0% found this document useful (0 votes)
7 views16 pages

Combinatorial and Statistical Analysis Techniques

This document presents 8 topics related to statistics. In the first topic, the number of ways to distribute 16 students into 3 teams of different sizes is calculated. In the second topic, the average distance that a rat will travel in a maze is calculated. In the third topic, the probability that exactly 4 students will repeat a course is calculated. The remaining topics include normal distribution models, confidence intervals, sample sizes, and hypothesis tests.

Translated by

ScribdTranslations
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
0% found this document useful (0 votes)
7 views16 pages

Combinatorial and Statistical Analysis Techniques

This document presents 8 topics related to statistics. In the first topic, the number of ways to distribute 16 students into 3 teams of different sizes is calculated. In the second topic, the average distance that a rat will travel in a maze is calculated. In the third topic, the probability that exactly 4 students will repeat a course is calculated. The remaining topics include normal distribution models, confidence intervals, sample sizes, and hypothesis tests.

Translated by

ScribdTranslations
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

1st Topic: Combinations

Problem formulation

A school group consists of 16 students. It is necessary to form simultaneously


3 teams with them, one of 5 students to go to the Red Cross, another of 3 students
to visit the hospital and the third of 2 students to go to the bank. How many
How can they be distributed?

Approach

The first team of 5 students can be selected from among the 16 available.
the school group; once that first team is formed, only 11 remain
students from which the second team must be formed with three from
they; once that second team is formed, only 8 students remain from
among which the third team must be integrated with two of them.

Solution

So that

16C5×11C3× 8C2
16! 11! 8!
x x
5 ! (16−5)!3! (11−3) !8! (8−2) !

= 4368 ×165 × 28
= 20 180 160

Interpretation of results:

It can be distributed in 20,180,160 ways to form the teams.

2nd Topic: Random Variable

Problem formulation

At the starting point of a labyrinth, there are three identical openings A, B, and C. If the
rat chooses
A returns to the starting point after traveling two meters. If he chooses B, he travels
five meters and returns to the same point. If he chooses C, he goes outside traveling a
metro. On average, how far does a rat travel before it leaves, if
Always choose a different hole from those selected in previous times?
Approach

The routes that can be taken with the distances traveled in each
case, they are (A, B, C) 8, (B, A, C) 8, (A, C) 3, (B, C) 6, (C) 1.

Solution:

Their chances would be:

P (A, B, C) = P (A) · P (B/A) · P(C/A∩B) = 1/3 · 1/2 · 1 = 1/6


P (B, A, C) = P (B) · P (A/B) · P(C/B∩A) = 1/3 · 1/2 · 1 = 1/6
P (A, C) = P (A) · P (C/A) = 1/3 · 1/2 = 1/6
P (B, C) = P (B) · P(C/B) = 1/3 · 1/2 = 1/6
P(C) = 1/3

As a result, the average distance traveled will be:


E[D] = 8 · 1/3 + 6 · 1/6 + 3 · 1/6 + 1 · 1/3 = 4.5

Interpretation of results:

The distance that it will at least cover before exiting will be 4.50 meters.

3rd Topic: Binomial Distribution Model

Problem formulation

The probability that an undergraduate student repeats the statistics course is


from 0.3. We choose 20 students at random. What is the probability that there is
exactly 4 students repeating the course?

Approach

It is a binomial distribution, the student either repeats or passes the course.


We consider it a successful event when they ask us.

