4.

1 Test of significance - t test

Working rule:
❖ Write the null hypothesis H0 and the alternative hypothesis H1.
𝑥̅ −𝜇 𝑠2
❖ Find the calculated value using |𝑡| = | |, Where 𝑆. 𝐸(𝑥̅ ) = √
𝑆.𝐸 (𝒙
̅) 𝑛−1

❖ Find the critical value using the table at 𝑛 − 1 degrees of freedom.

❖ If calculated value < critical value, Accept H0. H0 is the conclusion.
❖ If calculated value > critical value, Reject H0. H1 is the conclusion.
Notation: Mean S.D

Sample ̅
𝒙 𝒔
Population 𝝁 𝝈
Problems:
1. A Machinist making engine parts with axle diameter of 0.7 inches. A random
sample of 10 parts shows mean diameter 0.742 inches with a SD of 0.04 inches. On
the basis of this sample, would you say that the work is inferior at 5% level of
significance?
[𝒕(.𝟎𝟓, 𝟗) = 𝟐. 𝟐𝟔]

Since n = 10, apply t test.

By data, 𝑥̅ = 0.742, 𝑠 = 0.04, 𝜇 = 0.7, 𝛼 = 0.05
𝑠2 0.042
𝑆. 𝐸(𝑥̅ ) = √𝑛−1 = √ = 0.0133
9

H0: 𝝁 = 𝟎. 𝟕, The work is not inferior.

̅
𝒙−𝝁 𝟎.𝟕𝟒𝟐−𝟎.𝟕
Under 𝑯𝟎 , |𝒕| = |𝐒 𝐄(𝒙̅)| = | | = 𝟑. 𝟏𝟓𝟕𝟗
𝟎.𝟎𝟏𝟑𝟑

Calculated value = 3.1579

𝛼 = 0.05, 𝛾 = 𝑛 − 1 = 9.
Critical value of 𝑡 = 2.26
Calculated value > critical value,
Reject H0. Therefore, the work is inferior.

Dr. Narasimhan G, RNSIT 1

2. The nine items of the sample have the following values: 45, 47, 50, 52, 48, 47, 49, 53
and 51. Does the mean of these differ significantly from the assumed mean of 47.5?
[𝒕(.𝟎𝟓, 𝟖) = 𝟐. 𝟑𝟏]

Since n = 9, apply t test.

By data, 𝜇 = 47.5, 𝛼 = 0.05
∑𝑥 442
𝑥̅ = = = 49.11,
𝑛 9

∑ 𝑥2 ∑𝑥 2 21762
𝑠2 = −( 𝑛 ) = − 49.112 = 2418 − 2411.79 = 6.2079
𝑛 9

𝑠2 6.2079
𝑆. 𝐸(𝑥̅ ) = √𝑛−1 = √ = 0.8809
8

Assume H0: 𝝁 = 𝟒𝟕. 𝟓,

There is no significant difference from the assumed mean 47.5
̅−𝝁
𝒙 𝟒𝟗.𝟏𝟏−𝟒𝟕.𝟓
|𝒕| = | |=| | = 𝟏. 𝟖𝟐𝟕𝟔
̅)
𝑺.𝑬(𝒙 𝟎.𝟖𝟖𝟎𝟗

Calculated value = 1.8276

𝛼 = 0.05, 𝛾 = 𝑛 − 1 = 8
Critical value = 2.31
Since calculated value < critical value,
Accept H0.
∴ There is no significant difference from the assumed mean 47.5
3. A random sample of 10 boys had the following IQ: 70, 120, 110, 101, 88, 83, 95, 98,
107, 100. Does this data support the hypothesis that the population mean of IQ’s is
100 at 5% level of significance? [𝒕(.𝟎𝟓, 𝟗) = 𝟐. 𝟐𝟔
Since n = 10, apply t - test.
∑𝑥 972
𝑥̅ = = = 97.2
𝑛 10

∑ 𝑥2 ∑𝑥 2 96312
𝑠2 = −( 𝑛 ) = − 97.22 = 183.36
𝑛 10

𝑠2 183.36
𝑆𝐸(𝑥̅ ) = √𝑛−1 = √ = 4.5136
9

Assume H0: 𝝁 = 𝟏𝟎𝟎, The population mean of IQ’s is 100.

