MA3251-STATISTICS & NUMERICAL METHODS

Two mark questions & answers

UNIT – I TESTING OF HYPOTHESIS
1.State Null Hypothesis(H0) Nov-Dec 2012/May-june2011
For applying the test of significance,we first set up a hypothesis
which is a statement about the population parameter. This statement is
usually a hypothesis of no difference and so it is called null hypothesis
and is denoted by H0.
---------------------------------------------------------------------------------------------------------------------

2.What do you mean by Alternative hypothesis? Nov-Dec 2012/May-june2011

Any hypothesis which is complementary to the null hypothesis(H0)
is called an alternative hypothesis and is denoted by H1.
---------------------------------------------------------------------------------------------------------------------

3.Define Critical region.

A region, corresponding to a statistic t, in the sample space S which
amounts to rejection of the null hypothesis H0 is called as critical region
or region of rejection.
---------------------------------------------------------------------------------------------------------------------

4.What is meant by Critical value or Significant value?

The value of the test statistic which separates the critical region
from the acceptance region is called the critical value or significant value.
---------------------------------------------------------------------------------------------------------------------

5. DefineType I Error &Type II Error. Nov-Dec 2011/Apr-May 2011

In sampling theory to draw a valid inference about the population
parameter on the basis of the sample results,we decide to accept or to
reject the null hypothesis after examining a sample from it.
Type I Error : Rejection of null hypothesis when it is correct.
Type II Error : Acceptance of null hypothesis when it is wrong.
-------------------------------------------------------------------------------------------------------------------

6. Write down the procedure for Testing the hypothesis(For two-tailed test)
The null hypothesis is
The alternative hypothesis is
Since n is large the sampling distribution of is approximately normal(on the
assumption that H0 is true the statistic
is approximately N(0,1). We take the level of significance as ).

Inference : For a significance level (5% level)

if , is accepted at 5% level.
If >1.96, is rejected at 5% level.
For (1% level)
if , 0 is accepted at 1% level.
If , is rejected at 1% level.
---------------------------------------------------------------------------------------------------------------------

- STATISTICS & NUMERICAL METHODS

PAGE 1
7.State Confidence or Fiducial Limits & Confidence Interval.
Confidence interval is an interval that provides lower and upper
limits for a specific population parameter is expected to lie.(whose value
is unknown). The two values of the statistic which determine the limits
of the interval are called confidence limits. Thus confidence interval is
the interval in which a population parameter is expected to lie with
certain probability
---------------------------------------------------------------------------------------------------------------------

8.Define student’s t-test for difference of means of two samples.

withd.f. where

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

9.Write down the formula of test statistic t to test the significance of

Difference of means of two samples.
are sample means, are sample

Variances, are sample sizes.

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

10. State the applications of distribution. Nov-Dec 2011

The chi-square distribution has a large number of applications in
statistics and some of them are listed below:
1. To test the goodness of fit.
2. To test the independence of attributes.
3. To test the homogeneity of independent estimates of the population variance.
4. To test if the hypothetical value of the population variance is
5. To test the homogeneity of independent estimates of the population Correlation
co-efficient .
---------------------------------------------------------------------------------------------------------------------

11.Write down the conditions for validity of test. Apr-May 2011/May-June2011

For the validity of chi-square test of goodness of fit between theory and
experiment , the following conditions must be satisified.
1.The sample observations should be independent.
2. Constraints on the cell frequencies,if any, must be linear.
3. N, the total frequency should be reasonably large,say greater than 50.
4. No theoretical cell frequency should be less than 5. If any theoretical
Cell frequency is less than 5, then for application of test , it is
pooled with the succeeding or preceding so that the pooled frequency
is more than 5. This is to make the distribution a continuous
distribution to maintain the character of continuity of the distribution.
-----------------------------------------------------------------------------------------------------------------

STATISTICS & NUMERICAL METHODS

12.What do you mean by Chi-square test of goodness of fit?Apr-May 2010
This is a powerful test for testing the significance of the discrepancy
between theory and experiment. It helps us to find if the deviation of
the experiment from theory is just by chance or it is due to the
inadequacy of the theory to fit the observed data.
If Oi(i=1,2,…n) is a set of observed frequencies and Ei(i=1,2,…n) is the
corresponding set of expected frequencies then

with the condition that

follows chi-square distribution with (n-1) degrees of freedom.
---------------------------------------------------------------------------------------------------------------------

13.What are the assumptions of t-test?

