0% found this document useful (0 votes)
10 views21 pages

Markov Chains and Monte Carlo Simulations

The document discusses various concepts related to Markov chains, simulation models, and statistical analysis. It includes questions and answers about transition probability matrices, Monte Carlo simulations, and hypothesis testing. The content emphasizes the importance of modeling and simulation in understanding real-world processes and making informed decisions.

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)
10 views21 pages

Markov Chains and Monte Carlo Simulations

The document discusses various concepts related to Markov chains, simulation models, and statistical analysis. It includes questions and answers about transition probability matrices, Monte Carlo simulations, and hypothesis testing. The content emphasizes the importance of modeling and simulation in understanding real-world processes and making informed decisions.

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

Suppose that a man's profession can be classified as professional,

qualified worker or unqualified worker. Suppose that, of the children of


professionals, 80% are professionals, 10% are skilled workers and 10%
they are unskilled workers. In the case of children of workers
qualified, 60% are skilled workers, 20% are professionals, and 20% are not
qualified. Finally, in the case of unqualified workers, 50% of the children
they are unskilled workers, and 25% each are in the other two categories.
Suppose that every man has at least one son and forms a Markov chain.
following the profession of a randomly chosen son from a given
family for several generations. Set up the transition probability matrix.
Find the probability that a randomly chosen grandchild is a model of simulation MONTE.
randomly from an unskilled worker to a professional.

0.430
0.165
0.685
0.330
0.375
Answered on 04/16/2023 10:26:26

Explanation:

2a
Score:1.0/1.0
Question

A rat runs through the maze shown below. With each step, it leaves the room in which
is randomly choosing one of the doors to leave the room.

What is the transition matrix P for this Markov chain?


Answered on 04/16/2023 10:28:53

Explanation:

3a
Correct: 1.0/1.0
Question

A simulation model is a mathematical business model that combines


mathematical and logical concepts that attempt to emulate a real-life system through
use of computer software. To verify a simulation model:
Compare results of various simulation languages
Run the model for long enough to surpass the initial results.
of initialization
Confirm that the model accurately represents the real system
Make sure that the procedures for calculations are logically
correct
Compare the representation of a conceptual model with the real system
Answered on 04/16/2023 10:30:48

Explanation:

Comments:
Verification is the process of comparing two or more results to ensure their accuracy.
In this process, we have to compare the implementation of the model and its associated data.
with the conceptual description and specifications of the developer, confirming if the same
represents the real system with good accuracy.

4a
Score:1.0/1.0
Question

Probabilistic simulation is the process of explicitly representing this uncertainty.


specifying inputs as probability distributions and specifying
any random events that may affect the system Values for the inputs
probabilities of a simulation:
Use only historical sources
They are generated randomly based on historical information
They are controlled by the decision-maker
They are calculated by fixed mathematical formulas.
They are selected by the decision maker.
Answered on 04/16/2023 10:31:53

Explanation:

Comentários

Probabilistic inputs are the inputs that are chosen randomly. They are
used in quantitative approaches when trying to make a decision

5a
Score:1.0/1.0
Question

Many times we need to apply techniques for better understanding of processes.


What is the process of representing a model that includes its construction and
functioning of a process.
Modeling.
Modeling and Simulation.
Process engineering.
Production scheduling.
Simulation.
Responded on 04/16/2023 10:32:14

Explanation:
Modeling is the process of representing a model that includes its construction and
operation, with the aim of collecting information for the process analysis.

6a
Score: 1.0/1.0
Question

Consider the following statements regarding the feedback of systems


control of a modeling.

I. Feedback can improve stability or be detrimental to stability if not


for applied correctly.

II. Feedback can always improve stability

III. In many situations, feedback can reduce the effect of noise and disturbance
in the system's performance.

IV. In general, the sensitivity of the system gain of a feedback system


The variation of a parameter depends on where the parameter is located.

Is what is stated correct in:


I, II, and III only.
II and IV only.
I, II, and IV only.
I, III, and IV only.
I, II, III, and IV.
Responded on 04/16/2023 10:32:20

Explanation:

Negative feedback increases stability, but positive feedback does not reduce it.
stability and, for this reason, negative feedback systems are used.

