 6.30 4.20

14 I Non-application Yungay 8.45 6.60 5.60

15 I Non-application Musuq 0.00 0.80 1.65

16 II Non-application Musuq 0.00 0.00 0.40

17 II Non-application Yungay 5.50 6.10 2.15

18 II Non-application C386209.10 5.40 4.10 2.70

19 II Non-application Cruza148 6.30 7.10 5.80

20 II Non-application C387164.4 30.30 5.20 1.60

21 II 40mm Musuq 0.00 0.85 1.30

22 II 40mm Yungay 14.10 10.70 1.95

23 II 40mm C386209.10 12.00 3.80 3.10

24 II 40mm Cruza148 6.40 6.00 5.70

25 II 40mm C387164.4 46.60 4.10 2.40

26 II 7-days Musuq 6.00 3.60 2.30

27 II 7-days Yungay 14.30 5.90 2.70

28 II 7-days C386209.10 15.65 4.90 6.30

29 II 7-days Cruza148 5.00 7.30 8.00

30 II 7-days C387164.4 32.10 5.20 2.00

31 III 7-days C386209.10 10.40 8.35 3.05

32 III 7-days Musuq 0.70 2.70 3.70

33 III 7-days C387164.4 32.10 5.70 3.10

34 III 7-days Yungay 25.90 10.00 3.20

35 III 7-days Cruza148 9.30 8.60 3.55

36 III Non-application C386209.10 4.85 6.50 4.40

37 III Non-application Musuq 0.00 0.25 0.70

38 III Non-application C387164.4 29.20 5.50 4.65

39 III Non-application Yungay 13.70 12.10 1.10

40 III Non-application Cruza148 3.80 10.90 4.70

41 III 40mm C386209.10 5.10 5.85 3.20

42 III 40mm Musuq 0.50 1.00 1.10

43 III 40mm C387164.4 29.30 3.80 4.90

44 III 40mm Yungay 15.70 8.30 1.40

45 III 40mm Cruza148 8.10 10.60 5.80

yieldresponse = huasahuasi$YIELD$y1da + huasahuasi$YIELD$y2da + huasahuasi$YIELD$y3da

repsblocks = huasahuasi$YIELD$block

columnfactor = huasahuasi$YIELD$clon

rowfactor = huasahuasi$YIELD$trt

strip.plot(repsblocks, columnfactor, rowfactor, yieldresponse)

ANALYSIS STRIP PLOT: yieldresponse

Class level information

columnfactor : C387164.4 C386209.10 Cruza148 Yungay Musuq

rowfactor : 40mm 7-days Non-application

repsblocks : I II III

Number of observations: 45

model Y: yieldresponse ~ repsblocks + columnfactor + Ea + rowfactor + Eb + rowfactor:columnfactor + Ec

Analysis of Variance Table

Response: yieldresponse

Df Sum Sq Mean Sq F value Pr(>F)

repsblocks 2 7.5 3.75 0.2139 0.80970

columnfactor 4 5435.8 1358.96 36.2754 3.572e-05 ***

Ea 8 299.7 37.46 2.1343 0.09368 .

rowfactor 2 280.6 140.32 8.5361 0.03603 *

Eb 4 65.8 16.44 0.9365 0.46785

rowfactor:columnfactor 8 194.1 24.26 1.3821 0.27622

Ec 16 280.8 17.55

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

cv(a) = 27.7 %, cv(b) = 18.4 %, cv(c) = 19 %, Mean = 22.08644

R - Transformation - Examples For Absolute Value

abs(-16)

[1] 16

abs(16)

[1] 16

R - Transformation - Examples For Square Root

sqrt(16)

[1] 4

R - Transformation - Examples For Common Logarithm - Logarithm to Base 10

log10(1)

[1] 0

log10(10)

[1] 1

log10(100)

[1] 2

log10(1000)

[1] 3

log10(10000)

[1] 4

Note: Logarithmic scales reduce wide ranging quantities to tiny scopes

R - Transformation - Examples For Binary Logarithm - Logarithm to Base 2

log2(1)