(1)The parent population from which the sample is drawn is normal.
(2)The sample observations are independent.
(3)The sample is random.
(4) The population standard deviation is unknown and the sample size is n<30.
______________________________________________________________________________
14.State the chi-square value for 2x2 contingency table Nov-Dec 2012
In a 2x2 contingency table where in the frequencies are
a b
c d

the value of is
---------------------------------------------------------------------------------------------------------------------

15.Write down the applications of F test.

(i) To test whether there is any significant difference between two estimates of
Population variance.
(ii)To test if the two samples have come from the same population.
-------------------------------------------------------------------------------------------------------------------------------

STATISTICS & NUMERICAL METHODS

 MA3251-STATISTICS & NUMERICAL METHODS
Two mark questions & answers
UNIT – II DESIGN OF EXPERIMENTS

1. Write any two difference between RBD & CRD Apr-May2011

CRD RBD
a. It is one way classification It is two way classification
analysis of variance analysis of variance

b. Experimental error is large It is more different then CRD

because of reduced experimental error
-----------------------------------------------------------------------------------------------------------------
2. Discuss the advantages and disadvantages of RBD Apr-May2010
Advantages :
a. It has a simple layout but it is more efficient than CRD because of reduction of
experimental error
b. It is flexible and so any number of treatments and any number of replication may be
used.
c. It is a two way classification analysis of variance.
Disadvantages :
a. If the number of treatments is large than the size of the blocks will increase this may
cause heterogeneity within blocks
b. The shape of the experimental material should be rectangular.
---------------------------------------------------------------------------------------------------------------------
3. State the advantages of a factorial experiments over a simple experiment.Apr-May2010
a. Factorial design are widely used in experiments involving several factors
where it is necessary to study the effort of the factory on a response.
b. The factorial design are more efficient than one factor at a time
experiments.
c. Factorial designs form the basis of other designs of considerable
Practical value.
---------------------------------------------------------------------------------------------------------------------
4. Why a 2 x 2 Latin square is not possible?Explain Apr-May2007/2008
Consider n x n Latin square design, the degrees of freedom for SSE is
=(n2-1) – (n-1)-(n-1)-(n-1)
=n2-1-3n+3
=n2-3n+2
=(n – 1)(n – 2)
for n = 2, degrees of freedom S.S.E = 0 and hence MSE is not defined. Hence a 2 x 2 Latin
square design is not possible.

STATISTICS & NUMERICAL METHODS

5. Compare and contrastLSD and RBD Apr-May2006,2009
LSD RBD
a. It is a suitable for small number No such restrictions suitable for upto
of treatments, between 5 and 12 24 treatments.
b. The number of rows and columns There is no such restrictions.
are equal and hence the number It can have any number of replications
of replications is equal to the and treatments.
number of treatments
d. Experimental error is reduced Variations is controlled in one
to a large extent, because direction only.
variation is controlled in two
directions
d. Experimental area must be It is a rectangle (or) square.
a square
---------------------------------------------------------------------------------------------------------------------

6. What are the basic principles of the design of experiments? Nov-Dec2011/Nov-Dec2012

May-June2011
i. Replication ii. Randomization iii. Local control
--------------------------------------------------------------------------------------------------------------------
7. Define “Analysis of variance” or ANOVA
According to R.A fisher, analysis of variance is the separation of variance as
cribable to on group of causes from the variance as cribable to other groups.
8. Write down the assumptions in analysis of variance Nov-Dec2010/Nov-Dec2011
i. Normality, ii. Homogeneity iii. Independence of error
---------------------------------------------------------------------------------------------------------------------
9. Define RBD Nov-Dec2012
Let us consider an agricultural experiment using which we wish to test the effect of ‘k’
fertilizing treatments on the yield of crops. We assume that we know some information about
the soil fertility of the plots. Then we divide the plots into ‘h’ blocks, according to the soil
fertility each block containing ‘k’ blocks. Thus the plots in each block will be of homogeneous
fertility as far as possible within each block, the ‘k’ treatments are given to the ‘k’ plots in a
perfectly random manner, such that each treatment occurs only once in any block. But the same
k treatments are repeated from block to block. This design is called Randomised Block Design.
--------------------------------------------------------------------------------------------------------------------
10. What are the advantages of the Latin square design over other designs.May-June2011
The advantages of the Latin square design over other designs are :
(i) With a two-way stratification or grouping, the Latin Square controls more of the
variation than the completely randomized design or the randomized completely block design.
The two-way elimination of variation often results in small error mean square.
(ii) The analysis is simple, it is only slightly more complicated than that