̅−𝝁
𝒙 𝟗𝟕.𝟐−𝟏𝟎𝟎
|𝒕| = | |=| | = 𝟎. 𝟔𝟐𝟎𝟑
̅)
𝑺𝑬(𝒙 𝟒.𝟓𝟏𝟑𝟔

Calculated value = 0.6203

𝛼 = 0.05, 𝛾 = 𝑛 − 1 = 9.
Critical value = 2.26

Dr. Narasimhan G, RNSIT 2

 Calculated value < Critical value
Accept H0.
Therefore, the population mean IQ is100 at 5% level of significance.
4. A certain stimulus administered to each of 12 patients resulted in the following
increases of blood pressure: 5, 2, 8, -1, 3, 0, -2, 1, 5, 0, 4, 6. Can it be concluded that
the stimulus will in general be accompanied by an increase in blood pressure?
[𝒕(.𝟎𝟓, 𝟏𝟏) = 𝟐. 𝟐

Since n = 12, apply t - test.

∑𝑑 31
𝑑̅ = 𝑛 = 12 = 2.5833
∑ 𝑑2 ∑𝑑 2 185 31 2
𝑠2 = −( ) = − (12) = 15.4167 − 6.6734 = 8.7433
𝑛 𝑛 12

𝑠 2
8.7433
𝑆𝐸(𝑑̅) = √𝑛−1 = √ 11 = 0.8915

H0: 𝝁 = 𝟎, The stimulus will not increase in blood pressure.

̅ −𝝁
𝒅 𝟐.𝟓𝟖𝟑𝟑−𝟎
|𝒕| = | ̅ )| =| | = 𝟐. 𝟖𝟗𝟕7
𝑺𝑬(𝒅 𝟎.𝟖𝟗𝟏𝟓

Calculated value = 2.8977

𝛼 = 0.05, 𝛾 = 𝑛 − 1 = 11
Critical value = 2.2
Calculated value > Critical value
Reject H0.
∴ The stimulus will increase blood pressure.
5. Eleven students were given a test in statistics. They were given a month’s further
tuition and a second test of equal difficulty was held at the end of it. Do the marks
give evidence that the students have benefitted by extra coaching?
Boys: 1 2 3 4 5 6 7 8 9 10 11
Marks I test: 23 20 19 21 18 20 18 17 23 16 19
Marks II test: 24 19 22 18 20 22 20 20 23 20 17
[𝒕(.𝟎𝟓, 𝟏𝟎) = 𝟐. 𝟐𝟑]

Since n = 11, apply t test.

Σ𝑑 = Σ(𝑥2 − 𝑥1 ) = 11
∑𝑑
𝑑̅ = =1
𝑛
∑ 𝑑2 ∑𝑑 2 61 50
𝑠2 = −( ) = 11 − 1 = 11
𝑛 𝑛

𝑠 2
50/11 50
𝑆𝐸 (𝑑̅) = √𝑛−1 = √ 10 = √110 = 0.6742

Dr. Narasimhan G, RNSIT 3

 Assume H0: 𝝁 = 𝟎,
The students did not have benefitted by extra coaching.
̅−𝝁
𝒅 𝟏−𝟎
|𝒕| = | |=| | = 𝟏. 𝟒𝟖𝟑𝟐
̅)
𝑺𝑬(𝒅 𝟎. 𝟔𝟕𝟒𝟐
Calculated value = 1.4832
𝛼 = 0.05, 𝛾 = 𝑛 − 1 = 10.
Critical value = 2.23
Calculated value < Critical value
Accept H0.
∴ The students did not have benefit by extra coaching.
6. A group of boys and girls were given an intelligent test. The mean score SD’s and
numbers in each group are as follows:
Mean S.D n
Boys 124 12 18
Girls 121 10 14
Is the mean score of boys significantly different from that of girls?
[𝒕(.𝟎𝟓,𝟑𝟎) = 𝟐. 𝟎𝟒]

Since 𝑛1 = 18, 𝑛2 = 14, apply t test.