[1] 0

log2(10)

[1] 3.321928

log2(100)

[1] 6.643856

log2(1000)

[1] 9.965784

log2(10000)

[1] 13.28771

R - Transformation - Examples For Natural Logarithm - Logarithm to Base e (e = exp(1) ~ 2.71828)

e = Euler's number = Napier's constant

log(10)

[1] 2.302585

log(100)

[1] 4.60517

log(1000)

[1] 6.907755

log(10000)

[1] 9.21034

log(1)

[1] 0

R - Transformation - Examples For Exponential Function

(Inverse of exponential function is natural logarithmic function)

exp(2.302585)

[1] 9.999999

exp(4.60517)

[1] 99.99998

exp(6.907755)

[1] 999.9997

exp(9.21034)

[1] 9999.996

exp(0)

[1] 1

R - Transformation - Example For Logit & Inverse Logit

library("gtools")

dataforlogit=.1*1:9

dataforlogit

[1] 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

logitresult=logit(dataforlogit)

logitresult

[1] -2.1972246 -1.3862944 -0.8472979 -0.4054651 0.0000000 0.4054651 0.8472979

[8] 1.3862944 2.1972246

inv.logit(logitresult)

[1] 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9

R - Transformation - Examples For Arc-Sine

asin(0)

[1] 0

asin(0.1)

[1] 0.1001674

asin(0.2)

[1] 0.2013579

asin(0.3)

[1] 0.3046927

asin(0.4)

[1] 0.4115168

asin(0.5)

[1] 0.5235988

asin(0.6)

[1] 0.6435011

asin(0.7)

[1] 0.7753975

asin(0.8)

[1] 0.9272952

asin(0.9)

[1] 1.11977

asin(1)

[1] 1.570796

R - Transformation - Examples For Sine

sin(0)

[1] 0

sin(0.1001674)

[1] 0.09999998

sin(0.2013579)

[1] 0.2

sin(0.3046927)

[1] 0.3

sin(0.4115168)

[1] 0.4

sin(0.5235988)

[1] 0.5

sin(0.6435011)

[1] 0.6

sin(0.7753975)

[1] 0.7

sin(0.9272952)

[1] 0.8

sin(1.11977)

[1] 0.9000002

sin(1.570796)

[1] 1

R - Example For Chi-square Goodness of Fit Test

library("stats")

x = c(89,37,30,28,2)

chisq.test(x, p = c(40,20,20,15,5), rescale.p = TRUE)

Chi-squared test for given probabilities

data: x

X-squared = 9.9901, df = 4, p-value = 0.04059

Note:

The test is applied when you have one variable from a single population

It is used to determine whether sample data (observed frequencies) are consistent with a hypothesized distribution (expected frequencies)

R - Example For Chi-squared Contingency Table Tests (Chi-square Test of Independence)

library("stats")

M = as.table(rbind(c(762, 327, 468), c(484, 239, 477)))

dimnames(M) = list(gender = c("F", "M"), party = c("Democrat","Independent", "Republican"))

M

party

gender Democrat Independent Republican

F 762 327 468

M 484 239 477

Xsq=chisq.test(M)

Xsq

Pearson's Chi-squared test

data: M

X-squared = 30.07, df = 2, p-value = 2.954e-07

Xsq$observed

party

gender Democrat Independent Republican

F 762 327 468

M 484 239 477

Xsq$expected

party

gender Democrat Independent Republican

F 703.6714 319.6453 533.6834

M 542.3286 246.3547 411.3166

Xsq$residuals

party

gender Democrat Independent Republican

F 2.1988558 0.4113702 -2.8432397

M -2.5046695 -0.4685829 3.2386734

Xsq$stdres

party

gender Democrat Independent Republican

F 4.5020535 0.6994517 -5.3159455

M -4.5020535 -0.6994517 5.3159455

R - Example For Simple Plot Using Dots

plot(PlantGrowth$weight)

R - Example For Simple Plot Using Lines

plot(PlantGrowth$weight, type=”l”)

R - Example For Simple Plot Using Both Lines & Dots

plot(PlantGrowth$weight, type=”b”)

