BA4106 STATISTICS FOR MANAGEMENT

Academic Year : 2023-24 Programme : MBA

Year / Semester : I/I QUESTION BANK Course Coordinator: Mrs.M.Latha

Course Objectives Course Outcomes

1. To enable the students to have an insight On completion of the course, students will be able to
into basic statistical techniques. CO1: Compare the collected information using descriptive and
2. To gain an understanding about hypothesis inferential statistics to interpret the collected data.(K1)
testing, using tools such as Z test, F test, CO2: Apply the sampling theory in accounting and auditing
ANOVA, chi- square tests, regression & from business point of view.(K3)
correlation analysis and non-parametric tests. CO3: Use univariate and bivariate statistical tools for analysis of
3. To enable the students to draw conclusions collected data. (K2)
from the analysis for better decisionmaking. CO4: Apply non-parametric test for drawing meaningful
conclusions.(K3)
CO5: Apply correlation and simulation techniques for business
decision making. (K3)
CO6: Interpret the changes in economic
phenomena of future events using time series ( K2)

PART – A ( 2 MARK QUESTIONS WITH KEY)

S.N QUESTIONS Mark COs
o
UNIT I – INTRODUCTION

1 Define Statistics? How is statistics used in everyday life?

Statistics are usually defined as: A collection of numerical data that measure something,
1
The science of recording, organizing, analyzing and reporting quantitative information.
Statistics are everywhere, election predictions are statistics, anything food product that 1 K1
says they x% more or less of a certain ingredient is a statistic. Life expectancy is a
1
statistic. If you play card games card counting is using statistics. There are tons of
statistics everywhere you look.
2 State Baye’s theorem on rule of inverse probability.
If B1, B2…Bn be a set of exhaustive and mutually exclusive events and A be another
1 K1
2
event associated with Bi then
3 Define mutually exclusive and exhaustive events.
Two events are said to be mutually exclusive if the occurrence of any one of them
excludes the occurrence of other in a single experiment. 1
1 K1
All possible outcomes of an experiment are called exhaustive events.
1
4 The price of a selected stock over a five day period is shown as 170, 110, 130, 170 and 160.
Compute Mean, median and mode

1 K2
n=5, mean = 148 1
median = ((n+1)/2 )th term 160, mode = repeated value=170
1
5 If P(A/B) = 0.2 and P(B)=0.4 then find P(A ∩ B).
P(A∩B) = P(A/B)xP(B) 1 K2
1
P(A/B)xP(B) =0 .4x0.2=0.08 1
1|Page
6 What is the mean and variance of Binomial distribution?
mean= np, 1 1 K1
variance = npq 1
7 When do you say two events are independent?
P(A∩B) = P(A)x P(B) 1 K1
2
8 What is a random experiment?
An experiment is said to be a random experiment, if it‟s out-come can‟t be predicted 1 K1
2
with certainty.
9 Define a sample space.
The set of all possible out-comes of an experiment is called the sample space. It is 1 K1
2
denoted by „S‟ and its number of elements are n(s).
10 List the properties of Normal distribution.

(i) The mean of a normally distributed population lies at the centre of the normal
curve
(ii) The mean, median and mode of the normal distribution coincide. 1 K1
(iii) The curve is asymptotic at x axis on both sides. 2
(iv) The normal curve is bell shaped and symmetrical about the vertical line through
the centre

11 Give example of continuous and discrete variable.

A discrete random variable is characterized by jumps and gaps between one value and the
1
next. For example, the no. of tables in a Restaurant.
1 K2
These variables which can take all possible values in a given specified range are termed as
continuous variables. For example, the age of students in a school, heights (in cm), weight 1
(in kg) etc.
12 A coin is tossed 3 times. Find the sample space and probability of two heads.
n(s) =8 1 1 K2
P(two heads ) =3/8 1
13 Given x is distributed in Poisson fashion. Find E (x) if E(x2) =6
E(x2) = λ+ λ2 =6; λ= 2 1 1 K2
E (x) = 2 1
14 How to organize a data in retrievable format?
1 K1
Qualitative, Quantitative, Chronological, Geographical 1
15 From a pack of cards, one card is drawn . What is the probability that it is either a spade
or a king?
1 K2
P(Spade card) = 13/52, P(king card) = 4/52, P(Spade Ո King) = 1/52 1
P (Either spade or king) = P(A U B) = 4/13 1

UNIT II – SAMPLING DISTRIBUTION AND ESTIMATION

1 What is sampling distribution?

Suppose that we draw all possible samples of size n from a given population. Suppose
further that we compute a statistic (mean, proportion, standard deviation) for each 2 2 K1
sample. The probability distribution of this statistic is called Sampling Distribution.
2 Give two rules for determining sample size
Sample size n= S2Z2/E2 if standard deviation is given 1 2 K1
Sample size n= pqZ2/E2 if p, q values are given 1
3 What are qualities of good estimator?
Unbiasedness, Consistency, Efficiency, Sufficiency 2 K1
2
4 What are the advantages of Sampling?
A Sample survey is cheaper than a census survey. 1
1
More economical, Analysis of the results can be carried out speedily.