By data, ̅̅̅
𝑥1 = 124, ̅̅̅
𝑥2 = 121, 𝑠1 = 12, 𝑠2 = 10
𝑛1 𝑠12 +𝑛2 𝑠22 18(144)+14(100)
𝑠2 = = = 133.07
𝑛1 +𝑛2 −2 18+14−2

1 1 1 1
𝑆𝐸(𝑥 𝑥2 = √𝑠 2 (𝑛 + 𝑛 ) = √133.07 (18 + 14) = 4.1106
̅̅̅1 − ̅̅̅)
1 2

H0: 𝜇1 = 𝜇2 , the mean score of boys does not differ significantly from that of girls.
̅𝑥̅̅1̅ −̅̅̅̅
𝑥2 124 −121
|𝑡| = | |=| | = 0.7298
̅̅̅̅ −̅̅̅̅)
𝑆.𝐸(𝑥 1 𝑥 2 4.1106

Therefore, calculated value of t = 0.7298

𝛼 = 0.05, 𝛾 = 𝑛1 + 𝑛2 − 2 = 30, Therefore, critical value of t = 2.04
Since calculated value < critical value, Accept H0.
∴The mean score of boys does not differ significantly from that of girls.

7. The means of two random samples of sizes 9 and 7 are 196.42 and 198.82
respectively. The sum of squares of the deviations from the mean are 26.94 and
18.73 respectively. Can the sample be considered to have been drawn from the
same normal population? [𝒕(.𝟎𝟓, 𝟏𝟒) = 𝟐. 𝟏𝟒]

Dr. Narasimhan G, RNSIT 4

 Since n1 = 9, n2 = 7, apply t test.
By data, ̅̅̅ 𝑥2 = 198.82, 𝑛1 𝑠12 = 26.94, 𝑛2 𝑠22 = 18.73
𝑥1 = 196.42, ̅̅̅
𝑛1 𝑠12 +𝑛2 𝑠22 26.94+18.73
𝑠2 = = = 3.2621
𝑛1 +𝑛2 −2 9+7−2

1 1 1 1
𝑆𝐸(𝑥 𝑥2 = √𝑠 2 (𝑛 + 𝑛 ) = √3.2621 (9 + 7) = 0.9102
̅̅̅1 − ̅̅̅)
1 2

H0: 𝜇1 = 𝜇2 , sample is drawn from the same normal population.

̅𝑥̅̅1̅ −̅̅̅̅
𝑥2 196.42 −198.82
|𝑡| = | |=| | = 2.6368
̅̅̅̅ −̅̅̅̅)
𝑆𝐸(𝑥 1 𝑥 2 0.9102

Therefore, calculated value of t = 2.6368

𝛼 = 0.05, 𝛾 = 𝑛1 + 𝑛2 − 2 = 9 + 7 − 2 = 14, Critical value of t = 2.14
Since calculated value > critical value, Reject H0.
∴ Sample is not drawn from the same normal population.

8. From a random sample of 10 pigs fed on diet A, the increases in weight in a certain
period were 10, 6, 16, 17, 13, 12, 8, 14, 15, 9 lbs. For another random sample of 12
pigs fed on diet B, the increases in the same period were 7, 13, 22, 15, 12, 14, 18, 8,
21, 23, 10, 17 lbs. Test whether diets A and B differ significantly as regards their
effect on increases in weight? [𝒕(.𝟎𝟓, 𝟏𝟒) = 𝟐. 𝟎𝟗]

Since n1 = 10, n2 = 12, apply t test.