R - Example For Simple Plot Using Vertical Lines

plot(PlantGrowth$weight, type=”h”)

R - Example For Simple Plot Using Steps

plot(PlantGrowth$weight, type=”s”)

R - Example For Scatter Plot Using Dots

plot(age~circumference, Orange)

Note: 1st Variable in Vertical Axes & 2nd Variable in Horizontal Axes

R - Example For Scatter Plot Using Lines

plot(age~circumference, Orange, type=”l”))

Note: 1st Variable in Vertical Axes & 2nd Variable in Horizontal Axes

R - Example For Scatter Plot Using Both Dots & Lines

plot(age~circumference, Orange, type=”b”))

Note: 1st Variable in Vertical Axes & 2nd Variable in Horizontal Axes

R - Example For Histogram

hist(PlantGrowth$weight)

R - Example For Pie Plot

pie(table(Orange$age))

R - Example For Clustered Vertical Bar Plot / Column Chart

Population = data.frame(

row.names=c("Year1970", "Year1980", "Year1990", "Year2000", "Year2010"),

India=c(45, 47, 40, 34, 33),

Japan=c(38, 34, 38, 28, 29),

US=c(32, 31, 28, 47, 46),

UK=c(27, 26, 25, 36, 38),

China=c(30, 33, 24, 37, 32))

Population

India Japan US UK China

Year1970 45 38 32 27 30

Year1980 47 34 31 26 33

Year1990 40 38 28 25 24

Year2000 34 28 47 36 37

Year2010 33 29 46 38 32

barplot(as.matrix(Population),beside=T,legend=row.names(Population))

R - Examples of Saving the Plot in the Active Device Window as Image

savePlot("graph1.png", type="png")

savePlot("graph1.jpg", type="jpeg")

savePlot("graph1.tif", type="tiff")

R - Example For Least Significant Difference (LSD) Test / Critical Difference (CD)

p (p-value) = Probability

alpha = Threshold Value For p = Significance Level of the Test - Often Set to 0.05 (5%) or 0.01 (1%) or 0.1 (10%)

H₀ - Null Hypothesis - Assumes No (Null) Relationship Exists Among Groups in the Population

---

In ANOVA (Analysis of Variance)

If ( p < alpha )

Significant

Significantly Different

Null Hypothesis Rejected

Relationship Exists Among Groups in the Population

Proceed With LSD For Finding Which Group Having Relationship With Which Other Group(s) in the Population

Else

Non Significant

Groups Are Not Significantly Different

No (Null) Relationship Exists Among Groups in the Population

Null Hypothesis Accepted

---

Syntax

LSD.test(Response, Treatments, Residuals Degrees of Freedom From ANOVA, Residuals Mean Square From ANOVA, alpha = 0.05)

- - -

Density of 5 Ponds

density ponds

28.2 pond1

33.2 pond1

36.4 pond1

34.6 pond1

29.1 pond1

31 pond1

39.6 pond2

40.8 pond2

37.9 pond2

37.1 pond2

43.6 pond2

42.4 pond2

46.3 pond3

42.1 pond3

43.5 pond3

48.8 pond3

43.7 pond3

40.1 pond3

41 pond4

44.1 pond4

46.4 pond4

40.2 pond4

38.6 pond4

36.3 pond4

56.3 pond5

54.1 pond5

59.4 pond5

62.7 pond5

60 pond5

57.3 pond5

---

Select the above data kept in LibreOffice Calc > Right click over the selection > Context menu appears > Select Copy

water = read.table("clipboard",header=T)

summary(aov(density~ponds, data=water))