2|Page
2 K1

3|Page
 5 What is point estimate?
A point estimate is a single number, which is used to estimate an unknown population
parameter. It is the common way of expressing an estimate. In other words, the point 2 K1
2
estimate does not give any idea about the reliability or precision of the method of
estimation used.
6 A automobile repair shop has taken a random sample of 40 services that the average
service time on an automobile is 130 mins with a standard deviation of 26 min. Find the
standard error of the mean. 2 K2
16. n =40, = 130, 1
S.E = = 4.11 1
7 Define Strata.
Groups within a population formed in such a way that each group is relatively 2
2 K1
homogeneous but wider variability exists among the separate groups.

8 List the various sampling techniques

Simple random sampling, systematic sampling, stratified sampling, Cluster sampling, 2 2 K1
Judgment sampling and Quota sampling.
9 What is cluster sampling?
A sample design in which a cluster of elements is the primary sampling unit instead of 2 2 K1
individual element in the population
10 What are non sampling errors?
A non sampling error primarily arise at the stages of observation approximation and
processing of data and are thus present in both the complete enumeration and the 2 2 K1
sample survey.
11 Define unbiased estimator.
An estimator is said to be unbiased if its expected value is equal to the population
2 2 K1
parameter it estimates.
12 Define standard error of mean and confidence interval of the mean
S.E ( ) =σ/√n 1 2 K1
Confidence interval = + S.E ( ) Zα 1
13 State central limit theorem
Assumptions 1 2 K1
~ N(µ ,σ2/n) 1
14 What are the ways to decrease the Standard error.
Standard Error can be minimized by increasing the sample size 1 2 K1
Sampling error can be eliminated by increasing the efficiency of sampling 1
15 Define interval estimate.
The estimate of an interval in which an unknown population characteristic is expected 2 2 K1
to lie for a given level of significance.

UNIT III – TESTING OF HYPOTHESIS - PARAMETRIC TESTS

1 Define Hypothesis
A Hypothesis is a proposition or a statement that we would like to verify whether it is
2 3 K1
true or not.
2 Differentiate one tailed and two tailed test.
One tail test: A statistical hypothesis test in which the alternative hypothesis is
1
specified such that only one direction of the [possible values is considered.
Two tail test: A statistical hypothesis test in which the alternative hypothesis is 3 K2
specified such that it includes both the higher and the lower values of a parameter than 1
the value specified in the null hypothesis.
3 Define critical region.
The set of values of the test statistic that will cause us to reject the null hypothesis. 3 K1
2

4|Page
 4 Define Type I and Type II error?
Type I Error: An error caused by rejecting a null hypothesis that is true 1 3 K1
Type II Error: An error caused by accepting null hypothesis, that is false. 1
5 List out the different applications of t-test.
T test is applied for small samples i.e n<30 1
It is used to test whether there is any significant difference between sample mean and 3 K1
1
population mean.
6 What is Null Hypothesis and Alternative Hypothesis?
A Hypothesis of no difference is called Null Hypothesis. It is denoted by Ho 1 3 K1
Alternative hypothesis is opposite of null Hypothesis. It is denoted by H1 1
7 Write down the formula to test the difference of two means in case of large sample.
Z= | 1 - 2| / √(s 12/n1 +s 22/n2) 1
Where 3 K1
1 and 2 are sample mean, n1 , n2 are sample size and S1, s2 are sample 1
standard deviation.
8 What is ANOVA? Why is ANOVA helpful?
Analysis of Variance (ANOVA) is a statistical technique used to test the equality of
1 3 K1
three or more sample means.
It is helpful to test the homogeneity of several means. 1
9 What is level of significance?
Maximum size of the type I error to face risk is called Level of significance. 1 3 K1
Type I error is reject H0, when H0 is true. 1
10 Give test statistic for testing significance of difference between the variance of two small
sample.
S12= Σ(x 1 - 1)2 / n1 -1 S2 2= Σ(x2 - 2)2 / n2-1 3 K1
1
F test : F= S22/ S 12 1
11 Write the table of one way ANOVA
Source Sum of squares DoF Mean F ratio
Betw SSR R-1 MSR= F= 3 K1
sample SSR/R-1 MSR/MSE 2
Within SSE N-R MSE = (or)
Sample SSE/N-R MSE/MSR
12 State the basic principles of Experimental Design.
Replication, Randomization and Local control. 2 3 K1
13 What are the assumptions based on ANOVA?
The observations are independent; The samples are drawn from normal population. 1 3 K1
Various treatment and environmental effects are additive in nature.

1
14 Define Degrees of freedom.
The number of elements that can be chosen freely is called Degrees of freedom. 2 3 K1
15 Define test statistic.
The value of z or t calculated for a sample statistic such as the sample mean or the 3 K1
sample proportion is known as test statistic.