∑ 𝑥1 120
By data, ̅̅̅
𝑥1 = = = 12
𝑛1 10
∑ 𝑥2 180
𝑥2 =
̅̅̅ = = 15
𝑛2 12

∑ 𝑥1 2 ∑𝑥 2 1560
𝑠12 = − ( 𝑛 1) = − 144 = 12
𝑛1 1 10

∑ 𝑥2 2 ∑𝑥 2 3014
𝑠22 = − ( 𝑛 2) = − 225 = 26.17
𝑛2 2 12

𝑛1 𝑠12 +𝑛2 𝑠22 10(12)+12(26.17)

𝑠2 = = = 21.7020
𝑛1 +𝑛2 −2 10+12−2

1 1 1 1
𝑆𝐸(𝑥 𝑥2 = √𝑠 2 (𝑛 + 𝑛 ) = √21.7020 (10 + 12) = 1.9947
̅̅̅1 − ̅̅̅)
1 2

H0: 𝜇1 = 𝜇2 , diets A and B do not differ significantly.

̅𝑥̅̅1̅ −̅̅̅̅
𝑥2 12−15
|𝑡| = | | = |1.9947| = 1.5040
̅̅̅̅ −̅̅̅̅)
𝑆𝐸(𝑥 𝑥
1 2

Therefore, calculated value =1.6

𝛼 = 0.05, 𝛾 = 𝑛1 + 𝑛2 − 2 = 10 + 12 − 2 = 20, Critical value = 2.09
Since calculated value < critical value, Accept H0.

Dr. Narasimhan G, RNSIT 5

 ∴Diets A and B do not differ significantly.

Home work:
9. A machine is expected to produce nails of length 3 inches. A random sample of 25 nails
gave an average length of 31. Inches with standard deviation 0.3. Can it be said that the
machine is producing nails as per specifications? Given 𝑡0.05 (24) = 2.064
10. Two horses A and B were tested according to the time (seconds) to run a particular race
with the following results:
Horse A 28 30 32 33 33 29 34
Horse B 29 30 30 24 27 29
Test whether you can discriminate between the two horses.
Given that 𝑡0.05 = 2.20 for 11 degrees of freedom
11. Two types of batteries are tested for their length of life and the following results were
obtained:
Battery A Battery B
Mean 500 500
Variance 100 121
Sample size 10 10

Check whether there is a significant difference between two means. [𝑡0.05 (18) = 0.086]
12. A sample of 12 measurements of the diameter of a metal ball gave the mean 7.38 mm
with standard deviation 1.24 mm. Find 99% confidence limits for actual diameter.
[𝑡0.01 (11) = 3.11]
𝑠
Note: Confidence limits for the mean are 𝑥̅ ± 𝑡 (𝛾)
√𝑛−1 𝛼

13. A group of 10 boys fed on a diet A and another group of 8 boys fed on a different diet B
for a period of six months recorded the following increase in weight (lbs).

Diet A 5 6 8 1 12 4 3 9 6 10
Diet B 2 3 6 8 10 1 2 8
Test whether diet A and B differ significantly regarding their effort on increase in
weight.

Dr. Narasimhan G, RNSIT 6

 4.2 Test for goodness of fit
--------------------------------------------------------------------------------------------------------
Working rule:
Find Expected frequency using 𝐸𝑖 = 𝑁 × 𝑃(𝑥)
Assume 𝑯𝟎 : Expected frequency distribution is a good fit to the observed frequency
distribution.
Calculated value:
(𝑶𝒊 −𝑬𝒊 )𝟐
Under H0, 𝝌𝟐 = ∑ with 𝑛 − 𝑐 degrees of freedom.
𝑬𝒊

