Class 7

> getwd()
[1] "C:/Users/user/Documents"
> setwd(C:/Users/user/Desktop/R)
Error: unexpected '/' in "setwd(C:/"
> setwd("C:/Users/user/Desktop/R")
> getwd()
[1] "C:/Users/user/Desktop/R"
> bdt = read.csv("BschoolData.csv", header=TRUE)
> bdt
Student Salary.000
1 1 750
2 2 600
3 3 600
4 4 650
5 5 700
6 6 780
7 7 860
8 8 810
9 9 780
10 10 670
11 11 690
12 12 550
13 13 610
14 14 715
15 15 755
16 16 770
17 17 680
18 18 670
19 19 740
20 20 760
21 21 775
22 22 845
23 23 870
24 24 640
25 25 690
26 26 715
27 27 630
28 28 685
29 29 780
30 30 635
> head(bdt)
Student Salary.000
1 1 750
2 2 600
3 3 600
4 4 650
5 5 700
6 6 780
> plot (bdt, col ="orange", type ="h", lwd = 3, main = "package for 30 students")
Warning messages:
1: graphical parameter "type" is obsolete
2: graphical parameter "type" is obsolete
> abline ( h = mean (sa), lty = 4, col= "green")
> abline ( h = t5avgsal , lty = 4, col= "blue")
> abline ( h = median(sa) , lty = 4, col= "blue")
> abline ( h = median(sa) , lty = 4, col= "red")

> require ("psych")
Loading required package: psych
> summary (sa)
Min. 1st Qu. Median Mean 3rd Qu. Max.
550.0 655.0 707.5 713.5 773.8 870.0
> describe (sa)
vars n mean sd median trimmed mad min max range skew
X1 1 30 713.5 81.26 707.5 711.67 96.37 550 870 320 0.08
kurtosis se
X1 -0.83 14.84
ONE SAMPLE T-TEST
> t.test (sa, mu = 750)
One Sample t-test
data: sa
t = -2.4601, df = 29, p-value = 0.02009
alternative hypothesis: true mean is not equal to 750
95 percent confidence interval:
683.1558 743.8442
sample estimates:
mean of x
713.5
> t.test (sa, mu = 100)
One Sample t-test

data: sa
t = 41.351, df = 29, p-value < 2.2e-16
683.1558 743.8442
sample estimates:
mean of x
713.5
> t.test (sa, mu = 500)
One Sample t-test
data: sa
t = 14.39, df = 29, p-value = 9.751e-15
683.1558 743.8442
sample estimates:
mean of x
713.5
> t.test (sa, mu = 713.5)
One Sample t-test
data: sa
t = 0, df = 29, p-value = 1
alternative hypothesis: true mean is not equal to 713.5

683.1558 743.8442
sample estimates:
mean of x
713.5
> t.test (sa, mu = 750, conf.level = 0.99)
One Sample t-test
data: sa
t = -2.4601, df = 29, p-value = 0.02009
672.6047 754.3953
sample estimates:
mean of x
713.5
> mdt = read.csv("MinersData.csv",header = TRUE)
> mdt
Worker Mine Output
1 1 1 48
2 2 1 45
3 3 1 33
4 4 1 39
5 5 1 34
6 6 1 49
7 7 1 33
8 8 1 45
9 9 1 48
10 10 1 44
11 11 1 45
12 12 1 45
13 13 1 36
14 14 1 48
15 15 1 41
16 16 1 47
17 17 1 39
18 18 1 49
19 19 1 38
20 20 1 45
21 21 2 42
22 22 2 44
23 23 2 41
24 24 2 39
25 25 2 35
26 26 2 34
27 27 2 33
28 28 2 36
29 29 2 37
30 30 2 37
31 31 2 41
32 32 2 42
33 33 2 39
34 34 2 38
35 35 2 38
36 36 2 39
37 37 2 41
38 38 2 40
39 39 2 41
40 40 2 40
41 41 2 38
42 42 2 41
43 43 2 43
44 44 2 40
> head (mdt)
Worker Mine Output
1 1 1 48
2 2 1 45
3 3 1 33
4 4 1 39
5 5 1 34
6 6 1 49
> tail (mdt)
Worker Mine Output
39 39 2 41
40 40 2 40
41 41 2 38
42 42 2 41
43 43 2 43
44 44 2 40
> attach (mdt)
> attributes (mdt)
$names
[1] "Worker" "Mine" "Output"