UNIT IV – NON-PARAMETRIC TESTS

1 What are the applications of chi- square test?

Test of goodness of fit 1 4 K1
Test of independence of attributes, Test of Homogeneity 1
2 Differentiate Kruskal Wallis test and Mann Whitney U test.
Kruskal wallis is used test whether 3 or more populations are individual. 1 4 K1
Mann Whitney test is used to determine whether two different samples come from identical
1
population or these populations have different means.
3 What is non parametric test? Name any four non parametric test.
Test that rely less on parameter estimation and /or assumptions about the shape of a
1 4 K1
5|Page
1
population distribution.
ch square, H test, U test, run test

6|Page
 4 How do find the degrees o freedom in case of chi square test?
Degrees of freedom = n-1 1 4 K1
Degrees of freedom = (r-1) (c-1) 1
5 Explain the term “run” with an example.
A sequence of identical occurrences that may be preceded and followed by different
1
occurrences. 4 K2
Example: The response from 10 school boys for the question “ whether the boys prefer
1
their home near to school” - y y y n n y n y y
6 Kruskal Wallis test is the non parametric ANOVA. Why?
Kruskal wallis is used test whether 3 or more populations are individual. It is a non
4 K2
parametric test, whereas ANOVA is a parametric test used to test more than 2 2
samples.
7 What are the major advantages of non parametric methods over parametric methods?
No assumptions are required, more suitable when ranked or scaled. 1 4 K1
Do not take much time, simple calculations. 1
8 Define Kolomogrov simirnnov test
A non parametric test that is concerned with the degrees of agreement between a set of 4 K1
observed ranks and a theoretical frequency distribution. 2
9 Two HR managers A and B ranked 5 candidates for a new position. Their rankings of the
candidates are shown below. Compute the Spearman’s Rank Correlation
Candidate name: Nancy Linda Oviya John Mary
Rank by A: 2 1 3 5 4 4 K2
Rank by B: 1 3 4 5 2
Σd2 = 10, r = 1 – 6 (Σd 2 ) / (n (n2i -1)) 1
r=0.5 positive correlation 1
10 Write the formula for chi – Square test of single standard deviation.
4 K1
Chi square = Σ ((Oi –Ei)2 / Ei) 2
11 Define one sample Runs test
A non parametric test used for determining whether the items in a sample selected 4 K1
2
randomly.
12 Write the standard error of the U statistic of the Mann Whitney U test.
4 K1
σ =√ (n1 n2 (n1+n2 + 1) /12 2
13 A chi square value is never negative. Give reason.
4 K2
Differences between observed and expected frequencies are squared. 1
14 A contingency table for a chi square test has 5 columns and 4 rows . how many degrees of
freedom should be used?
4 K2
DoF = r-1 x c – 1 1
DoF = 12 1
15 Disadvantages of non parametric test.
Based on limited amount of information , it do not make use of all the available 2 4 K2
information. A good deal of information is lost.

UNIT V – CORRELATION, REGRESSION AND TIME SERIES ANALYSIS

1 Differentiate Correlation and Regression.

correlation coefficient are between X and Y is a measure of linear relationship between
1
X and Y. It does not reflect upon the nature of variable 5 K2
Regression coefficients are mathematical measures expressing the average relationship
between the two variables. It reflects on the nature of variable.
1
2 What is cyclical and seasonal variation?
Cyclical variations in a time series are the recurrent variations whose duration is more
1
than one year. 5 K1
Seasonal variations are variations which occur with some degree of regularity within a
specific period of one year or less.
1

7|Page
 3 How will you test the accuracy of regression equation?
If one of the regression coefficients is greater than unity the other must be less than
1 5 K2
unity.
Both the regression lines pass through the point ( , y ) are means of x and y. 1
4 What is non sense correlation?
Correlating irrelevant things is a non sense correlation. When r =0, the correlation 5 K1
2
between x and y is said to be non sense correlation.
5 Find the mean values of the variables X & Y from the following regression
lines 2y – x = 50 ; 3y – 2x = 10
solve equations 1 5 K2
=130, y =190 1
6 Why do we use multiple regressions instead of simple regression in estimating a
dependent variable? 5 K2
When we deal with more than one dependent variable we use multiple regression. 2
7 What are the changes or variations involved in time series analysis?
Secular trend, seasonal variations, cyclical variations and irregular variations. 2 5 K1
8 What is meant by forecasting errors?
Mean absolute deviation MAD = Σ l yi - y i l /n 1 5 K1
where yi = actual value y i = fitted value 1
9 State the major application of Time series analysis.
Analysis of Time series is helpful in economics, Business and science 1 5 K1
It helps in understanding past behavior of a variable 1
10 What are the methods for measuring cyclical variations?
Residual method, Direct method, Reference cycle analysis method, harmonic analysis 2 5 K1
method.
11 Give some examples of time series.
sales, production, import , export, population over the last 5 or 10 years. 2 5 K2
12 What is regression coefficient?
bxy = (nΣxy – ΣxΣy) /( nΣy2 –(Σy)2), 1 5 K1
byx = (nΣxy – ΣxΣy) /( nΣx2 –(Σx)2) 1
13 What are the uses of Regression analysis?
It can be useful to all natural, social and physical sciences where the data are in
1 5 K1
functional relationship.
It helps in prediction and it can estimate the values of unknown quantities. 1
14 What are the time series forecast error measures?
Root mean square error (RMSE) 1
5 K1
Mean absolute Deviation (MAD) 1
Mean Absolute Percentage Error (MAPE)
15 List the Merits and demerits of least Square method.
Merits: this is mathematical method and is completely objective in character. This
method gives trend value for the entire time period. 5 K1