7a
Score: 0.0 / 1.0
Question

A hypothesis test is used to determine a test statistic for


statements. The p-value obtained from a classic hypothesis test is:
the probability that the null hypothesis is false, given the data
the probability of observing the data or more extreme values if the
alternative hypothesis is true
the probability of observing the data or more extreme values if the
null hypothesis is true
the probability that the null hypothesis is true, given the data
the highest significant level at which the null hypothesis can be rejected
Responded on 04/16/2023 10:34:23
Explanation:

The alternative hypothesis is a statement used in statistical inference experiments. It is


contradictory to the null hypothesis and denoted by Ha or H1. We can also say that it is
simply an alternative to the null. In hypothesis testing, an alternative theory is a
statement that a researcher is testing. This statement is true from the point of view
of the researcher and, ultimately, proves to reject the null to replace it with an assumption
alternative. In this hypothesis, the difference between two or more variables is predicted by
Researchers, so that the pattern of the data observed in the test is not due to chance.

8a
Score: 1.0/1.0
Question

The average life of a sample of 100 lamps brand 'A' is 1615 hours.
similarity with other manufacturing processes, we assume the standard deviation equal to
120 hours. Using a significance level of 5%, we wanted to test whether the life
Is the average of all the lamps of this brand equal to or different from 1600 hours? What is it?
the conclusion?
that the average lifespan of the bulbs of this brand is less than 1600
that the average lifespan of the bulbs of this brand is less than 1480
the average lifespan of the bulbs of this brand is equal to 1480
the average lifespan of the bulbs of this brand is equal to 1600
that the average lifespan of bulbs from this brand is greater than 1600
Answered on 04/16/2023 10:35:35

Explanation:

Test statistics: Z = 1.25 (table)

Critical region: Rc-1.96 < Z < 1.96

Conclusion: According to the collected data, at a significance level of 5%. We conclude


that the average lifespan of the bulbs of this brand is equal to 1600.

9a
Score: 1.0/1.0
Question

The standard normal distribution is a normal distribution with a mean of zero and a standard deviation of one.
standard of 1. The standard normal distribution is centered at zero and the degree to which a
The extent to which a certain measure deviates from the mean is given by the standard deviation. For the

standard normal distribution, the area to the left of the mean is:
> 0.5
0.5
1
2.5
-0.5
Responded on 04/16/2023 10:37:06

Explanation:
In a normal distribution with parameters μ=0 and σ=1. Note that it is symmetrical, therefore,
it is the same size on the right and the left, therefore it will be equal to 0.5.

10a
Score: 1.0/1.0
Question

A Monte Carlo simulation takes the variable that has uncertainty and assigns it a
random value. The model is then executed and a result is provided. This
the process is repeated several times when assigning many different values to the variable
question. After the simulation is completed, the results are calculated for
to arrive at an estimate. Therefore, when using Monte Carlo simulation:
the values of the variables generated by the simulation must approximate the
values of real-world variables.
the values of the variables generated by the simulation must be exactly
equal to the values of real-world variables.
the averages of the variables generated by the simulation must be
systematically lower than the averages of real-world variables.
the averages of the variables generated by the simulation should be slightly
higher than the averages of real world variables.
the average values of the variables generated by the simulation should be
approaching the averages of real world variables.
Answered on 04/16/2023 10:38:23

Explanation:

When we are simulating variables, we are artificially injecting an error, however the
the average of the randomly generated values must necessarily approach the value
real.

Consider the Markov chain with transition matrix:

The process starts in state 1; find the probability that it is in


state 3 after two stages.
1/8
1/4
1/12
1/6
1/2
Responded on 04/16/2023 10:39:54

Explanation:
2a
Score:1.0/1.0
Question

Consider the Markov chain with transition matrix

The process starts in state 1. Find the matrix that is the limit of Pn as n approaches infinity.
→ ∞.
1/6,3/6 e 2/6
3/6,2/6 e 1/6
1/6, 2/6 and 3/6
2/6,3/6 e 1/6
3/6, 1/6 and 2/6
Answered on 04/16/2023 10:40:17

Explanation:
3a Correction: 0.0/1.0
Question

Mathematical modeling is the process of describing a real-world problem


in mathematical terms, usually in the form of equations, and then use these
equations to help understand the original problem and to discover new ones
resources about the problem. In the mathematical modeling of a process, what
Is option not a characteristic of a numerical solution method?
It can be applied to any type of process
A set of assumptions is made about the process.
The finite element method is used
Applicable only to simple problems
Does not provide exact information about the quantities of interest
Answered on 04/16/2023 10:44:06
Explanation:

Explanation:
In the development of a mathematical model, we often make a set of
assumptions about the process (for example, constitutive behavior, loads and conditions
contour) to derive the mathematical relationships that govern the system. A method
numeric, for example, the finite element method, provides an approximate solution
for a specific problem. Most practical problems are solved using the
numerical solution method.