$class
[1] "data.frame"
$row.names
[1] 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
[22] 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42
[43] 43 44
> subset (Mine)
Error in subset.default(Mine) :
argument "subset" is missing, with no default
> mdt1 = subset (mdt, Mine==1)
> mdt2 = subset (mdt, Mine==2)
> mdt1
Worker Mine Output
1 1 1 48
2 2 1 45
3 3 1 33
4 4 1 39
5 5 1 34
6 6 1 49
7 7 1 33
8 8 1 45
9 9 1 48
10 10 1 44
11 11 1 45
12 12 1 45
13 13 1 36
14 14 1 48
15 15 1 41
16 16 1 47
17 17 1 39
18 18 1 49
19 19 1 38
20 20 1 45
> mdt2
Worker Mine Output
21 21 2 42
22 22 2 44
23 23 2 41
24 24 2 39
25 25 2 35
26 26 2 34
27 27 2 33
28 28 2 36
29 29 2 37
30 30 2 37
31 31 2 41
32 32 2 42
33 33 2 39
34 34 2 38
35 35 2 38
36 36 2 39
37 37 2 41
38 38 2 40
39 39 2 41
40 40 2 40
41 41 2 38
42 42 2 41
43 43 2 43
44 44 2 40
> plot (Output, col = "red", type = "l")
> attach (mdt1)
The following objects are masked from mdt:
Mine, Output, Worker
> attach (mdt2)
The following objects are masked from mdt1:
> points (Output, col = "red", type = "l")
> dev.off()
null device
> attach (mdt1)
The following objects are masked from mdt1 (pos = 4):

> par (mfrow = c(1,2))
> attach (mdt1)
> plot (Output, col = "red",type = "h", lwd = 3)
> attach (mdt2)

> plot (Output, col = "blue",type = "h", lwd = 3)
> attach (mdt)
> describeBy (mdt, Mine)
Descriptive statistics by group
group: 1
Worker 1 20 10.50 5.92 10.5 10.50 7.41 1 20 19 0.0
Mine 2 20 1.00 0.00 1.0 1.00 0.00 1 1 0 NaN
Output 3 20 42.55 5.48 45.0 42.94 5.19 33 49 16 -0.5

kurtosis se
Worker -1.38 1.32
Mine NaN 0.00
Output -1.27 1.23
--------------------------------------------------
group: 2
Worker 1 24 32.50 7.07 32.5 32.50 8.90 21 44 23 0.00
Mine 2 24 2.00 0.00 2.0 2.00 0.00 2 2 0 NaN
Output 3 24 39.12 2.79 39.5 39.25 2.22 33 44 11 -0.45
kurtosis se
Worker -1.35 1.44
Mine NaN 0.00
Output -0.57 0.57
Two Sample t-test

t.test (Output~Mine)
Welch Two Sample t-test
data: Output by Mine
t = 2.5345, df = 27.03, p-value = 0.01736
alternative hypothesis: true difference in means is not equal to 0
0.65244 6.19756
sample estimates:
mean in group 1 mean in group 2
42.550 39.125
PAIRED SAMPLE TEST
> data = read.csv ("BT_AT_Data.csv", header = TRUE)
> data
Employee Ef.Bt Ef.At
1 1 41 44
2 2 35 36
3 3 40 48
4 4 50 47
5 5 39 40
6 6 45 52
7 7 35 35
8 8 36 51
9 9 44 46
10 10 40 55
11 11 46 39
12 12 42 40
13 13 37 36
14 14 34 39
15 15 38 50
16 16 42 46
17 17 46 49
18 18 39 42
19 19 40 51
20 20 45 37
> attach (data)
> t.test (Ef.Bt, Ef.At, paired = TRUE)
Paired t-test
data: Ef.Bt and Ef.At
t = -2.3913, df = 19, p-value = 0.02729
alternative hypothesis: true difference in means is not equal to 0
-6.4696523 -0.4303477
sample estimates:
mean of the differences
-3.45
> data = read.csv ("BT_AT_Data.csv", header = TRUE)
> data
Employee Ef.Bt Ef.At Difference
1 1 41 44 -3
2 2 35 36 -1
3 3 40 48 -8
4 4 50 47 3
5 5 39 40 -1
6 6 45 52 -7
7 7 35 35 0
8 8 36 51 -15
9 9 44 46 -2
10 10 40 55 -15
11 11 46 39 7
12 12 42 40 2
13 13 37 36 1
14 14 34 39 -5
15 15 38 50 -12
16 16 42 46 -4
17 17 46 49 -3
18 18 39 42 -3
19 19 40 51 -11
20 20 45 37 8
> attach (data)
The following objects are masked from data (pos = 3):
Difference, Ef.At, Ef.Bt, Employee