1
Demerits: Time consuming, Tedious. The type of curve to be fitted has to be selected
carefully.
1

PART – B (12 Mark Questions with Key)

S.No Questions Mark COs BTL

UNIT I – INTRODUCTION

1 A sales representative can convert a customer as a potential buyer with the probability of 70% .
8|Page
If he is able to meet 10 customers in a day , Find the probability of (i) Atleast one
customer (ii) not even a single customer (iii) exactly one customer
12 1 K2

9|Page
 Binomial distribution P(X)=ncx px q n-x
4
(i) P(X≥1)= 0.9999
(ii) P(X=0)= 0.0000059 4
(iii) P(X =1) = 0.0001378 4
2 In a bolt factory machines A, B and C manufactures respectively 25 %, 35% and
40%. Of the total of their output 5%, 4%, 2 % are defective bolts. A bolt is drawn
at random from the product and found to be defective. What are the probability 12
that it was manufactured by Machines A, B and C
K2
Formula : and assumptions 1
3
P(E1/A)= 25/69 3
P(E2/A)= 28/69 3
P(E3/A)= 16/69 3
3 In a test of 2000 electric bulbs it was found that the life of a particular make was
normally distributed with an average life of 2040 hours and SD of 60 hours.
12
Estimate the number of bulbs likely to burn for (i) more than 2150 hours (ii) less
than 1950 hours (iii) more than 1920 hours but less than 2160 hours 1 K2
Normal distribution: Formula and given data N=2000 3
P(X>2150) = 0.0336, N= 2000 x 0.0336= 67 3
P(X<1950)= 0.0668, N = 134 3
P(1920<X<2100) = 0.8185, N= 1637 3
4 Marks of PG class are recorded and the head of the department need to do an
analysis based on the student’s performance on the particular paper for the
improvement of result. The data are grouped in the following table. Find the
mean and median. Also find the mark which maximum students obtained. 12
20-30 30-40 40-50 50-60 60-70
3 5 20 10 5 1 K2
Assumed mean = 45, Σfd =90
Mean = A + Σfd/n = 47.093
Median m = l1 + (l2-l1)(m-c)/f = 47
Mode = l1 + [(f1-f0 )i ]/ [(f1-f0 ) + (f1-f2 )] = 46.5
5 Four coins were tossed 150 times and the following results were obtained
No of heads: 0 1 2 3 4
12
Observed frequency: 28 62 46 10 4
Fit a binomial distribution.
Mean = Σfx / Σf = 1.33 1 K2
Mean = np therefore p = 0.2667, q =0.7333
N =150, P(X)= N . ncx px q n-x
0 1 2 3 4
31.80 57.84 42.07 15.30 2.78
6 The ages of a sample of 8 faculty members selected from the school of business
administration are shown below. Compute average age, mode, median age and
S.D 12
Faculty: 1 2 3 4 5 6 7 8
Age: 42 30 73 50 51 37 42 59 2 K2
Mean = Σf/n = 48 4
Median =(n+1/2)th term = 46 4
Mode = 42, S.D =√( Σ(x - )2/n) = 12.63 4