Df Sum Sq Mean Sq F value Pr(>F)

ponds 4 2193.4 548.4 56.16 3.95e-12 ***

Residuals 25 244.1 9.8

---

Signif. codes: 0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

library("agricolae")

result = LSD.test(water$density, water$ponds, 25, 9.8, alpha = 0.05)

result

$statistics

Mean CV MSerror LSD

43.16 7.253233 9.8 3.722394

$parameters

Df ntr t.value alpha test name.t

25 5 2.059539 0.05 Fisher-LSD water$ponds

$means

water$density std r LCL UCL Min Max

pond1 32.08333 3.205256 6 29.45120 34.71546 28.2 36.4

pond2 40.23333 2.530349 6 37.60120 42.86546 37.1 43.6

pond3 44.08333 3.080530 6 41.45120 46.71546 40.1 48.8

pond4 41.10000 3.666061 6 38.46787 43.73213 36.3 46.4

pond5 58.30000 3.036445 6 55.66787 60.93213 54.1 62.7

$comparison

NULL

$groups

trt means M

1 pond5 58.30000 a

2 pond3 44.08333 b

3 pond4 41.10000 bc

4 pond2 40.23333 c

5 pond1 32.08333 d

R - To get help in browser instead of the in-build R (in Ubuntu 14.04.1)

Run the below commands in R prompt > to switch between open help in default browser or help in in-build R helper terminal

options(help_type = "html")

options(help_type = "text")

options(help_type = "pdf")

Note:

texinfo - needed to avoid error "/usr/bin/texi2dvi: not found" while giving help like "?sink" in R, after command "options(help_type = "pdf")"

Even after installing above texinfo, gives error "Error in texi2dvi(file = file, pdf = TRUE", in Ubuntu 14.04.1

which may be related to error "Dates is specific format in header settings prevent rendering to PDF"

If No Proxy, then it should also have 127.0.0.1 in No Proxy for html to work

R - To get help / the manual about working function "aov"

R - To Find, in Which Package, Working Function "aov" is

?aov

R - To search all help topics with the word related to "ao"

R - To Find, Which All Are The Packages Having Function with Name Similar To "ao"

??ao

R - To change R fix() function editor vim to nano (in Ubuntu 14.04.1)

Run the below commands in R prompt

options(editor="nano")

R - To Scroll Back & View More Number of Previous Output (in Ubuntu 14.04.1)

Dash > R (Console (or Terminal) > Edit > Profile Preferences > Scrolling > Scrollback (default 512) lines > Select Unlimited

R - Example of Running system / terminal commands like "clear" inside R

system("clear")

R - To Install Additional Package (By Selection) Through Internet

install.packages()

R - Example For Installing a Particular Additional Package Through Internet

install.packages("agricolae")

R - To Install Additional Package Without Internet

(.tar.gz Package Files Are Kept Locally in $HOME/packages/ Along With Dependecny Package Files)

Step 1: Create index files (PACKAGES, PACKAGES.gz) for all source package files (.tar.gz) kept in $HOME/packages/ (Creating a Local Repository)

library(tools)

write_PACKAGES("./packages/")

Step 2: Installing Locally Kept Package Along With Dependency Packages

install.packages("packagename", contriburl="file:///path/to/packages/")

Example For Above Command

install.packages("agricolae", contriburl="file:///home/supreme/packages/")

Note:

R Additional Packages Can Be Downloaded From URL - https://cran.r-project.org/src/contrib/

or

From A Computer /tmp/.../downloaded_packages/ Folder Where it is Installed Using Internet (Will Get Deleted on Restart)

R - To Display R Version, Platform, Attached, Loaded (and Not Attached) Packages

sessionInfo()

R - To List All Loaded Packages

loadedNamespaces()

R - To List All Loaded & Attached Packages (To List Packages Included in The Search Path)

search()

R - To List All Installed Packages

library()

.packages(all.available = TRUE)

R - Example - To Load and Attach an Installed Package

library("agricolae")

R - Example - To Detach & Try To Unload a Loaded & Attached Package

detach(package:agricolae, unload=TRUE)

R - To List Available Datasets, Excluding Datasets From Unloaded Pacakges

data()

R - To List Available Datasets, Including Datasets From Unloaded Packages

data(package = .packages(all.available = TRUE))

R - Example of Listing All Datasets Available in a Package (Even if Not Loaded)

data(package="agricolae")

R - Example of Loading Specific Dataset From a Specific Package

Method 1:

data(plots, package="agricolae")