STATISTICS & NUMERICAL METHODS

for the randomized complete block design.
(iii) The analysis remain relatively simple even with missing data, Analytical procedures
are available for omitting one or more treatments, rows, or columns.
However the number of treatments is limited to the number of rows and columns except
in some situations. For more than ten treatments, the Latin square is seldom used.
--------------------------------------------------------------------------------------------------------------------
11. What do you understand by “Design of an experiment”?
The design of experiment may be defined as “the logical construction of the
experiment in which the degree of uncertainity with which the inference is
drawn may be well defined.
--------------------------------------------------------------------------------------------------------------------
12. What are the advantages of a completely randomized experimental designs?
Nov-Dec2010
The following are the main advantages of this type of design :
1. It is easy to lay out the design.
2. It allows for complete flexibility. Any number of factor classes and replications
may be used.
3. The statistical analysis is relatively simple, even if we donot have the same
number of replicates for each factor class or if the experimental errors are
not the same from class to class of this factor.
4. The method of analysis remains simple when data are missing or rejected
and the loss of information due to missing data is smaller than with any
other design.
--------------------------------------------------------------------------------------------------------------------
13. What is the aim of the design of experiments?
The main aim of the design of experiments is to control the extraneous
variables and hence to minimize the experimental error so that the results of the
experiments could be attributed only to the experimental variables.
14. Define experimental error.
The estimation of the amount of variation due to each of the independent
factors separately and then comparing these estimates due to assignable factors
with the estimate due to the chance factor is known as experimental error or
simple error.
---------------------------------------------------------------------------------------------------------------------
15.When do you apply analysis of variance technique?
To test the homogeneity of several means.
---------------------------------------------------------------------------------------------------------------------

STATISTICS & NUMERICAL METHODS

 MA3251-Statistics & Numerical Methods
Unit III - Solution of Equations and Eigen value Problems
Two mark Question and answer
1. Difference between Gauss elimination and Gauss Seidel.

Gauss elimination Gauss Seidel

1. Direct method Iterative method
2. Solution is accuracy Solution is required degree of accuracy
3. For all systems of equations This method will not work. Since the convergence is
this method will work not assured.

2. What is the condition on A for solving the system of equation Ax = B by Jacobi and
gauss-seidel?
The system of equation is diagonally dominant.
.
3. Write the iterative formula of Newton-Raphson method.

4. State the order of convergence and convergence condition for newton’s Raphson
method.
The order of convergence is 2.
Condition for convergence is
5. What are the merits of Newton’s method of iteration?
Newton’s method is successfully used to improve the result obtained by other methods. It
is applicable to the solution of equations involving algebraical functions as well as
transcendental functions.
6. Show that newton’s Raphson formula to find can be expressed in the form

If then

STATISTICS & NUMERICAL METHODS

Let and

=
7. For Solving a linear system, Compare Gaussian elimination method and Gauss-
Jordan method.
Gaussian elimination Gauss- Jordan method
1. Coefficient matrix is transformed Coefficient matrix is
into upper triangular matrix. transformed into diagonal
matrix.
2. Direct Method Indirect Method
3. We obtained Solution by Back No need of Back Substitution
Substitution method. method.
8. State the principle used in Gauss- Jordan method.
Coefficient matrix is transformed into diagonal matrix.
9. Give two indirect methods to solve a system of linear equations.
Gauss-jacobi method; Gauss –seidel method.
10. What is meant by diagonally dominant?
The absolute value of the largest coefficient is greater than (or) equal to the sum of the
absolute values of all the remaining coefficient.
11. Define algebraic and transcendental equations.
The equation of the form are called algebraic equations if is purely a
polynomial in x.
If also contains trigonometric, logarithmic, exponential function, then the equation
is known as transcendental equations.
12. Compare Gauss-elimination and Gauss-seidel methods for solving linear systems of
the form Ax = B.
Gauss-elimination is direct method.
Gauss-seidel is iterative method.

STATISTICS & NUMERICAL METHODS

13. What type of eigen value can be obtained using power method?
We can obtain dominant eigen value of the matrix.
14. State the difference between direct and iterative methods of solving system of
equations.
Direct methods Iterative methods
1. It gives exact value It gives only approximate solution
2. Simple, take less time Time consuming and labourious.
3. This method determine all the roots at the same This method determine only one
time. root at a time.

15. Find the inverse of the matrix A = by Gauss –jordan method.

=
By using elementary row operation.

