Questions tagged [monte-carlo]
Questions on Monte Carlo methods, methods that require the repeated generation of pseudo- or quasi-random numbers for computing their results.
0
votes
0answers
12 views
Can we use the control variate Monte Carlo variance reduction approach to estimate variance?
The control variate technique is a super useful was of fusing low- and high-fidelity models to reduce the variance in an estimate of an expected value. Consider an expensive, high-fidelity model $f(x)$...
0
votes
0answers
22 views
How to do Monte Carlo Method for exceedingly large numbers?
For a paper I'm writing for my math class, I need to do several Monte Carlo simulations for a game I'm playing. The $p=0.6190411273$, a normal number... but the $n=2.14974(10^{10})$. I've tried to run ...
0
votes
0answers
10 views
Unbiased Metropolis within Gibbs Sampler MCMC
I am currently using MCMC to estimate the inner cells of a contingency table. The date comes from a simulation I conducted and thus I know the true values of the inner cells. However, I have the ...
1
vote
0answers
11 views
Intuition behind convergence of MCMC inference methods
I'm studying Gibbs Sampling for inference, a popular MCMC algorithm and I was stunned by its ability to fit a Gaussian Mixture just by sampling.
I would like to know the intuition behind it, and why ...
0
votes
0answers
16 views
Proposal density of Metropolis algorithm
I am new to the Metropolis-Hastings algorithm and am trying to wrap my head around the key points of it. I understand that it uses a Markov Chain Monte Carlo simulation to sample points throughout a ...
0
votes
0answers
26 views
Convergence in total variation distance of Markov kernel $n$-fold composition to the stationary measure
Let
$(E,\mathcal E)$ be a measurable space
$\mu$ be a measure on $(E,\mathcal E)$
$p:E\to(0,\infty)$ with $$\int p\:{\rm d}\mu=1$$ and $\pi$ denote the measure with density $p$ with respect to $\mu$
$...
2
votes
0answers
37 views
How to MCMC (or other simulation) given a non-stationary distribution?
Say I was given some directed graph that satisfies the Markov property, has a stationary distribution, $\pi$, and I know the transition probabilities are functions of some unknown parameters $P_{i\to ...
0
votes
0answers
14 views
simulation of customer negotiation strategies using R
If I ask the question in the wrong forum, let me know, I will delete it. It is still difficult for me to decide the forum.
I am currently studying the issue of Models for customer-supplier negotiation ...
0
votes
0answers
12 views
About function V in geometric drift condition for Markov Chain
When I read the geometric ergodicity of Markov chain in Meyn and Tweedie, I note that in the drift condition $PV(x)<\lambda V(x)+bI_{x\in C}$, where $V(x)\ge 1$ is required. Why $V(x)\ge 1$ rather ...
1
vote
0answers
13 views
Is having a burn-in time relevant when only trying to sample from a distribution?
I'm trying to simulate - via the Metropolis-Hastings algorithm - a sample $X$ of size 10000 from a density $f$ using a proposal distribution $g$.
The Markov chain $X$ obtained by this algorithm has ...
3
votes
0answers
44 views
Feynman-Kac formula in action.
Briefly speaking, the Feynman-Kac formula gives a way for constructing $C^2$ functions satisfying certain PDEs in the classical sense (at least, it's how it is explained in Oksendal's book that I am ...
1
vote
0answers
22 views
Lattice vs. Random sampling for function interpolation
Suppose $f: [0,1]\times[0,1]\rightarrow \mathbf R$ is smooth. I am to interpolate the function from the function values of $f$ at $n^2,\, n\in \mathbf N$ samples points. I have the freedom to pick ...
0
votes
0answers
51 views
Python monte carlo value at risk with non normal distribution
What is the right way to implement a monte carlo method on a currency portfolio with non normal distribution?
I am using a geometric brownian motion with normal random variables but I would like to ...
0
votes
1answer
25 views
How to discard negative values while adopting Monte Carlo?
I am trying to simulate a random variable, for a Monte Carlo simulation, which is equal to another Normal random variable, superimposed with a zero mean gaussian random variable as specified below --
...
1
vote
1answer
43 views
Monte Carlo double integral over surface of $|x|+|y| \leq 1$
$\iint_{|x|+|y|\le1}\!x^2\,dxdy$
I am supposed to calculate this by using Monte Carlo integration. Can anyone give basic hints or directions? I know the idea behind the Monte Carlo integration ...
0
votes
1answer
23 views
Comparing two random variables with monte carlo sampling
Suppose there are two numbers X1 and X2 that are from a random continuous probability distribution with unknown range. You are given the value of X1 and you need to determine whether X1 is less than ...
0
votes
0answers
11 views
Derivation of tau time-stepping in Gillespie algorithm?
I'm trying to find the derivation of tau ($\tau$) in the Gillespie algorithm. All the papers and chapters I've found simply say, without actually showing its derivation: "Tau is given by"
$\tau = \...
1
vote
1answer
665 views
Mathematics solution for Gerrymandering problem?
Gerrymandering is a practice intended to establish a political advantage for a particular party or group by manipulating district boundaries, and can create large disproportions in voting results as ...
0
votes
0answers
13 views
Monte Carlo Markov Chain - Metropolis-Hastings - Estimation of parameters
I have 6 parameters to estimate : $p=(\theta=[a,b]$, $\nu=[r_0,c_0,\alpha,\beta])$ with Bayesian and MCMC methods :
$$\text{PSF}(r,c) = \bigg(1 + \dfrac{r^2 + c^2}{\alpha^2}\bigg)^{-\beta}$$
and the ...
0
votes
0answers
52 views
Why is the Monte Carlo integration dimensionally independent?