Method 2:

library("agricolae")

data(plots)

R - Example of Getting Information About a Dataset

?Orange

R - Example For Creating / Testing Time Series Objects

Syntax

ts(data, frequency, start)

start: time of the first observation

end: time of the last observation

data: a vector or matrix of the observed time-series values

frequency: the number of observations per unit of time

Example 1:

x = ts(c(3,4,5,6,8,11,12,13,14), frequency = 4, start = c(2016, 2))

x

Qtr1 Qtr2 Qtr3 Qtr4

2016 3 4 5

2017 6 8 11 12

2018 13 14

is.ts(x)

[1] TRUE

Example 2:

x = ts(c(3,4,5,6,8,11,12,13,14), frequency = 12, start = c(2016, 2))

x

Feb Mar Apr May Jun Jul Aug Sep Oct

2016 3 4 5 6 8 11 12 13 14

is.ts(x)

[1] TRUE

Example 3:

x = ts(c(3,4,5,6,8,11,12,13,14), frequency = 3, start = c(2016, 2))

x

Time Series:

Start = c(2016, 2)

End = c(2019, 1)

Frequency = 3

[1] 3 4 5 6 8 11 12 13 14

is.ts(x)

[1] TRUE

R - Example For AutoRegressive (AR) Modelling of Time Series & Predicting

sunspot.year

Time Series:

Start = 1700

End = 1988

Frequency = 1

[1] 5.0 11.0 16.0 23.0 36.0 58.0 29.0 20.0 10.0 8.0 3.0 0.0

[13] 0.0 2.0 11.0 27.0 47.0 63.0 60.0 39.0 28.0 26.0 22.0 11.0

[25] 21.0 40.0 78.0 122.0 103.0 73.0 47.0 35.0 11.0 5.0 16.0 34.0

[37] 70.0 81.0 111.0 101.0 73.0 40.0 20.0 16.0 5.0 11.0 22.0 40.0

[49] 60.0 80.9 83.4 47.7 47.8 30.7 12.2 9.6 10.2 32.4 47.6 54.0

[61] 62.9 85.9 61.2 45.1 36.4 20.9 11.4 37.8 69.8 106.1 100.8 81.6

[73] 66.5 34.8 30.6 7.0 19.8 92.5 154.4 125.9 84.8 68.1 38.5 22.8

[85] 10.2 24.1 82.9 132.0 130.9 118.1 89.9 66.6 60.0 46.9 41.0 21.3

[97] 16.0 6.4 4.1 6.8 14.5 34.0 45.0 43.1 47.5 42.2 28.1 10.1

[109] 8.1 2.5 0.0 1.4 5.0 12.2 13.9 35.4 45.8 41.1 30.1 23.9

[121] 15.6 6.6 4.0 1.8 8.5 16.6 36.3 49.6 64.2 67.0 70.9 47.8

[133] 27.5 8.5 13.2 56.9 121.5 138.3 103.2 85.7 64.6 36.7 24.2 10.7

[145] 15.0 40.1 61.5 98.5 124.7 96.3 66.6 64.5 54.1 39.0 20.6 6.7

[157] 4.3 22.7 54.8 93.8 95.8 77.2 59.1 44.0 47.0 30.5 16.3 7.3

[169] 37.6 74.0 139.0 111.2 101.6 66.2 44.7 17.0 11.3 12.4 3.4 6.0

[181] 32.3 54.3 59.7 63.7 63.5 52.2 25.4 13.1 6.8 6.3 7.1 35.6

[193] 73.0 85.1 78.0 64.0 41.8 26.2 26.7 12.1 9.5 2.7 5.0 24.4

[205] 42.0 63.5 53.8 62.0 48.5 43.9 18.6 5.7 3.6 1.4 9.6 47.4

[217] 57.1 103.9 80.6 63.6 37.6 26.1 14.2 5.8 16.7 44.3 63.9 69.0

[229] 77.8 64.9 35.7 21.2 11.1 5.7 8.7 36.1 79.7 114.4 109.6 88.8

[241] 67.8 47.5 30.6 16.3 9.6 33.2 92.6 151.6 136.3 134.7 83.9 69.4

[253] 31.5 13.9 4.4 38.0 141.7 190.2 184.8 159.0 112.3 53.9 37.5 27.9

[265] 10.2 15.1 47.0 93.8 105.9 105.5 104.5 66.6 68.9 38.0 34.5 15.5

[277] 12.6 27.5 92.5 155.4 154.7 140.5 115.9 66.6 45.9 17.9 13.4 29.2

[289] 100.2

arsunspot = ar(sunspot.year)

arsunspot

Call:

ar(x = sunspot.year)