Hence

16. Are the first iteration values same it the equations are
solved by Gauss- seidel and Gauss – Jacobi method.

Let
Gauss – Jacobi method :
Gauss- seidel method:

17. Solve the linear system by gauss –jordan method.

=
Therefore x = 1 and y = 1

STATISTICS & NUMERICAL METHODS

18. Find the first iteration values of x,y,z satisfying

19. By Gauss elimination method, solve

20. On what type of equation newton’s method can be applicable?

Newton’s method can be applicable for algebraic and transcendental equation.
21. State the basic principle involved for finding by Gauss Jordan method.
Reduce the augmented matrix (A / I) into (I/ X) ,then
22. Establish an iteration formula to find the reciprocal of a positive number N by
newton’s method.

= +

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

STATISTICS & NUMERICAL METHODS

 MA3251-STATISTICS & NUMERICAL METHODS
Unit-IV INTERPOLATION , NUMERICAL DIFFERENTIATION AND INTEGRATION
Two mark Question and answer

1. What is the nature of the nth divided difference of a polynomial of the nth degree?
The nth divided difference of a polynomial of the nth degree is constant.
2. State Newton’s divided difference formula.

3. State the properties of divided difference.

1.The divided difference are symmetrical in all their arguments.
2.The divided difference of sum (or) difference of two functions is equal to the sum (or)
difference of the corresponding separate divided difference.
3. The nth divided difference of a polynomial of the nth degree is constant.
4.The divided difference operator is linear.
4. Show that the divided difference are symmetrical in all their arguments.(or)
The value of any difference is independent of the order of the argument.
We know that

Therefore
5.Find the divided difference table for

-1 -1
2
1 5 16/3
18 .94
2 23 10
48
4 119
6.Using Lagrange’s formula , to find the quadratic polynomial that takes these value.
then find y(2).

7. Define forward difference and backward difference.

Forward

Backward

STATISTICS & NUMERICAL METHODS

8.Define central difference and divided difference.
central difference

Divided difference

9. Evaluate
=

10.Evaluate
=

11.Find the sixth term of the sequences 8,12,19,29,42…

0 8
4
1 12 3
7 0
2 19 3
10 0
3 29 3
13
4 42

=
= 8 + 5(4) + 10(3) + 10(0) = 58
The sixth term is 58.
12.Find the second divided difference with arguments a,b. If

, Similarly

13. State Newton’s formula to find f’(x) using the forward differences.
Let y=f(x) be a function taking the values corresponding
to of the independent variable x. Let the values of x be
at equidistant intervals of size h.
Then Where -------(1)
(1) gives the value of at any x, which is a non tabular value.
In particular, at , u=0. Then putting u=0 in (1), we have

STATISTICS & NUMERICAL METHODS

14.Find at x=1 from the following table:
x 1 2 3 4
y 1 8 27 64
The forward difference table is as follows.
x y
1 1
7
2 8 12
19 6
3 27 18
37
4 64

Here h=1,

------------------------------------------------------------------------------------------------
15.Find at x=2 from the following data
x: 2 3 4
y: 26 58 112

------------------------------------------------------------------------------------------------
16.Find at x=6 from the following data
x: 2 4 6
y: 3 11 27

----------------------------------------------------------------------------------------------
17.A curve passing through the points (1,0),(2,1) and (4,5).Find the slope
of the curve at x=3

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

STATISTICS & NUMERICAL METHODS

18.State the basic principle for deriving Simpson’s rule.(or)
When does Simpson’s rule give exact result?
Simpson’s rule will give exact result, if the entire curve y=f(x) is
itself a Para bola.
------------------------------------------------------------------------------------------------
19.state the order of error in Simpson’s rule.
Error in Simpson’s rule is of order .
------------------------------------------------------------------------------------------------
20.Using Simpson’s rule, find given

------------------------------------------------------------------------------------------------
21.A curve passing through (2,8),(3,27),(4,64) and (5,125). Find the area
of the curve between x-axis and the lines x=2 and x=5, by Trapezoidal rule.

-----------------------------------------------------------------------------------------------
22.Evaluate by Simpson’s rule, taking h=1
x: -2 -1 0 1 2
y: 16 1 0 1 16

------------------------------------------------------------------------------------------------
23.Why is Trapezoidal rule so called?
The trapezoidal rule is so called because it approximates the integral
By the sum of a trapezoids.
-----------------------------------------------------------------------------------------------
24.How the accuracy can be increased in Trapezoidal rule of evaluating
A given definite integral?
If the number of points of the base segment b-a, (the range of
Integration) is increased, a better approximation to the area given
by the definite integral will be obtained.
---------------------------------------------------------------------------------------------
25.Evaluate by Trapezoidal rule,dividing the range into 4 equal parts.

