Name: Kalash Poudel Roll No.

: 6

TABLE OF CONTENT

S.N. Title Signature

1 Confidence Interval of Mean

2 Z-Test of Single Mean

3 Z-Test of Difference of Two Sample Mean

4 Paired t-Test

5 t-test of difference of mean

6 KS-One Sample Test

7 Chi-Square Test

8 Partial Correlation

9 Multiple Regression

10 Design of Experiment (CRD)

11 Design of Experiment (RBD)

12 Design of Experiment (LSD)

Name: Kalash Poudel Roll No.: 6

Use of Excel Inbuilt analysis tools:

Name: Kalash Poudel Roll No.: 6
Name: Kalash Poudel Roll No.: 6

EXPERIMENT NO. 1

Confidence Interval of Mean

QUESTION:

If the population standard deviation of 3.2 of a sample size of 100 is drawn

from a population whose sample mean is 25. Find the 95% confidence
interval for the population mean.

SOLUTION:

Symbol Value Formula Used

Standard Deviation of σ 3.2
Population
Sample Size n 100
Sample Mean x̄ 25

Level of Significance 𝛂 0.05 1(100%) - 95%

Confidence Interval At CI 0.627188475 CONFIDENCE(𝛂, σ , n)

95%:
Upper Limit 25.62718848 x̄ + CI
Lower Limit 24.37281152 x̄ - CI

CONCLUSION:

Hence, the confidence interval is (24.37281152, 25.62718848)

Symbol Value Formula

Standard Deviation Of σ 3.2
Population
Sample Size n 100
Sample Mean x̄ 25

Level of Significance 𝛂 0.05 1(100%) - 95%

Confidence Interval At CI 0.627188475 CONFIDENCE(𝛂, σ ,

95%: n)
Upper Limit 25.62718848 x̄ + CI
Name: Kalash Poudel Roll No.: 6

24.37281152 x̄ - CI

EXPERIMENT NO. 2

Z-Test of Single Mean

QUESTION:

A sample of 400 students is found to have a mean height of 170 cm. Can it
be reasonably regarded as a sample from a large population with a mean
height of 169.5 cm and a standard deviation of 3.5?

SOLUTION:

Symbol Value Formula Used

Sample Size n 400
Sample Mean x̄ 170
Population Mean μ 169.5
Population Standard σ 3.5
Deviation
Level of Significance 𝛂 0.05

Null Hypothesis H0
Alternative Hypothesis H1

Z Value ZCal 2.857142857 (x̄ - μ) / (σ / SQRT(n))

Critical Value ZTab 1.959963985 NORM.S.INV((1- 𝛂/2))

HYPOTHESIS:
Name: Kalash Poudel Roll No.: 6

 H0: The mean height of students is 169.5 cm. (μ = 169.5)

 H1: The mean height of students is not 169.5 cm. (μ ≠ 169.5)

DECISION: Since | ZCal | > | ZTab |, Accept H1.

CONCLUSION:

The mean height of students is not 169.5.

EXPERIMENT NO. 3

Z-Test of Difference of Two Sample Mean

QUESTION:

Test whether two sample means are significantly different if selected from a
population with standard deviation 840 and 920 respectively with the
following score values.

X Y
52 22
27 34
2 8
49 83
76 68
72 64
77 115
71 57
95 32
55 99
68 98
29 29
97 38
17 96
98 92
Name: Kalash Poudel Roll No.: 6

SOLUTION:

HYPOTHESIS:

 H0: Two Sample Means are not significantly different.

 H1: Two Sample Means are significantly different.

z-Test: Two Sample for Means

X Y
Mean 59 62.33333333
Known Variance 840 920
Observations 15 15
Hypothesized Mean Difference 0
z -0.307728727
P(Z<=z) one-tail 0.379144379
z Critical one-tail 1.644853627
P(Z<=z) two-tail 0.758288758
z Critical two-tail 1.959963985

So, from the table:

ZTab = 1.959963985

ZCal = -0.307728727

DECISION: Since | ZCal | < | ZTab |, Accept H0.

CONCLUSION:

The two Sample Means are not significantly different.

Name: Kalash Poudel Roll No.: 6

EXPERIMENT NO. 4
Paired t-Test

QUESTION:

An IQ test was administered to five persons before and after they were given
Horlicks. The result is given below:

Candidates 1 2 3 4 5
IQ Before Horlicks 110 120 123 132 125
IQ After Horlicks 120 118 125 136 121

Test whether there is any change in IQ after the Horlicks at a 1% level of

significance.

SOLUTION:

t-Test: Paired Two Sample for Means

IQ Before Horlicks IQ After Horlicks

Mean 122 124
Variance 64.5 51.5
Observations 5 5
Pearson Correlation 0.746079288
Hypothesized Mean Difference 0
df 4
t Stat -0.816496581
Name: Kalash Poudel Roll No.: 6

P(T<=t) one-tail 0.230025376

t Critical one-tail 3.746947388
P(T<=t) two-tail 0.460050753
t Critical two-tail 4.604094871

HYPOTHESIS:

 H0: There is no change in IQ after Horlicks.