4a
Score: 0.0/1.0
Question

Analyze the following statements.

I. Simulation is a way to reproduce the behavior of a system using


a model that describes its processes. Simulation models consist of
specify the mathematical relationships between decision variables, variables
uncontrollable and independent variables.
II. Simulation is a tool that should only be used when the situation
involves, at most, ten decision variables and the system has no constraints
non-linear operational.
III. It is important to simulate a process long enough to reach a state
stationary, so that the results obtained represent the actual values of
system. A limitation of the tool is the need for advanced software,
even to simulate simple systems, with one or two uncontrollable variables.
IV. The compression of time, one of the characteristics of simulation, is the ability
to obtain estimates of the operational characteristics in a much shorter time than
that the time required to collect the same data in a real system.

Select the option in which all statements are CORRECT:


II, IV
I, III
II, III
I
I, IV
Answered on 04/16/2023 10:41:48

Explanation:

Explanation:
A simulation imitates the operation of real-world processes or systems using
models. The model represents the main behaviors and characteristics of the process
the selected system, while the simulation represents how the model evolves under
different conditions over time. The simulations are generally based on
computer, using a model generated by software to provide support for decisions of
managers and engineers, as well as for training purposes. The simulation techniques
they aid in understanding and experimentation, as the models are visual and interactive

5a
Score:1.0/1.0
Question
The design model is evaluated by the software team for
determine___________; and those that were established. The alternative that
correctly complete the above excerpt is:
Errors, inconsistencies, or omissions.
Existence of alternatives.
Implementation of the model within the constraints, schedule, and cost.
B and C only.
A and B only.
Responded on 04/16/2023 10:42:00

Explanation:

The software team evaluates the project model to identify any flaws, inconsistencies
or omissions; whether there are alternatives; and whether the model can be implemented within the
restrictions, schedule, and budget that were specified.

6a
Score:1.0/1.0
Question

Analysis of a system is the operation of a model in terms of time or


space, which helps to analyze the performance of an existing or proposed system.
The description is related to:
Modeling.
Control Systems.
Layout.
Analysis of the process.
Simulation.
Answered on 04/16/2023 10:42:14

Explanation:

The simulation of a system is the operation of a model in terms of time or space.


that helps analyze the performance of an existing or proposed system.

7a
Score:1.0/1.0
Question

Statistics is the science that is concerned with developing and studying methods to
collect, analyze, interpret and present empirical data. Which of the following
Which statements best describe the relationship between a parameter and a statistic?

A parameter is used to estimate a statistic.


A parameter has a sampling distribution with the statistic as
variance.
A parameter has a sampling distribution that can be used.
to determine which values the statistic is likely to have in samples
repeated.
A statistic is used to estimate a parameter.
A parameter has a sampling distribution with the statistic as the mean.
Answered on 04/16/2023 10:45:14

Explanation:

The objective of quantitative research is to understand the characteristics of populations.


finding parameters. In practice, it is often very difficult, time-consuming, or unfeasible
collect data from all members of a population. Instead, the data is
collected from samples.

8a
Score:0.0/1.0
Question

The association of metalworking industry owners is very concerned.


with the time lost due to workplace accidents, the average, in recent times,
It has been around 60 man-hours per year with a standard deviation of 20.
man-hours. A program for accident prevention was attempted, after which it was
A sample of nine industries was taken and the number of man-hours measured.
lost due to accidents, which was 50 hours. Would you say, at the 5% level, that there is
evidence of improvement? Source: Morettin & Bussab, Basic Statistics 5th edition,
p. 334.
We therefore refuse, as there was no improvement.

We accept, for there was no improvement


We accepted it because there was an improvement.

With the presented data, analysis is impossible


Therefore, we rejected it, as there was improvement.