UNIT II – SAMPLING DISTRIBUTION AND ESTIMATION

1 Describe the various technique of sampling. 12

Simple random sampling 3
systematic sampling 3 2 K2
stratified sampling 3
10 | P a g e
 cluster sampling (any four) 3
2 a)In a random selection 64 of 600 road crossing in a town, the mean number of
automobile accident is 4.2 and sample standard deviation is 0.8 . Construct 95 %
confidence interval for the mean number of accidents.
b) A cigarette manufacturer wishes to use the random sample to estimate average 12
Nicotine content. Sampling error should be more than 1 milligram. Standard
deviation is 4 milligrams. What sample size should the company take at 99 %
confidence? 2 K3
a)n=64, N=600, =4.2, s=0.8 1
S.E of mean = s√N-n/√[(n-1)(N-1)] = 0.952 2
Confidence interval at 95% = (4.0135, 4.3865) 3
(b) s=4, E=1, Z= 1% = 2.58 3
n= S2z2/E2 = 107 3
3 a)A simple random sample of size 100 has mean 15, the population variance being
25. Find an interval estimate of the population mean with a confidence level of
99 % and 95 %
b)A random sample of 700 units from a large consignment showed that 200 were 12
damaged. Find
(i) 95% and (ii) 99% confidence limits for the proportion of damaged units in the 2 K3
consignments.
(a) n = 100, =15, SD =5, SE of mean = s/√n = 0.5, 3
Confidence interval at 99 % =( 13.71, 16.29) , at 95 % = (14.02, 15.98) 3
(b) P=x/n = 0.2857, 95% confidence interval = (0.2522, 0.3192) 3
Confidence interval 99% = (0.2416, 0.3298) 3
4 a)The quality control manager of a tyre company has sample of 100 tyres with
mean 30214 km. Population standard deviation is 860 km. Construct 95%
confidence interval of the mean life time of tyre.
b)A principal of a college wants to estimate the proportion of smokers among 12
students. What size of sample size should be taken to have proportion not
exceeding 10% with almost certainty. It is believed from previous records that the 2 K3
proportion of smokers was 0.30.
(a) n =100, =30214, s=860, SE = s/ √n =86 3
Confidence interval at 95% = (30045.44, 30382.56) 3
(b) E =10%, p=0.30, q=0.70 3
n = pqz2/E2 = 189 3
5 a) What do you mean by estimation? Differentiate point estimation and interval
estimation. 12
b) Explain about estimation and qualities of good estimator.
Meaning of estimation 3 2 K3
Point estimation 3
Interval estimation 3
Qualities of good estimator 3
6 Estimate the population mean at 95% confidence interval from the following
sample data drawn from normal distribution
12
x: 10 20 30
f: 6 10 4 2 K3
= Σ fx/n = 19, σ= √[ (Σfx2 - 2)/n] =7 6
confidence interval = 11.08, 26.92 6

UNIT III – TESTING OF HYPOTHESIS - PARAMETRIC TESTS

1 Ten individuals are chosen at random from a population and their heights are
found to be in inches. 63,63,66,67,68,69,70,70,71,71. Find the mean heights in the
universe is 66 inches 12 3 K2

11 | P a g e
 Hypothesis; n=10, µ = 66, = 67.8 2
Σ(x - )2= 81.6, S2 = Σ(x - )2/ n-1 = 9.07, S = 3.01 4
T test = | - µ| / (S/ √n) = 0.18 4
T.V = 2.262, Degrees of freedom = 9, LOS = 5%. Accept Ho 2
2 The average number of articles produced by two machines per day are 200 and
250 with standard deviation 20 and 25 respectively on the basis of records of 25
days of production. Can you regard both the machines are equally efficient at 1% 12
level of significance?
3 K2
Hypothesis, Level of significance = 1%, Given value, 1 = 200, 2= 250, s1=20,
s22=25, n1=25,n 2=25
2
S = n s 2 +n s 2 / n +n -2 = 533.85, S = 23.11 4
1 1 2 2 1 2
T test = | 1 - 2| / s√(1/ n1 +1/ n2) = 7.645 4
T.V = 2.576, Reject Ho 2
3 Time taken by workers in performing a job are given below

Method I: 20 16 26 27 23 22 -

Method II: 27 33 42 35 32 34 38 12

Test at 1% level of significance whether there is any significant difference between the
variance of time distribution. 3 K2

Hypothesis, Level of significance = 5%, Given value, 1 = 22.33, 2= 34.43

2
Σ(x1 - 1)2 = 81.336, Σ(x2 - 2 )2 = 133.70, S 21= Σ(x1 - 1)2 / n1 -1 = 16.27, S 22= Σ(x2 - 4
)2 / n -1 = 22.28
2 2
F test : f= S22/ S 12 = 1.3696, 4
DOF = (6,5) , T.V = 4.95 Accept Ho 2
4 The mean population of a random sample of 400 villagers in Jaipur district was
found to be 400 with standard deviation of 12. The mean population of a random
sample of 400 villages in Meerut district was found to be 395 with a 12
standard deviation 15 .
Is the difference between the two district means statistically significant? 3 K2
N1= 400, n2=400, 1 = 400, 2= 395, s1=12, s2=15 2
Z test | 1 - 2| / √(s 12/n1 +s 22/n2) 4
Z = 5.205, T.V = 1.96 Reject Ho 6
5 Before an increase in Exercise duty on Tea, 800 persons out of 1000 persons were
found to be Tea drinkers and after an increase in exercise duty in Tea 800 people
were Tea drinkers in a sample of 1200 people . Test whether there is any 12
significant difference in tea consumption at 5 % level.
3 K2
n1= 1000, n2=1200, 1= 800, 2=800, p1= 0.8, p2 =0.667 2
P= 0.7291, q=0.2709 2
Z test = | p1-p2| / √ (pq/n1+pq/n2) = 6.8349 . 6
T.V = 1.96.Accept Ho 2
6 In a big city 325 men out of 600 men were found to be smokers. Does this
information supports the conclusion that the majority of men in this city are
smokers? 12
3 K2
N=600, x = 325, p‟= x/n = 0.54, Hypothesis 4
P=0.5, q=0.5, z tset = p‟ – p / (√pq/n) = 2 6
T.V = 1.96, LOS = 5% . Reject Ho. 2
12 | P a g e
 UNIT IV – NON-PARAMETRIC TESTS
1 The following table gives the number of air crashes that occurred during various days
of the week. Test whether accidents are uniformly distributed over the week.
12 Days: Mon Tue Wed Thur Fri Sat
No of aircrash : 14 18 12 11 15 14
Hypothesis, Los = 5% 2 4 K3
E i = Σ x /n = 14, 2
Chi square = Σ ((Oi –Ei)2 / Ei) = 2.13 6
DoF = n-1 -5, T.V = 11.07. Accept Ho. 2
2 A sample of 12 fathers and their sons height is given below