 H1: There is some change in IQ after Horlicks.

So, from the table, we can note that,

tTab = 4.604094871

tCal = -0.816496581

DECISION: Since | tCal | < | tTab |, Accept H0.

CONCLUSION:

There is no change in IQ after Horlicks.

 Name: Kalash Poudel Roll No.: 6

EXPERIMENT NO. 6

Kolmogorov-Smirnov One Sample Test

QUESTION:

The number of laptops in 10 different departments is given below. Test

whether the laptops are uniformly distributed over the entire office by
Kolmogorov Smirnov test.

Depart No 1 2 3 4 5 6 7 8 9 10
No of laptop 8 10 9 12 15 7 5 12 13 9

SOLUTION:

H0: The laptops are uniformly distributed

H1: The laptops are not uniformly distributed

De No of Observed Observed Expecte Expecte Expected |fe-f0|

p laptop CF (cf0) relative d freq (f) d CF relative
No s freq (f0) (cfe) freq (fe)
1 8 8 0.08 10 10 0.1 0.02
2 10 18 0.18 10 20 0.2 0.02
3 9 27 0.27 10 30 0.3 0.03
4 12 39 0.39 10 40 0.4 0.01
5 15 54 0.54 10 50 0.5 0.04
6 7 61 0.61 10 60 0.6 0.01
7 5 66 0.66 10 70 0.7 0.04
8 12 78 0.78 10 80 0.8 0.02
 Name: Kalash Poudel Roll No.: 6

9 13 91 0.91 10 90 0.9 0.01

10 9 100 1 10 100 1 0
N 10 N=100 100
Max = 0.04

Critical Value from KS_TABLE (DTab): 0.122

Calculated Value from above table (DCal): MAX |Fe – F0| = 0.04

DECISION: Since | DCal | < | DTab |, Accept H0.

CONCLUSION:

The laptops are uniformly distributed.

EXPERIMENT NO. 9

Multiple Regression

QUESTION:

Find regression equation, Coeff. of determination, and standard error.

Also, Interpret the results.
S.N Initial Weight Initial Age (Weeks) Weight Gain
(Pound) x1 x2 (y)
1 39 8 7
2 52 6 6
3 49 7 8
4 46 12 10
5 61 9 9
6 35 6 5
7 25 7 3
8 55 4 4

SOLUTION:
Name: Kalash Poudel Roll No.: 6

From the above analysis table, we can note that,

Least Square Equation: y = -4.191709 + 0.10483 x1 + 0.8065025 x2

Standard Error (SE): 1.88811919

Coefficient of Determination (R2): 0.83364226

Interpretation of Regression Coefficients:

b0 = -4.191 means that it is the average weight gain when x1 and x2 are
zero.

b1 = 0.104 means that the weight increases by 0.104 per unit change in
initial weight, keeping the age constant.

b2 = 0.806 means that the weight increases by 0.806 per unit change in
age keeping the initial weight constant.

CONCLUSION:

The regression equation is y = -4.191709 + 0.10483 x1 + 0.8065025 x2

The R2 shows that the regression equation can represent 83.36% of true
observations
Name: Kalash Poudel Roll No.: 6

EXPERIMENT NO. 10

Design of Experiment (CRD)

QUESTION:

The yield of treatments in different plots is given below. Carry out the
analysis

Treatments
t1 2537 2069 1797 2104
t2 2211 3366 2591 2544
t3 2536 2459 2827 2385 2460
t4 1401 1170 1516 2104 1077

SOLUTION:
Name: Kalash Poudel Roll No.: 6

From the above table, we can note that,

FCal = 11.253

FTab = 3.343

Now,

HYPOTHESIS:

 H0: There is no significant difference between treatments.

 H1: There is a significant difference between treatments.

DECISION: Since, FCal > FTab, Accept H1.

CONCLUSION:
Name: Kalash Poudel Roll No.: 6

There is a significant difference between treatments.

EXPERIMENT NO. 11

Design of Experiment (RBD)

QUESTION:

Carry out the analysis:

X 7 Y 8 Z 12 X 8
Y 10 X 8 X 9 Z 5
Z 8 Z 11 Y 12 Y 6

SOLUTION:

Rearranging Table:

B1 B2 B3 B4
T1 7 9 6 8
Name: Kalash Poudel Roll No.: 6

T2 10 8 9 5
T3 8 11 12 6

From the table, we can note,

FT (For Treatments): 0.764

FT (Critical for Treatments): 5.143

FB (For Blocks): 1.274

FT (Critical for Blocks): 4.757

For Treatment T:

 H0: There is no significant difference between treatments.

 H1: There is a significant difference between treatments.

For Blocks B:

 H0: There is no significant difference between blocks.

Name: Kalash Poudel Roll No.: 6

 H1: There is a significant difference between blocks.

DECISION: In both cases,

FCal (FT , FB) < FT, so accept H0.

CONCLUSION:

There is no significant difference between treatments.

There is no significant difference between blocks.