Answered on 04/16/2023 10:46:53

Explanation:

We want to test the hypothesis that µ, the average number of hours lost due to accidents
work has remained the same.

9a
Score: 1.0/1.0
Question

A Monte Carlo simulation is used to model the probability of different


results in a process that cannot be easily predicted due to the
intervention of random variables. It is a technique used to understand the impact
of risk and uncertainty. A Monte Carlo simulation is used to solve a
series of problems in many fields, including investments, business, physics and
engineering. The important step needed for the simulation approach
Monte Carlo in solving a problem is.

I. Validate the model


II. Design the experiment
III. Perform the experiment

Is what is stated correct:


Only II
Just III
Only I and II
Only II and III
Just I
Answered on 04/16/2023 10:47:09

Explanation:

The important step required for the simulation approach in solving a


the problem is to test and validate the model, design the experiment and conduct the experiment.

10a
Score: 0.0/1.0
Question

Discrete event simulation is a method used to model systems of


real world that can be decomposed into a set of processes
logically separate that progress autonomously over time. Each
event occurs in a specific process and receives a logical hour. The result
this event can be a past result for one or more other processes.
If one event occurs, another event cannot happen, that is, the events that
cannot occur simultaneously are called:
Exhaustive Events
Equally likely events
Independent events
Random events
Mutually exclusive events
Responded on 04/16/2023 10:47:20

Explanation:

Mutually exclusive events are things that cannot happen at the same time.
1. The association of metalworking industry owners is very concerned about the
lost time due to workplace accidents, which has averaged in recent times to
order of 60 hours/man per year and standard deviation of 20 hours/man. An attempt was made to a
accident prevention program, after which a sample of nine was taken
Industries and the number of man-hours lost due to accidents was measured, which amounted to 50 hours.
Would you say, at a 5% level, that there is evidence of improvement? Source: Morettin & Bussab,
Basic Statistics 5th edition, p. 334.

We accept it, as there was no improvement.

With the data presented, analysis is impossible.

We reject it, as there was no improvement

We accept, for there has been improvement.

We rejected it, as there was an improvement.

Data Resp.: 03/22/2023 11:51:08

Explanation:

We want to test the hypothesis that µ, the average number of hours lost due to accidents
work, has remained the same.

2. The average life of a sample of 100 bulbs brand 'A'


It is 1615 hours. By similarity to other processes of
manufacturing, we assume the standard deviation is equal to 120 hours.
Using a significance level of 5%, we wanted to test
if the average life of all the bulbs of this brand is equal
or different from 1600 hours. What is the conclusion?

that the average lifespan of the bulbs of this brand is shorter than 1600

that the average lifespan of the bulbs of this brand is less than 1480

that the average lifespan of the bulbs of this brand is equal to 1600
that the average lifespan of the bulbs of this brand is greater than 1600

the average lifespan of the bulbs of this brand is equal to 1480


Response Date: 22/03/2023 11:52:04

Explanation:

Test statistics: Z = 1.25 (table)

Critical region: Rc =-1.96 < Z < 1.96

Conclusion: According to the data collected, at a significance level of 5%. We conclude


the average lifespan of lamps of this brand is equal to 1600.

Stochastic Processes 4495

3. An auto insurance company classifies its clients into


three categories: bad, satisfactory, and preferred. No one
change from bad to preferred or from preferred to bad in
one year. 40% of customers in the poor category become
satisfactory, 30% of those in the satisfactory category
they move to the preferential ones, while 10% remain bad;
20% of those in the preferred category are demoted.
for satisfactory. What is the limiting fraction of drivers
in each of these categories?

Data Resp.: 03/22/2023 11:52:13

Explanation:
4. Consider the Markov chain with transition matrix

The graph that represents this chain is:


Data Resp.: 31/03/2023 11:14:51

Explanation:
4496FUNDAMENTALS OF SIMULATION

5. Mathematical models are classified according to


the type of equation used in its formulation. The models
in which the output signal can be calculated accurately,
as soon as the input signal and the initial conditions are
known, are classified as:

Stochastic

Heuristic

Phenomenological

Transubstantial

Deterministic
Data Resp.: 31/03/2023 11:16:57

Explanation:

Resolution
Models can be static or dynamic. Within dynamics, they can be
deterministic (there are no random variables) or stochastic (there are random variables)
random). They can also be: discrete (discrete events require attention) or
continuous (full-time observation). The heuristics, phenomenological and
transubstantials do not exist or do not fit the test. As mentioned in
"precision", can be determined
The simulation can be defined as the technique that
represents the functioning of a real system. To do this,
a model must be developed that expresses
mathematically the operating conditions of the system and
the relationships between its components. In relation to
main characteristics of systems and their models of
simulation, consider the statements below.