Coefficients:

1 2 3 4 5 6 7 8

1.1305 -0.3524 -0.1745 0.1403 -0.1358 0.0963 -0.0556 0.0076

9

0.1941

Order selected 9 sigma^2 estimated as 267.5

predict(arsunspot, n.ahead = 25)

$pred

Time Series:

Start = 1989

End = 2013

Frequency = 1

[1] 135.25933 148.09051 133.98476 106.61344 71.21921 40.84057 18.70100

[8] 11.52416 27.24208 56.99888 87.86705 107.62926 111.05437 98.05484

[15] 74.84085 48.80128 27.65441 18.15075 23.15355 40.04723 61.95906

[22] 80.79092 90.11420 87.44131 74.42284

$se

Time Series:

Start = 1989

End = 2013

Frequency = 1

[1] 16.35519 24.68467 28.95653 29.97401 30.07714 30.15629 30.35971 30.58793

[9] 30.71100 30.74276 31.42565 32.96467 34.48910 35.33601 35.51890 35.52034

[17] 35.65505 35.90628 36.07084 36.08139 36.16818 36.56324 37.16527 37.64820

[25] 37.83954

Note: $pred - Prediction, $se - Standard Error

R - Example For Moving Average

Syntax

SMA(x, n)

x: Price, Volume, etc... Data Series

n: Number of Periods To Average Over

Note: SMA - Simple Moving Average Calculates the Average of the Series Over the Past n Observations

Example

library("TTR")

data("ttrc")

x = ttrc$Close[1:50]

x

[1] 3.08 3.11 3.09 3.10 3.11 3.16 3.22 3.23 3.32 3.30 3.32 3.26 3.16 3.25 3.29

[16] 3.31 3.32 3.37 3.42 3.42 3.44 3.41 3.40 3.43 3.46 3.39 3.43 3.47 3.48 3.50

[31] 3.58 3.54 3.51 3.49 3.48 3.46 3.46 3.45 3.50 3.49 3.51 3.55 3.48 3.49 3.44

[46] 3.40 3.40 3.39 3.42 3.37

SMA(x, 20)

[1] NA NA NA NA NA NA NA NA NA NA

[11] NA NA NA NA NA NA NA NA NA 3.2420

[21] 3.2600 3.2750 3.2905 3.3070 3.3245 3.3360 3.3465 3.3585 3.3665 3.3765

[31] 3.3895 3.4035 3.4210 3.4330 3.4425 3.4500 3.4570 3.4610 3.4650 3.4685

[41] 3.4720 3.4790 3.4830 3.4860 3.4850 3.4855 3.4840 3.4800 3.4770 3.4705

mean(x[1:20])

[1] 3.242

mean(x[2:21])

[1] 3.26

R - Example For ARIMA (AutoRegressive Integrated Moving Average) Modelling of Time Series & Predicting

lh

Time Series:

Start = 1

End = 48

Frequency = 1

[1] 2.4 2.4 2.4 2.2 2.1 1.5 2.3 2.3 2.5 2.0 1.9 1.7 2.2 1.8 3.2 3.2 2.7 2.2 2.2

[20] 1.9 1.9 1.8 2.7 3.0 2.3 2.0 2.0 2.9 2.9 2.7 2.7 2.3 2.6 2.4 1.8 1.7 1.5 1.4

[39] 2.1 3.3 3.5 3.5 3.1 2.6 2.1 3.4 3.0 2.9

arimalh = arima(lh, order = c(3,0,0))

arimalh