The student repeats the course P(A) = p = 0.3


The student does not repeat the course Ā
P 1 - p = q = 1 - 0.3 = 0.7

We selected 20 students n= 20

It is a binomial distribution with parameters n= 20, p = 0.3

B (n, p) ---------B (20; 0.3)


The probability of there being exactly 4 repeating students x = 4

Solution:

P ( x=k )=
(k) .p . q
k n−k
k = 4; n = 20; p =0,3;q = 0,5

0.7
¿
¿
P ( x=4 )=
( )
20
4
.(0.3)4. ¿

n! 20!
(nk)= k (n−k
! )! Combinatorial numbers (204 )= 4 ! (20−4)! 4845

0.7
¿ 0.7
¿ ¿
P (x= 4) = 4845. ¿ = 0, 13
4( )
P ( x=4 )= 20 .(0.3)4. ¿ (0.3)4. ¿

Interpretation of results:

The probability of having exactly 4 students repeat the course is 0,


13

4°Topic: Normal Distribution Model

Problem formulation

In a city, it is estimated that the maximum temperature in the month of April follows
a normal distribution, with a mean of 23° and a standard deviation of 5°. Calculate the
number of days in the month when maximums between 21° and
27°

Approach

x−µ
We know that Z=
σ
Like x1= 21 and x2= 27 then the P(x1≤ X ≤ x2)
23°

Solution:

21−23 27−23
P (21 ≤ X ≤ 27) = P ( 5 Less than or equal to Z less
5 ) than or equal to

−2 4
P (21 ≤ X ≤ 27) = P ( 5 ≤Z≤ 5 ( ) = P (- 0.4 ≤ Z ≤ 0.8)

= P (- 0.4 ≤ Z ≤ 0.8) = P (Z ≤ 0.8) – [1 - P (Z ≤ 0.4)]

P (Z ≤ 0.8) + P (Z ≤ 0.4) – 1 = 0.7881 + 0.6554 -1 = 0.4435

0.4435 * 30 days = 13.3 days

Interpretation of results:

The number of days in the month of April in which temperatures are expected to reach
maximums between 21° and 27° is 13 days.

5th Topic: Sampling distributions of difference


proportions

Problem formulation

It is known that 3 out of every 6 products manufactured by machine 1 are


defective and that 2 out of every 5 objects manufactured by machine 2 are
defective; samples of 120 objects are taken from each machine:

Data:

3
P1= 6 = 0.5 y 1 = 120 objects

2
P2= 5 = 0.4 y 2 = 120 objects

Approach
a. What is the probability that the proportion of defective items of
Does machine 2 outperform machine 1 by at least 0.10?

P (p21≥ 0.10)

Solution:

( p 2 − p 1 )−(P2−P1) 0.0958−(−0.10)
Z= = =3.06

√ P1.q1P2.q2
n1
+
n2 √ (0.50) .(0.50) (0.40).(0.60)
120
+
120

0.10− ( 120
0.5
)=0.0958

Z= 3.06 ------ P (Z= 3.06) = 0.0011

Interpretation of results:

The probability that there is a difference in proportions of items.


defective at least 10% in favor of machine 2 is 0.0011.

Approach

b. What is the probability that the proportion of defective items of


Does machine 1 outscore machine 2 by at least 0.15?

P (p12≥ 0.15)

Solution:

( p 1 − p 2 )−(P1−P2) 0.1458−0.10
Z= = =0.72

√ P1.q1P2.q2
n1
+
n2 √ (0.50) .(0.50) (0.40).(0.60)
120
+
120
0.15− ( 120
0.5
)=0.1458

Z= 0.72 ----- P (Z= 0.72) = 0.2357

Interpretation of results:

The probability that there is a difference in the proportions of items


defective at least 15% in favor of machine 1 is 0.2357.

6th Topic: Confidence Interval for the Difference of Means

Problem formulation

An experiment was conducted to compare the average time required by the


human body to absorb two medications, A and B. Suppose that the
time required for each medication to reach a specific level in
blood flow is normally distributed. Twelve were randomly chosen.
people to test each drug by recording the time in minutes that
it took to reach a specific level in the blood. Calculate an interval of
95% confidence for the difference in average time. Assume variances
equal.

Medication A Medication B

A 12 B = 12

X́ A =26.8 X́ B = 32.6
SA=2 15.57 SB2= 17.54

Solution:

s p=
√ ( A S) 2n−1
S 2Ain−1+ B(

n A +n B−2
B )
=
√ 15.57 ( 12−1 )+17.54 (12−1 )
12+12−2

s p=4.07

µ B - µ A=¿ ( X́ B - X́ A )± p
√ 1 1
+
n A nB

µ B - µ A=¿ (32.6 – 26.8) ± (2.074) · (4.07).