I. A system can be understood as a set of


entities that act and interact to achieve a goal
logical.
II. A dynamic system must be represented only by
continuous random variables.
III. A deterministic simulation model is one that
that the variables are discrete random variables.

Is what is stated in:

I and II

II and III

III

I, II and III
Data Resp.: 31/03/2023 11:18:19

Explanation:

Resolution
Every system is made up of input, processing (interaction), output. I) correct. II) No
it necessarily has to be continuous random variables. III) In theory, there doesn't even exist
a random variable in deterministic simulation.

4497 CONCEPTUAL MODEL

7. Observe the statements below:

I. The complexity of the arbitrary simulation model,


circumvents analytically intractable models, facilitates
hypothetical and sensitivity analyses, the construction of a
model can lead to system improvements and a greater
understanding can be used to verify solutions
analytics.

MEANWHILE

II. The simulation provides only solution estimates,


resolve only one parameter at a time, it may take a long time
development time and/or computer (simulation
as a last resort?). Do not use computer simulation
if an analytical or common sense solution is
available, or if the resources are insufficient or if the
costs of the simulation outweigh the benefits.

Present the correct answer:

Statement I is correct, but II is wrong.

Both are correct and II complements I.

Both are correct and II does not complement I.

Both statements are wrong.

Statement I is wrong, but II is correct.


Data Resp.: 31/03/2023 11:18:50

Explanation:

Both are correct where I is an advantage of using simulation and II presents a


disadvantage.

8. CAD project and computer-aided drawing (CAD is


a technology for project), documentation or technique
that replaces manual drawing with a process
automated. Computer-Aided Manufacturing (CAM)
is related to the use of controlled machines
by computers. Therefore, based on the stated,
project modeling and manufacturing using CAD/CAM
they mean:

Finished products and production executions of products.

Mass production in fashion companies.

Prototype and finished products.

Production cycles of products, finished products, and prototypes.

Software and hardware tools.


Data Resp.: 31/03/2023 11:18:54

Explanation:

The computer-aided design and computer-aided manufacturing software


(CAD/CAM) is used to design and manufacture prototypes, finished products, and cycles of
production of products.

4499 SIMULATION AND OPTIMIZATION

9. The standard normal distribution, also called


Z distribution is a special normal distribution in which the
the mean is 0 and the standard deviation is 1. Any distribution
normal can be standardized by converting its values into
Z scores indicate how many standard deviations
the average where each value is located. The formula to calculate the
standard normal random variable is:

x-sigma/mu

μ-x/σ

μ - σ/x

x - μ/σ

σ-x/μ
Data Resp.: 31/03/2023 11:18:58

Explanation:

To standardize a value from a normal distribution, convert the individual value into a z-
score

Subtract the average from your individual value.


Divide the difference by the standard deviation.

10. Parameters are numbers that describe the properties


of entire populations. Statistics are numbers that
they describe the properties of the samples. For example, the
the average income of Brazil is a population parameter.
on the other hand, the average income of a sample taken from
Brazil is a sample statistic. Both values
they represent the average income, but one is a parameter
versus a statistic. Which of the following statements
better describes the relationship between a parameter and a
statistics?

A statistic is used to estimate a parameter.

A parameter has a sampling distribution with the standard deviation as the mean.

A parameter is used to estimate a statistic.

A parameter has a sampling distribution with the statistic as the mean.


A parameter has a sampling distribution that can be used to
determine which values the statistic is likely to have in repeated samples.
Data Resp.: 31/03/2023 11:19:06

Explanation:

The difference between a parameter and a statistic is that a parameter is a fixed measure that
describes the entire population, while a statistic is a characteristic of a sample,
a portion of the target population. A parameter is a fixed and unknown numerical value,
while the statistic is a known number and a variable that depends on the portion of the
population.

You might also like