Father X 65 63 67 64 68 62 70 66 68 67 69 71
12
Son Y 68 66 68 65 69 66 68 65 71 67 68 70

Calculate Spearman’s Rank correlation. 4 K3

Arrange data in ascending order and ranking 2
Σd 2= 72.5 4
i
Tx= repeated value in X = m(m2 – 1)/ 12 = 0.5 2
Ty= repeated value in Y = m(m2 – 1)/ 12 = 0.5
2 2
r = 1 – 6 (Σd + T + T ) / (n (n -1)) = 0.722 4
i x y
3 Caffeine content in two brands of Coffee, Elite and Hot cafe are given below. Test
the Hypothesis at 0.05 Level of Significance that the average caffeine contents of
two brands are equal against that they are unequal.
12
Elite 2.1 4.0 6.3 5.4 4.8 3.7 6.1 3.3 - -
Hotcafe 4.1 0.6 3.1 2.5 4.0 6.2 1.6 2.2 1.9 5.4
4 K3
Hypothesis, LOS = 5%
Ascending order arranging and ranking

2
R1 = 93, n1=8, n2=10

2
U = n1 n2 + (n1(n1 +1) / 2 )– R1 = 23, µ = n1 n2 /2 = 40, σ =√ (n1 n2 (n1+n2 + 1) /12 =
6
11.25
Z = (U -µ)/σ = 1.51 , T.V = 1.96 Accept Ho 2
4 Use sign test to see if there is a difference between the number of days until
collection of an account receivable before and after collection policy. Use 0.05 level
of significance 12
Before 30 28 34 35 40 42 33 38 34 45 28 27 25 41 36
After 34 29 33 32 47 43 40 42 37 44 27 33 30 38 364 K3
n=14, no of + =5, no of - =9, p= 0.357, q = 0.643, 2
Hypothesis, LoS = 5% 2
Standard error = σp = √pq /n = 0.13 4
Limits of acceptance region = (P Ho + 1.96 σp) = (0.24, 0.75) . Accept Ho 4
5 Discuss the association for 1000 school boys between general and mathematical
abilities
General Ability
Good Fair Poor
Mathematica

12
l Ability

Good 44 22 4
Fair 265 257 178 4 K3

Poor 41 91 98
13 | P a g e
Calculate Expected value. 2
Hypothesis, LoS = 5% 2
Chi square = Σ ((Oi –Ei)2 / Ei) = 69.142 4
DoF= (r-1)(c-1) = 4, T.V = 3.841 Reject Ho 4

14 | P a g e
 6 The marks secured in History test of the students in public school and Primary
schools are given below
Primary: 73 75 83 77 72 69 56 80 68 60 84
Public: 70 78 79 81 65 63 74 83 67 76 88 61 64 71 86 48 12
Test the Hypothesis at 0.05 LoS that there is no significant difference in the
performance of test against the alternative that the performance are significantly
different. 4 K3
Hypothesis, LOS = 5% 2
Ascending order arranging and ranking 2
R1 =154.5, n1= 11, n2=16 2
U = n1 n2 + (n1(n1 +1) / 2 )– R1 = 87.5, µ = n1 n2 /2 = 88, σ =√ (n1 n2 (n1+n2 + 1) /12 =
4
20.26
Z = (U -µ)/σ = 0.02 , T.V = 1.96 Accept Ho 2

UNIT V – CORRELATION, REGRESSION AND TIME SERIES ANALYSIS

1 Find the correlation coefficient between X and Y for the

data X: 12 9 8 10 11 13 7
Y: 14 8 6 9 11 12 3 12
(ii)Find the means of the variables from the regression equations
10y= 8x + 66 and 20 x = 9y +107 5 K3
Cov (x,y) = 46, σy= 5.29 σy=9.16 4
r = cov(x,y)/(σx.σy) , r = 0.949 4
X=13, y=17 4
2 From the following data (i) Find two regression equation (ii) Calculate correlation
coefficient (iii) Most likely mark of statistics mark when mark in economics is 30.
Economics 25 28 35 32 31 36 29 38 34 32 12
Statistics 43 46 49 41 36 32 31 30 33 39
bxy = (nΣxy – ΣxΣy) /( nΣy2 –(Σy)2), byx = (nΣxy – ΣxΣy) /( nΣx2 –(Σx)2), bxy = 0.233,
2 5 K3
bxy = 0.66
Mean = 32, mean y= 38 2
Regression eqn x on y : x =0.233y + 23.14, Regression eqn y on x : y =0.666x + 16.88 4
Correlation = r =0.392 2
Statistics mark y = 37 2
3 Fit a trend line to the following data using free hand method and moving average
method
Year 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 12
No. of 15 18 17 20 23 25 29 33 36 40
5 K2
students
3 yearly moving average: 16.67 18.33 20 22.67 25.67 29 32 36.33 4
Graph (free hand) 4
Graph ( moving average) 4
4 A computer while calculating correlation r from 25 pairs of observation obtained
the following. n=25, ∑x = 125, ∑y = 100, ∑x2 = 650, ∑y2 = 460, ∑xy = 508. A 12
recheck showed that he had copied two pairs (6,14) and (8,6) while correct values
are (8,12) and (6,8). Obtain the correct value of correlation,. 5 K3
Σx = 125,Σy = 100, Σx2 = 650, Σy2 = 436, Σxy = 520 4
Cov (x,y) = 0.8, σx = 1,σy = 1.2 6
r = 0.67 2