√ 1 1
+
12 12

2.35 ≤ µB - µ A≤ 9.25

Interpretation of results:

With a 95% confidence level, it is known that the average time to reach
A specific level is higher for medication B.

7th Topic: Sample size when variance is unknown


population

Problem formulation

The following data are the weights in grams of 16 bags of a certain material
plastic that is selected in a depot for the purpose of verifying the weight
promedio: 506, 508, 499, 503, 504, 510, 497, 512, 514, 505, 493, 496, 506,
502, 509, 496.
a) If the weight of each bag is a normal random variable with a standard deviation of 5
grams, obtain the confidence intervals at 90, 95, and 99% for the mean of the
weight of the bags.

b) Determine the sample size, n, necessary for the length of


interval, with α = 0.05, is less than or equal to one unit.

Approach

Let the random variable X = "weight in grams", X has a distribution N (µ, 5.2).

a) Considering that:
n = 16 X́ = 503,76 y σ = 5

Substituting these values into the expression of the interval for the mean of a
normal population
with known, we obtain:

1-alpha zα interval
2

0.90 1.64 [501,7;


505.8
0.95 1.96 [501,3;
506.2
0.99 2.58 Invalid input format
506.9

b) The sample size required for the length of the interval (L) to be
less than or equal to
the unit, with a level α= 0.05, is:

1.96¿2.5 2
4Zα2 /2.σ 2 ¿
n≥ ==384.16
L2 4¿
¿

otsaiyt,I n≥385

Yes, for the data from the previous example, if it were unknown:
Obtain the confidence intervals at 90%, 95%, and 99% for the mean weight of
the bags
(Assuming that the population is normal)

b) Determine the sample size, n, necessary for the length of the


interval, with α =
0.05, is less than or equal to one unit.

Approach

a) Given that is unknown, replacing its value with S = 6.2022 and


using the distribution with 15 degrees of freedom instead of the distribution
standard normal, the new intervals presented in the following are obtained
table

1-alpha tα interval
2

0.90 1.753 [501.03;


506.47
0.95 2.131 [500,45;
507.05
0.99 2.947 [499.18;
508.32

b) The resulting sample size in this case, taking as an estimation of


the value calculated with the given sample and replacing t15, α /2 with Z α /2 is:

1.96¿2June 6, 2022 2
4Z2α /2. S 2 ¿
n≥ = =591.103
L2 4¿
¿

Therefore, n≥592

Interpretation of results:

Note that in this case a much larger sample size is needed.


than that obtained in the previous statement

8° Topic: Hypothesis testing for qualitative variables

Framing of the problem


The company ENTEL wants to compare the daily transportation expenses of the equipment.
of sales and collection staff. Collected the following information
sample (amount in dollars).

Sales ($) 131 135 146 165 136 142

Cobranza ($) 130 102 129 143 149 120 139

At the significance level of 0.10, it can be concluded that the average expenses
Are the sales team diaries greater? What is the p-value?

Approach

SALES Collections
131 130
135 102
146 129
165 143 Test of
136 149 hypothesis
142 120
139
a) This is a one-tailed test
H0u1<= u2
142.5 130.28 average
hsediabltesbelw
leiulronisdecihet
Deviation
12.24 15.78
n st htIfceivtarilaulresiachehdten,hulypohtew
siblerijcetd
Number ieseaceptaH1
n=6 n=7
of data
detaulclacsicitsitats tsethet ofuelvahet )c

Data:

n=6
1 n=7
2

Prom=.1425. 1 Prom=.1303. 2

12.2
1 S=15.8
2

α=0.10 t( 0.10)=1.363

Gradosdelibertad=6+7–2=11
Solution:

( 1 ) 2n −1
S12n−1+S 2( 2 )
S 2=
n1+ n2−2

148.84 ( 6−1 )+249.64 ( 7−1 ) 744.2+1497.84


S 2p= =
6+7−2 11

S 2p=203.82

1 1
+
n1n2
1 1
+
6 7
12.2
√ 203.82(¿)= 7.819
√ S ( ¿)= 142.5−130.3
2
σ ¿
´ 1− X
X ´2
t= ¿

t=1.56

d) The decision regarding the null hypothesis


t calculated at 1.56 is greater than 1.363, the null hypothesis is rejected

1.363

Interpretation of results:

Therefore, the null hypothesis is rejected, and it is concluded that the average daily expenses of sales
the completed ones are greater.

9° Topic: Two-way analysis of variance


Problem formulation

Research is being conducted on the effect of three types of fertilizers on two types of
soil. It is expected that the effect of the different fertilizers will manifest in a way
different depending on the type of soil. For the present study we will take
two types of soil, acidic and alkaline, and three types of fertilizer that we will denote with
A, B, and C. We thus have two factors (soil and fertilizer) with 2 and 3 levels.
Respectively, resulting in 6 combinations. We will take a design.
factorial with two factors and three replicas in each of the combinations of
the levels of the two factors.

Approach

The hypotheses that the different factors have no effect and that
there is no interaction; they are contrasted through two-way analysis of variance
ways with interaction, comparing the variability between the levels of factor A,
the variability between the levels of factor B, C, and the variability due to the
interaction with variability within groups or residual.

A B C
8 10 8
Acid 4 8 6
0 6 4
14 4 15
Alkaline 10 2 12
o 6 0 9

Sum of Average of
squares squares
SOIL 1 18,000 18,000
Fertilizer 2 48,000 24,000
SOIL*FERTILIZER 2 144,000 72,000
O
RESIDUAL 12 106,000 8, 833

SOIL *Fertilizer

Quantity media Deviation [Link]


d in standard
ACID, A 3 4,000 4,000 2,309
ACID, B 3 8,000 2,000 1,155
ACID, C 3 6,000 2,000 1,155
ALKALINE, A 3 10,000 4,000 2,309
ALKALINE,B 3 2,000 2,000 1,155
ALCALINO,C 3 12,000 3,000 1,732
Interpretation of results:

The answer is an index of


abundance of a certain
species after the application of the
different subscriptions.

10° Topic: Regression and Correlation

Problem formulation

A shopping center knows based on the distance, in kilometers, at which


located in a population center, customers come in hundreds, that
they are listed in the table:

Number of Distance
Clients (X) hi (Y)
8 15
7 19
6 25
4 23
2 34
1 40

Calculate the linear correlation coefficient.

If the shopping center is located 2 km away, how many customers can it have?
wait?
If you want to receive 500 clients, how far from the core of ...
Should the population be positioned?
Approach

xi yi x I·yi xi2 yi2

8 15 120 64 225

7 19 133 49 361

6 25 150 36 625

4 23 92 16 529

2 34 68 4 1156

1 40 40 1 1600

28 156 603 170 4496

Solution:

28 156
X́ = 4.67 Ý = =
6 6

26
170
σ 2X = −4.672=6.53 σ Y2 =
6
4496
−26 2=73.33
6

σ X = √ 6.53=2.55 σ Y= √ 73.33=8.56

σ 603
XY= −4.677=−20.92
6

−20.92
r= =−0.96
2.55∗8.56

Very strong negative correlation, shows absolute inverse dependence.

−20.92(
x−4.67= y−26 ) x=−0.29y+12.09
73.33

x=−0.29∗2+12.09=1151 clients

−20.92(
y−26= x−4.67 ) y=−3.2x+40.96
6.53

y=−3.2∗5+ 40.96=24.96 km

Interpretation of results:

It is demonstrated that the distance with the number of clients keeps a


inverse relationship: the shorter the distance, the greater the number of customers that
They are expected to arrive at the mall.

You might also like