Where 𝑂𝑖 − Observed frequency or tabulated frequency

𝐸𝑖 − Expected frequency or theoretical frequency
𝑛 − number of terms, 𝑐 − number of constraints
Critical value:
Level of significance 𝛼 = 0.05 𝑜𝑟 0.01 (Always upper tailed)
1, 𝐼𝑛 𝑔𝑒𝑛𝑒𝑟𝑎𝑙
Degrees of freedom 𝛾 = 𝑛 − 𝑐. Where 𝑐 = {2, 𝐹𝑜𝑟 𝑃𝑜𝑖𝑠𝑠𝑜𝑛 𝑑𝑖𝑠𝑡𝑟𝑖𝑏𝑢𝑡𝑖𝑜𝑛
3, 𝐹𝑜𝑟 𝑛𝑜𝑟𝑚𝑎𝑙 𝑑𝑖𝑠𝑡𝑟𝑖𝑏𝑢𝑡𝑖𝑜𝑛
Use table.
Conclusion:
If calculated value < critical value,
Accept 𝑯𝟎 .
The expected frequency distribution is a good fit to the observed frequency distribution.
If calculated value > critical value,
Reject 𝑯𝟎 .
The expected frequency distribution is not a good fit to the observed frequency distribution.
--------------------------------------------------------------------------------------------------------
1. A die is thrown 60 times and the frequency distribution for the number appearing
on the face x is given by the following table:

𝒙: 1 2 3 4 5 6

𝒇: 15 6 4 7 11 17
2 (5)
Test the hypothesis that the die is unbiased. [𝜒0.05 = 11.07]

By data observed frequency 𝑂𝑖 : 15, 6, 4, 7, 11, 17.

Find expected frequency 𝐸𝑖 = 𝑁 × 𝑃(𝑥) , 𝑥: 1, 2, 3, 4, 5, 6

Dr. Narasimhan G, RNSIT 7

 1 1 1 1 1 1
𝑃(𝑥): 6 , 6 , 6 , 6 , 6 , 6

1 1 1 1 1 1
𝑁 × 𝑃(𝑥): 60 × (6) , 60 × (6) , 60 × (6) , 60 × (6) , 60 × (6) , 60 × (6)

𝐸𝑖 : 10, 10, 10, 10, 10, 10

𝑨𝒔𝒔𝒖𝒎𝒆 𝑯𝟎 : The die is unbiased.

(𝑶𝒊 −𝑬𝒊 )𝟐
Under 𝑯𝟎 , 𝝌𝟐 = ∑ with 𝒏 − 𝟏 = 𝟓 d.f
𝑬𝒊

𝑥𝑖 𝑂𝑖 (𝑂𝑖 − 𝐸𝑖 )2 (𝑂𝑖 − 𝐸𝑖 )2
𝐸𝑖
𝐸𝑖
1 15 10 25 2.5
2 6 10 16 1.6
3 4 10 36 3.6
4 7 10 9 0.9
5 11 10 1 0.1
6 17 10 49 4.9
13.6
Calculated value = 13.6

Critical value= 11.07

∴ Calculated value > Critical Value.

Reject 𝑯𝒐 .

Therefore, the die is not unbiased.

2. The following table gives the number of road accidents that occurred in a large city
during the various days of a week. Test the hypothesis that the accidents are
uniformly distributed over all the days of a week. [ 𝝌𝟐𝟎.𝟎𝟓 (𝟔) = 𝟏𝟐. 𝟓𝟗]

Day: Sun Mon Tue Wed Thu Fri Sat Total

No. of accidents: 14 16 8 12 11 9 14 84

By data observed frequency 𝑂𝑖 : 14, 16, 8, 12, 11, 9, 14.

Find expected frequency 𝐸𝑖 = 𝑁 × 𝑃(𝑥), 𝑥: 1, 2, 3, 4, 5, 6, 7

1 1 1 1 1 1
𝑃(𝑥): 7 , 7 , 7 , 7 , 7 , 7

Dr. Narasimhan G, RNSIT 8

 1 1 1 1 1 1
𝑁 × 𝑃(𝑥): 84 × (7) , 84 × (7) , 84 × (7) , 84 × (7) , 84 × (7) , 84 × (7)

𝐸𝑖 : 12, 12, 12, 12, 12, 12, 12

𝑨𝒔𝒔𝒖𝒎𝒆 𝑯𝟎 : The accidents are uniformly distributed over all the days of a week.

