Scribd
Upload
663 views

Assignment 2

1. The document contains 5 problems related to random number generation and testing. Problem 1 generates a sequence of random integers using the multiplicative congruential method. Problem 2 performs a Kolmogorov-Smirnov test to check if a sequence is uniformly distributed. Problem 3 analyzes periods of different linear congruential generators. Problem 4 generates sequences from a multiplicative congruential generator to check for maximum periods. Problem 5 performs a chi-square test to check for association between variables.

Uploaded by

Day-Veed Acharya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
663 views

Assignment 2

1. The document contains 5 problems related to random number generation and testing. Problem 1 generates a sequence of random integers using the multiplicative congruential method. Problem 2 performs a Kolmogorov-Smirnov test to check if a sequence is uniformly distributed. Problem 3 analyzes periods of different linear congruential generators. Problem 4 generates sequences from a multiplicative congruential generator to check for maximum periods. Problem 5 performs a chi-square test to check for association between variables.

Uploaded by

Day-Veed Acharya
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 4

David Acharya

Assignment 2

Problem 1
Use the multiplicative congruential method to generate a sequence of four three-digit random
integers and corresponding random numbers. Let X0 = 117, a = 43, and m = 1000

Given,
X0 = 117
a = 43
m= 1000

X1 = 43 x 117 mod 1000 31


X2= 43 x 31 mod 1000 333
X3 = 43 x 333 mod 1000 319
X4= 43 x 319 mod 1000 717
X5 = 43 x 717 mod 1000 831

Problem 2
The sequence of numbers 0.54, 0.73, 0.98, 0.11 and 0.68 has been generated. Use the
Kolmogorov-Smirnov test with α = 0.05 to learn whether the hypothesis that the numbers are
uniformly distributed on the interval [0, 1] can be rejected.

H0 = The observations are from Uniform Distribution (0,1)


H1 = The observations not from Uniform Distribution (0,1)
N = The number of numbers in the sequence given.

R(i) i /N i / N-R(i) R(i)-(i-1)/N

0.11 0.2 0.09 0.11

0.54 0.4 - 0.34

0.68 0.6 - 0.28

0.73 0.8 0.07 0.13

0.98 1.0 0.02 0.18


D+ = Max{ i/N- R(i)} = 0.09
D- = Max{ R(i)-(i-1)/N} = 0.34
D = Max {D+, D- } = 0.34 < 0.565
which is less than given D0.05 = 0.565
Hence H0 is not rejected.
David Acharya

Problem 3
Figure out whether these linear congruential generators can achieve a maximum period; also,
state restrictions on X0 to obtain this period.

a. The mixed congruential method with


a = 2, 814, 749, 767, 109
c = 59, 482, 661, 568, 307
m = 248

The mixed congruential method


(a = 749 , c = 661) and ( a = 109 , c= 307) can achieve the maximum period because in both the
cases c is relatively prime to m and m (a-1) is divisible by 4. That means (a-1) / 4 is an integer.
There is no restrictions on X0 to obtain this period.

b. The multiplicative congruential method with


a = 69, 069
c=0
m = 232

The maximum period can be achieved (a-5) is divisible by 8.


That is, (69069-5) / 8 is an integer.
In this case maximum period can be achieved because X0 must be an odd integer

c. The mixed congruential method with


a = 4951
c = 247
m = 256
The maximum period cannot be achieved because m= 256 = 28 and a= 4951 which is relatively
prime to m and a-1 is not divisible by 4, (4951-1) /4 is not an integer.

d. The multiplicative congruential method with


a = 6507
c=0
m = 1024
The maximum period can be achieved because (a-3) is divisible by 8.
That is, m =1024 = 210.
That is, (a-3) /8 = (6507-3) / 8 is an integer
David Acharya

Problem 4
Consider the multiplicative congruential generator under the following circumstances:
(a) X0 = 7, a = 11, m = 16

The multiplicative congruential generator,


Xn = aXn-1 mod m, n = 1,2,…..
Given X0 = 7
X1 = 11 x 7 mod 16 = 77 mod 16 = 13
X2 = 11 x 13 mod 16 = 143 mod 16 = 15
X3 = 11 x 15 mod 16 = 165 mod 16 = 5
X4 = 11 x 5 mod 16 = 55 mod 16 = 7
The cycle repeats and the length of the cycle is 4
The maximum period occurs when X0 is odd and a has the form 3+8k where k = 1, 2, 3,…..
In this case, the maximum period 4 occurs when X0 is odd and a = 3+8k where k =1
So, the maximum period 16 is not achieved

(b) X0 = 8, a = 11, m = 16
The multiplicative congruential generator,
Xn = aXn-1 mod m, n = 1,2,…..
Given X0 = 8
X1 = 11 x 8 mod 16 = 88 mod 16 = 8
The cycle repeats and the length of the cycle is 1
The maximum period 16 is not achieve because X0 is even

(c) X0 = 7, a = 7, m = 16
The multiplicative congruential generator,
Xn = aXn-1 mod m, n = 1,2,…..
Given X0 = 7
X1 = 7 x 7 mod 16 = 49 mod 16 = 1
X2 = 1x7 mod 16 = 7 mod 16 = 7
The cycle repeats and the length of the cycle is 2
The maximum period 16 is not achieve because X0 do not have the form of 3 + 8k.

(d) X0 = 8, a = 7, m = 16
The multiplicative congruential generator,
Xn = aXn-1 mod m, n = 1,2,…..
Given X0 = 8
X1 = 8 x 7 mod 16 = 56 mod 16 = 8
The cycle repeats and the length of the cycle is 1
The maximum period 16 is not achieve because X0 is even.
David Acharya

Problem 5

CHI-SQUARE TEST
Value Df Asymptotic Significance (2-
Sided)
Pearson Chi- 306.00 289 0.235
square
Likelihood 104.053 289 1.000
ratio
Linear -by- 1.541 1 .215
Liner
Association
N of valid 18
cases

324 cells have expected count less than 5 (100%)


The minimum expected count is 6

Null Hypothesis: No association between 2 variables


Alternative Hypothesis: Association exists between 2 variables
p value is not < 0.05, fail to reject null hypothesis

You might also like