15 | P a g e
5 Using the method calculate seasonal variations from the data given below
Year I Quarter II Quarter III Quarter IV Quarter
2011 72 68 80 70
2012 76 70 82 74
2013 74 66 84 80
2014 76 74 84 78
5 K2
2014 78 74 86 82

Total 376 352 414 384 2

Seasonal average 75.2 70.4 82.8 76.8 2
General average = 76.3, seasonal index = seasonal average x 100/ general average =
4
98.55, 92.26, 108.5, 100.65
6 What are the assumptions made by the regression model in estimating
the parameters and in significance testing? 12
Analyze In what ways regression analysis can be used? 5 K2
Assumptions in regression model 6
Uses of regression analyzes 6

PART – C (20 MARK QUESTIONS WITH KEY)

S.No QUESTIONS Mark COs BTL

UNIT I – INTRODUCTION

1 A manufacturing firm produces steel pipes in three plants with daily production
of 500, 1000, 2000 with respectively. According to past experience it is known that
fraction of defective output is 0.005, 0.008, 0.010. If a pipe is selected from a days 20
total production and found to be defective. What is the probability of that it come
from I plant, II plant and III plant?
1 K2
Formula : and assumptions

2
P(A1/B)= 0.0007

4
P(A2/B)= 0.0022

4
P(A3/B)= 0.0057

4
P(I plant) = 0.0814, P(II plant) = 0.2558, P(III plant) = 0.6627

6
2 Global green company has the average early sales in an outlet is Rs. 25 lakhs and
S.D is Rs. 5 Lakhs . If the sales follow normal distribution find
(i) Probability of sales greater than Rs. 30 Lakhs
(ii) Probability of sales between Rs. 20 Lakhs and 30 lakhs.
20
(iii) Since 1000 outlets the company owns, Find the number of outlets
less than Rs. 15 Lakhs. 1 K2
µ = 25, S.D =5, z = x -µ /σ 3
P(x ≥ 30 ) = p(z ≥ 1) = 0.1587 5
P (20 ≤ x ≤ 30 ) = P (-1 ≤ z ≤ 1 ) = 0.6826 5
P (X < 15) = P(z < -2) = 0.0228. No of outlets = 23 7

16 | P a g e
 UNIT II – SAMPLING DISTRIBUTION AND ESTIMATION

1 a)A movie maker sampled 55 fans who viewed his master piece movie and asked
them whether they had planned to see it again. Only 10 of them believed that the
movie was worthy of a second look. Find the Standard error of the population of
fans who will view the film a second time. Construct a 90 % confidence interval
for this population. 2 K3

20

17 | P a g e
 b) The manager of a shop selling beverages wants to estimate the actual amount
of beverages in one litre bottles from a nationally known manufacturer. As per
manufacturer’s specification the standard deviation of the volume of the
beverage is 0.02 litre . The average amount of beverage per one litre bottle is
found to be 0.995 litre on checking 50 bottles. Set up 99 % confidence interval,
estimate of the true population average amount of beverage in a one liter bottle.
Check whether the manufacturer is genuine in filling the beverage.
(a) n=55 , p =0.18, q=0.82 3
SE = √pq/n = 0.052 4
TV at 90% = 1.645, P= (0.095, 0.266) 3
(b) n=50, =0.995, σ = 0.02 4
T.V = 2.58, Confidence limit = ( 0.987, 1.003) Reject Ho. 6
2 a)Television advertisers mistakenly believe that most viewers understand most
of the advertisement that they see and hear . In this connection, a research study
covering 2300 viewers above the age of 20 years was taken. Each viewer looked at
30 second television advertisement or a part of it. It was found that 1914 viewers
misunderstood either the entire advertisement or a part of it. Determine 95%
confidence interval for the proportion of all viewers that will misunderstand all
are part of the television advertisement used in this study.