(𝑶𝒊 −𝑬𝒊 )𝟐
Under 𝑯𝟎 , 𝝌𝟐 = ∑ , with 𝒏 − 𝟏 = 𝟔 degrees of freedom.
𝑬𝒊

𝑥 𝑂𝑖 𝐸𝑖 (𝑂𝑖 − 𝐸𝑖 )2 (𝑂𝑖 − 𝐸𝑖 )2
𝐸𝑖
Sun 14 12 4 4/12
Mon 16 12 16 16/12
Tue 8 12 16 16/12
Wed 12 12 0 0
Thu 11 12 1 1/12
Fri 9 12 9 9/12
Sat 14 12 4 4/12
50/12
50
Calculated value = 12

Critical value = 12.59

∴ Calculated value < Critical Value.

Accept 𝑯𝒐 .

Therefore, the accidents are uniformly distributed over all the days of a week
3. A set of 5 similar coins is tossed 320 times and the result is
Number of heads: 0 1 2 3 4 5
Frequency: 6 27 72 112 71 32
Test the hypothesis that the data follows a binomial distribution. [𝝌𝟐𝟎.𝟎𝟓 (𝟓) = 𝟏𝟏. 𝟎𝟕]

By data, observed frequency 𝑂𝑖 : 6, 27, 72, 112, 71, 32.

Find expected frequency 𝐸𝑖 = 𝑁 × 𝑃(𝑥), 𝑥: 0, 1, 2, 3, 4, 5

1 𝑥 1 5−𝑥 1
𝑃(𝑥) = 𝑛𝐶𝑥 𝑝 𝑥 𝑞 𝑛−𝑥 = 5𝐶𝑥 (2) (2) = 32 × 5𝐶𝑥 (n- no. of coins)

1
𝑁 × 𝑃(𝑥) = 320 × 32 × 5𝐶𝑥 = 10 × 5𝐶𝑥

𝐸𝑖 : 10 × 5𝐶0 , 10 × 5𝐶1 , 10 × 5𝐶2 , 10 × 5𝐶3 , 10 × 5𝐶4 , 10 × 5𝐶5

Dr. Narasimhan G, RNSIT 9

 Assume 𝑯𝟎 : The data follows Binomial distribution.

(𝑶𝒊 −𝑬𝒊 )𝟐
Under 𝑯𝟎 , 𝝌𝟐 = ∑ , with 𝒏 − 𝟏 = 𝟔 − 𝟏 = 𝟓 degrees of freedom.
𝑬𝒊

(n-number of frequencies)

𝐸𝑖 𝑥 𝑂𝑖 (𝑂𝑖 − 𝐸𝑖 )2 (𝑂𝑖 − 𝐸𝑖 )2
𝐸𝑖
𝐸𝑖
0 6 10 16 1.6
1 27 50 529 10.58
2 72 100 784 7.84
3 112 100 144 1.44
4 71 50 441 8.82
5 32 10 484 48.4
78.68

Calculated value = 78.68

Critical Value = 11.07

∴ Calculated value > Critical Value.

Reject 𝑯𝒐 .

Therefore, the data does not follow Binomial distribution.

-------------------------------------------------------------------------------------------------------

4. Fit a Poisson distribution to the following data and test for its goodness of fit at
level of significance 0.05.

𝒙: 0 1 2 3 4

𝒇: 419 352 154 56 19 [𝝌𝟐𝟎.𝟎𝟓 (𝟑) = 𝟕. 𝟖𝟐]

By data, observed frequency 𝑂𝑖 : 419, 352, 154, 56, 19

Find expected frequency 𝐸𝑖 = 𝑁 × 𝑃(𝑥), 𝑥: 0, 1, 2, 3, 4

Σ𝑓𝑥 904
𝑚 = 𝑚𝑒𝑎𝑛 = = 1000 = 0.904
Σ𝑓

𝑒 −𝑚 = 𝑒 −0.904 = 0.4049

Dr. Narasimhan G, RNSIT 10

 𝑒 −𝑚 𝑚 𝑥 (0.4049)(0.904)𝑥
∴ 𝑃(𝑥) = =
𝑥! 𝑥!
(0.904)𝑥
𝐸𝑖 = 𝑁 × 𝑃(𝑥) = 1000 × 𝑃(𝑥) = 404.9 ×
𝑥!