Experiment No. 12

Design of Experiment (LSD)

QUESTION:

Analyze the given data:

D 20 B 17 A 20 C 19
B 21 A 18 C 18 D 17
A 18 C 21 D 17 B 17
C 20 D 19 B 17 A 18

SOLUTION:

Rearranging the table:

Ti..
Name: Kalash Poudel Roll No.: 6

20 17 20 19 76
21 18 18 17 74
18 21 17 17 73
20 19 17 18 74
T.j. 79 75 72 71 297

Square of Values:

Ti..^2
400 289 400 361 5776
441 324 324 289 5476
324 441 289 289 5329
400 361 289 324 5476
T.j.^2 6241 5625 5184 5041 88209

ANOVA Table:

SV d.f SS MS F
Name: Kalash Poudel Roll No.: 6

Rows 3 1.1875 0.395833333 0.149606299

Column 3 9.6875 3.229166667 1.220472441
Treatment 3 5.1875 1.729166667 0.653543307
Error 6 15.875 2.645833333
Total 15 31.9375

From the table, we can note,

FT (For Treatments): 0.653

FR (For Row): 0.149

FC (For Columns): 1.2204

FT (Critical for Treatments/Row/Column): 4.757

HYPOTHESIS:

For Treatment T/ Columns C/ Row R:

 H0: There is no significant difference between

treatments/columns/rows.

 H1: There is a significant difference between treatments/columns/rows

DECISION: In all cases,

FCal (FT, FC, FR) < FT, so accept H0.

CONCLUSION:

There is no significant difference between treatments.

There is no significant difference between rows.

There is no significant difference between columns.

Name: Kalash Poudel Roll No.: 6

Experiment No. 7

Chi-Square test of independent of attributes

QUESTION:

A tobacco company claims that there is no relationship between smoking

and lung ailments. To investigate the claims, a random sample of 300 men
aged 40-50 is given a medical test. The observed sample results are tabulated
below. Based on this information, can it be concluded that smoking and lung
ailments are independent?

Lung Ailment Non- Lung Ailment

Smokers 75 105
Non-Smokers 25 95

SOLUTION:

HYPOTHESIS:
Name: Kalash Poudel Roll No.: 6

 H0: There is no relation between smoking and lung ailment.

 H1: There is a relation between smoking and lung ailment.

Calculation Table
Lung Aliments Non- Lung Aliments Total
Smokers 75 105 180
Non-Smokers 25 95 120
Total 100 200 300

Observed Freq. (O) Expected Freq. (e) = (RT * CT) / n χ2 = (O - e) ^2 / e

75 60 3.75

105 120 1.875

25 40 5.625

95 80 2.8125
χ2 = ∑ (O - e) ^2 / e 14.0625

Critical Value of Chi-square = 3.841458821 CHISQ.INV.RT(0.05,1)

From the above table, we can note that,

χ2Cal = 14.0625

χ2Tab = 3.841

DECISION: Since χ2Cal > χ2Tab, Accept H1.

Name: Kalash Poudel Roll No.: 6

CONCLUSION:

There is a relationship between smoking and lung ailment.

EXPERIMENT NO. 5

t-test of difference of means

QUESTION:

The following table shows the time taken to complete the maze by eight
students of BCA and CSIT. Can it be concluded that CSIT students are more
efficient than BCA students?

BCA CSIT
8 10
12 8
13 12
9 15
3 6
8 11
10 12
9 12
Name: Kalash Poudel Roll No.: 6

SOLUTION:

HYPOTHESIS:

 H0: Both CSIT and BCA students are equally efficient in solving the
maze.

 H1: CSIT students are more efficient in solving the maze.

From the above analysis, we can note that,

tCal = -1.208

tTab = 1.761

DECISION: Since | tCal | < | tTab |, Accept H0.

CONCLUSION:

Both CSIT and BCA students are equally efficient in solving the maze.
Name: Kalash Poudel Roll No.: 6

EXPERIMENT NO. 8

Partial Correlation Coefficient

QUESTION:

Find Partial Correlation Coefficient (r(X,Y).Z)) i.e. Partial Correlation

between X and Y, controlling Z. Also find the coefficient of partial
determination and interpret.

Marks (Z) Hours (X) Final Marks (Y)

85 5 90
90 7 75
70 4 89
90 8 85
80 9 50

SOLUTION:

Correlation Values Used Formula

Name: Kalash Poudel Roll No.: 6

Correlation (X, Y) -0.771157 CORREL(X:Y)

Correlation (X, Z) 0.51875138 CORREL(X:Z)

Correlation (Y, Z) -0.0125743 CORREL(Y:Z)

Partial Correlation -0.8944579

(X, Y).Z

In Percentage
Coefficient of Partial Determination 0.80005494 80.00549377

From the above table, we can note that,

Partial Correlation Coefficient r(X,Y).Z) = -0.8944

Coefficient of Partial Determination = 0.80

CONCLUSION:

The coefficient of partial determination, as calculated at 80%, signifies that

80% of the variability in the relationship between X and Y can be attributed
to their connection or relationship after taking into account the influence of
Z. The remaining 20% of the variability in their relationship is accounted for
by the effect of Z.