Here

f(x)=

STATISTICS & NUMERICAL METHODS

26. Using Trapezoidal rule, find from the following set of
Values of x and f(x)
x 0 1 2 3 4 5 6
f(x) 1.56 3.64 4.62 5.12 7.08 9.22 10.44
Here h=1

27. What is the local error term in Trapezoidal formula?

Principal part of the error in the interval (
Where is the value of y and is the value of the second
derivative of y at x=
------------------------------------------------------------------------------------------------
28. State the local error term in Simpson’s one third rule.
Principal part of the error in the interval (
Where is the value of y and is the value of the fourth
Order of y at x=
------------------------------------------------------------------------------------------------
29.What are the errors in Trapezoidal and Simpson’s rule of numerical
Integration?
Error in Trapezoidal rule
Error in Simpson’s rule
-----------------------------------------------------------------------------------------------
30.In order to evaluate by Simpson’s what is the
restriction on the number of intervals?
Let n=interval
Simpson’s rule : The number of ordinates is odd or the intervals
Number is even.

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

STATISTICS & NUMERICAL METHODS

 Unit V-NUMERICAL SOLUTION OF ORDINARY DIFFERENTIAL
EQUATIONS
1.Write down the fourth order Taylor algorithm.
Let
Then the Taylor algorithm is given by

------------------------------------------------------------------------------------------------
2. What are the merits and demerits of the Taylor series method?
It is a powerful single step method. It is the best method if the
expression for higher order derivatives are simple.
The major demerit of this method is the evaluation of higher order
derivatives become tedious for complicated algebraic expressions.
------------------------------------------------------------------------------------------------
3.Given Find by Taylor series method.

where h=0.1

------------------------------------------------------------------------------------------------
4.Find y(0.1) by Euler’s method, given that
Given

------------------------------------------------------------------------------------------------
5. Using Euler’smethod,compute for x=0.1 and 0.2 with h=0.1 given

Given

------------------------------------------------------------------------------------------------
6. Find y(0.1) from by Euler’s method.
Given

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

STATISTICS & NUMERICAL METHODS

7. Given and y(0)=1. Find y(0.01),y(0.02) by Euler method.
Given

------------------------------------------------------------------------------------------------
8. State modified Euler algorithm to solve at

------------------------------------------------------------------------------------------------
9. Write down the Runge-kutta formula of fourth order to solve

Let h denote the interval between equidistant values of x. If the

initial values are , the first increment in y is computed from the
formulas.

Then
The increment in y in the second interval is computed in a similar
manner using the same three formulas, using the values in the
place of respectively.
__________________________________________________________________
10. State the advantages of Runge-Kutta method over Taylor series
method.
Runge-Kutta methods do not require prior calculation of higher
derivatives of y(x), as the Taylor method does. Since the differential
equations using in applications are often complicated, the calculation
of derivatives may be difficult.
Also, the Runge-Kutta formula involve the computation of f(x,y) at
various positions, instead of derivatives and this function occurs in the
given equation.
------------------------------------------------------------------------------------------------
11.What are the distinguished properties of Runge-Kutta methods?
1. These methods do not require the higher order derivatives and
requires only the function values at different points.
2. To evaluate , we need only but not previous of y’s
3. The solution by these methods agree with Taylor series solution
Upto the terms of where r is the order of the Runge-Kutta
method.
------------------------------------------------------------------------------------------------
12. Which is better Taylor series method or Runge-Kutta method? Why?

STATISTICS & NUMERICAL METHODS

 Runge-Kutta method is better since higher order derivatives of y are
not required. Taylor series method involves use of higher order
derivatives which may be difficult in case of complicated algebraic
equations.
------------------------------------------------------------------------------------------------
13.State the order of error in R-K method of fourth order.
Error in R-K fourth order method is where h is the interval of
differencing.
------------------------------------------------------------------------------------------------
14.State Milne’s Predictor-Corrector formula.
Predictor:
Corrector:
------------------------------------------------------------------------------------------------
15. State the Predictor-Error and Corrector-Error in Milne’s method.
Predictor-Error = ; Corrector-Error =
------------------------------------------------------------------------------------------------
16.Distinguish Single-step and Multi-step methods.
Single-step methods: To find , the information at is enough
Multi-step methods: To find , the past four values
and are needed.

------------------------------------------------------------------------------------------------
17. State the finite approximations for and with error terms.
and . Then

, Error =
------------------------------------------------------------------------------------------------
18. Solve
Let
By boundary condition, y(1)=1 and y(2)=2
We have
We have to determing
Replacing
-----------(1)
Put i=1 ,
Using ,

------------------------------------------------------------------------------------------------
19. Write the central difference approximations for &
= ; =
----------------------------------------------------------------------------------------------

STATISTICS & NUMERICAL METHODS