𝐸𝑖 = 405, 366, 165, 50, 11

Assume 𝑯𝒐 : The data follows Poisson distribution.

(𝑶𝒊 −𝑬𝒊 )𝟐
Under 𝑯𝟎 , 𝝌𝟐 = ∑ with 𝒏 − 𝟐 = 𝟓 − 𝟐 = 𝟑 degrees of freedom.
𝑬𝒊

𝑥 𝑂𝑖 𝐸𝑖 (𝑂𝑖 − 𝐸𝑖 )2 (𝑂𝑖 − 𝐸𝑖 )2
(𝑖) 𝐸𝑖
0 419 405+1 169 0.4033
1 352 366 196 0.5355
2 154 165 121 0.7333
3 56 50 36 0.7200
4 19 11+2 36 2.7692
5.1613
Numbers added in 𝐸𝑖 only to preserve totality.

∴ Calculated value = 5.1613

Degrees of freedom= 𝑛 − 2 = 5 − 2 = 3 (∵ It follows Poisson distribution)

Critical value = 7.82

∴ Calculated value < Critical Value.

Accept 𝑯𝟎 .
Therefore, the data follows Poisson distribution.
------------------------------------------------------------------------------------------------------
5. Genetic theory states that children having one parent of blood type M and other
blood type N will always be one of the three types M, MN, N and that the
proportion of these types will on average 1:2:1. A report says that out of 300
children having one M parent and one N parent, 30% were found to be type M ,
45% of type MN and remainder of type N. Test the hypothesis by 𝝌𝟐 test.
[𝝌𝟐𝟎.𝟎𝟓 (𝟐) = 𝟓. 𝟗𝟗]

By data, observed frequency 𝑂𝑖 : 30% 𝑜𝑓 300, 45% 𝑜𝑓 300, 25% 𝑜𝑓 300.

Find expected frequency 𝐸𝑖 = 𝑁 × 𝑃(𝑥), 𝑥: 𝑀, 𝑀𝑁, 𝑁

1 2 1
𝑃(𝑥): ,4,4
4

Dr. Narasimhan G, RNSIT 11

 1 2 1
𝑁 × 𝑃(𝑥): 300 × 4 , 300 × 4 , 300 × 4

𝐸𝑖 : 75, 150, 75

Assume 𝑯𝟎 : The proportion of these types is on average 1:2:1

(𝑶𝒊 −𝑬𝒊 )𝟐
Under 𝑯𝟎 , 𝝌𝟐 = ∑ with 𝒏 − 𝟏 = 𝟑 − 𝟏 = 𝟐 degrees of freedom.
𝑬𝒊

𝑥 𝑂𝑖 𝐸𝑖 (𝑂𝑖 − 𝐸𝑖 )2 (𝑂𝑖 − 𝐸𝑖 )2
𝐸𝑖
1
M 30% of 300 = 90 300 × 4 = 75
225 3
MN 45% of 300 = 135 2
300 × = 150
4 225 1.5
M 25% of 300 = 75 1
300 × = 75
4 0 0
4.5
Calculated value = 4.5

Critical value = 5.99

Calculated value < Critical Value.

Accept 𝑯𝟎 .
Therefore, the Genetic theory, ‘The proportion of these types is on average
1:2:1’, fitted to the report.
-------------------------------------------------------------------------------------------------------

6. In experiments on Pea breading, the following frequencies of seeds were obtained:

Round Wrinkled Round Wrinkled Total

and yellow and yellow and green and green
315 101 108 32 556

Theory predicts that the frequencies should be in proportions 𝟗: 𝟑: 𝟑: 𝟏. Examine

the correspondence between theory and experiment. [𝝌𝟐𝟎.𝟎𝟓 (𝟑) = 𝟕. 𝟖𝟐]

By data, observed frequency 𝑂𝑖 : 315, 101, 108, 32

Find expected frequency 𝐸𝑖 = 𝑁 × 𝑃(𝑥), 𝑥: 𝑅𝑌, 𝑊𝑌, 𝑅𝐺, 𝑊𝐺

9 3 3 1
𝑃(𝑥): 16 , 16 , 16 , 16
9 3 3 1
𝑁 × 𝑃(𝑥): 556 × 16 , 556 × 16 , 556 × 16 , 556 × 16