b) a stock market analyst wants to estimate the average return on a certain 20

stock. A random sample of 15 days yields an average return of =10.37% and a 2 K3
standard deviation of s = 3.5%. assuming a normal population of returns. Give a
95% confidence interval for the average return on this stock.
a)σ = √pq/n 2
p= 0.832, q = 0.1678 2
σ = 0.00783 2
confidence interval at 95 % = (0.815, 0.845) 4
(b) =10.37, s =3.5, T.V= 2.145 4
Confidence interval = (8.43, 12.31) 6

UNIT III – TESTING OF HYPOTHESIS - PARAMETRIC TESTS

1 Four doctors each test 4 treatments for a certain disease and observe the number of
days each patient takes to recover. The recovery time in number of days are given as
follws.
Treatment
Doctor A B C D
1 10 14 19 20
2 11 51 17 21
3 9 12 16 19
4 8 13 17 20 20 3 K2
Find the Variance at 5 % level of significance to test whether the sales differ with
respect (i) Treatment (ii) Doctor
Hypothesis, CF = T2/N = 4795.56 4
TSS = 1477.44, SSR = 321.69 4
SSC = 380.69, SSE = 775.06 4
F ratio =1.47(between treatment) F= 1.24 (Between doctor) 4
T.V = 3.86 (3,9) (both cases)
4
(i) Accept H0(ii) Accept H0

18 | P a g e
 2 To study the performance of 3 detergents and three different water
temperatures, the following whiteness readings were obtained using specially
designed equipment.
Perform two way ANOVA at 5% level.
Detergents
Water Temperature A B C
Cold 57 55 67
20
Warm 49 52 68
3 K2
Hot 54 46 58

Hypothesis, CF = T2/N = 28448.44 4

TSS = 439.56, SSR = 73.56 4
SSC = 304 .22, SSE = 61.78 4
F ratio =2.38(between temperature) F= 9.85 (Between detergents) 4
T.V = 6.94 (both cases)
4
(i) Accept H0(ii) Reject H0

UNIT IV – NON-PARAMETRIC TESTS

1 A department store has three sales counters. The manager wants to compare the
sales of the three stores over a six day week. The relevant data is as follows:
Counter A sales: 78 62 71 58 73
Counter B sales: 76 85 77 90 87
Counter C sales: 74 79 60 75 80
Compare the equality of mean sales in all the three counters using Kruskal Wallis 20
method.
Hypothesis, LOS 5%, n= n1+n2+n3 =15 4 4 K3
Arrange in ascending order and ranking 4
R1= 23, R2 = 59, R32 = 38 2 4
H = 12/ n (n+1) [ R /n + R /n R 2/n ] – 3 (n+1) = 6.54 6
1 1 2 2+ 3 3
T.V = 5.991 Reject H0 2
2 A dietician wants to test three types of diet plans 1,2,3. He selected a
homogenous group of 23 persons and placed them into 3 sub groups. Each
subgroup trying a different diet plan. Each plan was tried for a period of 30
days. The following observation of weight loses in pounds were recorded for
members of each group
after this period of 3o days. Determine at 0.05 LoS whether there is a difference in 20
weight reducing effects or not.
Diet plan 1: 4.0 3.8 3.7 6.2 5.6 4.2
4 K3
Diet plan 2: 3.6 5.2 2.8 3.0 3.8 5.0 3.9 5.5
Diet plan 3: 6.5 7.2 5.9 5.5 6.8 7.7 8.0 8.2 7.0
Hypothesis, LOS 5%, n= n1+n2+n3 =23 4
Arrange in ascending order and ranking 4
R1= 56.5, R2 = 52, R3 = 167.5 4
H = 12/ n (n+1) [ R 2/n + R 2/n R 2/n ] – 3 (n+1) = 7.748 6
1 1 2 2+ 3 3
T.V = 5.991 Reject H0 2
UNIT V – CORRELATION, REGRESSION AND TIME SERIES ANALYSIS
1 Mr. X owns a small company that manufactures portable message tables. Since
he started the company, the number of tables he has sold is represented by this
time series:
Year: 1987 1989 1990 1991 1992 1993 1996 number of tables sold
Tables : 140 144 160 152 168 176 180 by him. Also calculate
Find the linear equation using least square method that describes the trend in the trend value for the
19 | P a g e
year 1988 20 5 K2

20 | P a g e
 Σy = na+ bΣx, Σxy = aΣx +bΣx2, 4
a= 159.29, b = 4.955 4
Trend value for 1988 = 144.425 2
Trend values : 139.45, 149.37, 154.34, 159.29, 164.25, 169.21, 184.09 6
Graph 4
2 The manager of a company wants to analyze about the sales of a particular brand
of television and he wants to forecast the sales of the television in future. Data
from 1985 to 1989 was given. Fit a parabola of second degree to the following and
20
analyse using the curve.
Year: 1985 1986 1987 1988 1989
Sales: 16 18 19 20 24 5 K3
a= Σy – cΣx2/n , b =Σxy/ Σx2 , c =Σx2y – a Σx2/Σx4 4
a= 18.83, b = 1.8, c = 0.286 6
Trend values: y = a+ bx +cx2= 16.35, 17.31, 18.83, 20.91, 23.5 6
Graph 4

21 | P a g e