The following objects are masked from data (pos = 4):
Ef.At, Ef.Bt, Employee
> barplot (Difference, col ="orange")
> barplot (Difference, col ="orange", xlab = "Employee", ylab = "Difference between before and after")
> barplot (Difference, col ="orange", xlab = "Employee", ylab = "Difference between before and after",
main = "Effectiveness of training")
> t.test (Difference)
One Sample t-test
data: Difference
t = -2.3913, df = 19, p-value = 0.02729
-6.4696523 -0.4303477
sample estimates:
mean of x
-3.45
>

Class 7

Uploaded by

Copyright:

Available Formats

Class 7

Uploaded by

Document Information

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

Class 7

Uploaded by

Copyright:

Available Formats

> getwd()

Error: unexpected '/' in "setwd(C:/"

> bdt = read.csv("BschoolData.csv", header=TRUE)

1: graphical parameter "type" is obsolete

2: graphical parameter "type" is obsolete

> abline ( h = mean (sa), lty = 4, col= "green")

> abline ( h = t5avgsal , lty = 4, col= "blue")

> abline ( h = median(sa) , lty = 4, col= "blue")

> abline ( h = median(sa) , lty = 4, col= "red")

Loading required package: psych

> summary (sa)

Min. 1st Qu. Median Mean 3rd Qu. Max.

550.0 655.0 707.5 713.5 773.8 870.0

> describe (sa)

vars n mean sd median trimmed mad min max range skew

X1 1 30 713.5 81.26 707.5 711.67 96.37 550 870 320 0.08

ONE SAMPLE T-TEST

> t.test (sa, mu = 750)

One Sample t-test

t = -2.4601, df = 29, p-value = 0.02009

alternative hypothesis: true mean is not equal to 750

95 percent confidence interval:

> t.test (sa, mu = 100)

One Sample t-test

t = 41.351, df = 29, p-value < 2.2e-16

alternative hypothesis: true mean is not equal to 100

95 percent confidence interval:

> t.test (sa, mu = 500)

One Sample t-test

t = 14.39, df = 29, p-value = 9.751e-15

alternative hypothesis: true mean is not equal to 500

95 percent confidence interval:

> t.test (sa, mu = 713.5)

One Sample t-test

alternative hypothesis: true mean is not equal to 713.5

> t.test (sa, mu = 750, conf.level = 0.99)

One Sample t-test

t = -2.4601, df = 29, p-value = 0.02009

alternative hypothesis: true mean is not equal to 750

99 percent confidence interval:

> mdt = read.csv("MinersData.csv",header = TRUE)

Worker Mine Output

> head (mdt)

Worker Mine Output

> tail (mdt)

Worker Mine Output

> attach (mdt)

> attributes (mdt)

[1] "Worker" "Mine" "Output"

> subset (Mine)

argument "subset" is missing, with no default

> mdt1 = subset (mdt, Mine==1)

> mdt2 = subset (mdt, Mine==2)

Worker Mine Output

Worker Mine Output

> plot (Output, col = "red", type = "l")

> attach (mdt1)

The following objects are masked from mdt:

Mine, Output, Worker