𝐸𝑖 : 313, 104, 104, 35

Assume 𝑯𝒐 : The frequencies are in proportions 𝟗: 𝟑: 𝟑: 𝟏

Dr. Narasimhan G, RNSIT 12

 (𝑶𝒊 −𝑬𝒊 )𝟐
Under 𝑯𝟎 , 𝝌𝟐 = ∑ with 𝒏 − 𝟏 = 𝟒 − 𝟏 = 𝟑 degrees of freedom.
𝑬𝒊

𝑥 𝑂𝑖 𝐸𝑖 (𝑂𝑖 − 𝐸𝑖 )2 (𝑂𝑖 − 𝐸𝑖 )2
(𝑖) 𝐸𝑖
RY 315 9 4 0.0128
556 ( ) = 313
16
WY 101 3 9 0.0865
556 ( ) = 104
16
RG 108 3 16 0.1538
556 ( ) = 104
16
WG 32 1 9 0.2571
556 ( ) = 35
16
0.5102
Calculated value = 0.5102

Critical value = 7.82

Calculated value < Critical Value.

Accept 𝑯𝒐 .
Therefore, the theory, ‘The frequencies should be in proportions 𝟗: 𝟑: 𝟑: 𝟏, fitted
to the experiment.
------------------------------------------------------------------------------------------------------

Tabulated values of 𝝌𝟐 𝜶 (𝝂)

𝜈 𝜒 2 0.05 (𝜈) 𝜒 2 0.01 (𝜈)

1 3.84 6.64
2 5.99 9.21
3 7.82 11.34
4 9.49 13.28
5 11.07 15.09
6 12.59 16.81
7 14.07 18.48
8 15.51 20.09
9 16.92 21.67
10 18.31 23.21

-------------------------------------------------------------------------------------------------------

7. The theory predicates the proportion of beans in the four groups 𝐺1 , 𝐺2 , 𝐺3 𝑎𝑛𝑑 𝐺4
should be in the ratio 9: 3: 3: 1. In an experiment with 1600 beans the numbers in the
four groups were 882, 313, 287 and 118. Does the experimental result support the
Dr. Narasimhan G, RNSIT 13
 2 (3)
theory? [𝜒0.05 =
7.815]
8. Records taken of the number of male and female births in 800 families having four
children are as follows:
Number of male births 0 1 2 3 4
Number of female births 4 3 2 1 0
Number of families 32 178 290 236 94
Test whether the data are consistent with the hypothesis that the binomial law holds and
2 (4)
the chance of male birth is equal to that of female birth. [𝜒0.05 = 9.488]

-------------------------------------------------------------------------------------------------------------------------

F Distribution
Introduction:
❖ The F test is named in honour of the great statistician R A Fisher. The objective of the F
test is to find out whether the two independent estimates of population variance differ
significantly or whether the two samples may be regarded as drawn from the same
population having the same variance.
𝑠2
❖ For carrying out the test significance, The ratio F is defined as 𝐹 = 𝑠12 , 𝑠12 > 𝑠22 where
2
∑(𝑥−𝑥̅ )2 ∑(𝑦−𝑦̅)2
𝑠12 = , 𝑠22 =
𝑛1 −1 𝑛2 −1
❖ The calculated value of F is compared with the tabulated value for 𝜈1 and 𝜈2 at 5% or
1% level of significance. 𝜈1 – Degrees of freedom for sample having larger variance and
𝜈2 - Degrees of freedom for sample having smaller variance.
❖ If the calculated value is less than the tabulated value the null hypothesis is accepted and
it is inferred that both the samples come from the same population.
❖ Since F test is based on the ratio of two variances, it is also known as the variance ratio
test.
❖ The ratio of two variances follows a distribution called the F distribution.

Dr. Narasimhan G, RNSIT 14