Suppose that the random variables $x_1, x_2, ... x_N$ are drawn independently from the probability density function $p(x)$.
Now the convergence rate of a deterministic numerical integration method ...
1
vote
1answer
68 views
Why does the Monte-Carlo Method Work?
I've been reading about the Monte-Carlo Method and how it is much simpler for computers to use the Monte-Carlo Method to guesstimate solutions to complex problems like the Standard Model. It is ...
0
votes
0answers
66 views
Random numbers associated in Monte Carlo Simulation
An Outcome has a probability of 35% of occurring. To Simulate this outcome, which integer random numbers on a scale of 0-99 should be associated with it for Monte Carlo Simulation?
3
votes
1answer
30 views
Approximating the first moment of h(x) where $x$~Lognomal($\mu, \sigma$)
What is the best way to approximate $E(h(X))$, where $X$ ~ Lognomal($\mu, \sigma$).
So far, I can think of Monte Carlo Methods and Gaussian Hermite quadrature as below:
\begin{align}
E(h(X)) &= ...
0
votes
0answers
29 views
How can we measure how good a Metropolis-Hastings estimator of an integral is?
Let
$(E,\mathcal E,\mu)$ be a $\sigma$-finite measure space
$Q$ be a Markov kernel on $(E,\mathcal E)$ with $$Q(x,\;\cdot\;)=q(x,\;\cdot\;)\mu\;\;\;\text{for all }x\in E\tag1$$ for some $\mathcal E\...
1
vote
0answers
40 views
Markov kernel for the simulated tempering algorithm
Let
$(E,\mathcal E,\mu)$ be a measure space
$I$ be a set with $|I|\in\mathbb N$ and $\zeta$ denote the counting measure on $(I,2^I)$
$w_t:E\to[0,1]$ be $\mathcal E$-measurable for $t\in I$ with $$\...
3
votes
0answers
75 views
How to find Minimum of Function with Many Local Minima
I'm trying to find the smallest local minima within a given boundary condition, e.g., a circle. Currently, I'm using a monte carlo algorithm to approximate the minimum, followed by a gradient descent ...
2
votes
1answer
73 views
Why is Monte Carlo integration randomly sampled?
As I understand, Monte Carlo integration uses stochastic sampling to sample points.
Obviously, you would need many samples to reach an accurate result, but why does this process have to be random?
...
0
votes
0answers
13 views
Optimal importance sampling distribution
Let
$(\Omega,\mathcal A,\operatorname P)$ be a probability space
$(E,\mathcal E,\mu)$ be a measure space
$f:E\to\mathbb R$ be $\mathcal E$-measurable
$p:E\to[0,\infty)$ be $\mathcal E$-measurable ...
0
votes
0answers
18 views
Quickly estimating the optimal bin size for the Jackknife re-sampling method
I am trying to apply the Jackknife method to compute confidence intervals for data collected from Monte Carlo simulations. My understanding is that to counter the effect of autocorrelations I should ...
0
votes
0answers
22 views
Construct a new confidence interval (CI) from a published asymmetric CI which was determined using Monte Carlo simulation.
Background: NOAA publishes precipitation frequency estimates for the U.S. where the authors use a Monte Carlo simulation technique to generate 1,000 synthetic data sets to estimate a 90% confidence ...
0
votes
0answers
28 views
essential understanding issue in monte carlo simulation
lets look at my problem with this example:
$$ \int_0^1 f(x) dx=\mathbb{E}[f(U)]$$ where $U$ is uniformly distributed on $[0,1]$.
The Monte Carlo estimator would be $\displaystyle M:=\frac{1}{n} \sum_{...
-1
votes
1answer
59 views
Monte Carlo Integration - unbounded domain
Monte Carlo Integration - function np.sin(θ)^24) / (θ^2) where 0<θ<∞ .
How can we integrate this function over a bounded domain and get an accurate result and what bounds should you choose to ...
0
votes
1answer
39 views
Markov Chain Monte Carlo thermolization time estimation (not by eye)
For a given MCMC algorithm, there are two important time(=step) scale.
$\tau_{thermolization}$ also known as burn-in time, intialization time.
$\tau_{indenpendent}$ the time scale to make $X_i$ and $...
1
vote
2answers
168 views
Monte Carlo to evaluate infinite integral on R
I am using Monte Carlo method to evaluate the integral above:
$$\int_0^\infty \frac{x^4sin(x)}{e^{x/5}} \ dx $$
I transformed variables using $u=\frac{1}{1+x}$ so I have the following finite integral:
...
0
votes
0answers
46 views
Antithetic sampling and Monte Carlo simulation
Consider:
\begin{align}
f(x) = \left\{ \begin{array}{ll}
0, & 0 < x < 0.9 \\
100, & 0.9 < x < 0.91 \\
0, & \textrm{otherwise} \\
\end{array}\right.
\end{align}
Determine ...
2
votes
0answers
24 views
Show that the metropolis matrix is irreducible
Let
$E$ be a countable set equipped with the discrete topology and $\mathcal E:=\mathcal B(E)$
$\pi$ be a probability measure on $(E,\mathcal E)$ with $$\pi(x):=\pi(\left\{x\right\})>0\;\;\;\text{...
0
votes
1answer
127 views
How to calculate the transition matrix in Markov sampling (example)?
Let's say you can simulate a discrete uniform distribution $\{0,1\}$ (like a coin toss). With $P\{1\} = P\{2\} = 0.5$.
Now we would like to simulate a distribution $S = \{1,2,3\}$ with $P_Z\{1\} = 0....
0
votes
1answer
33 views
using monte carlo to determine uncertainty.
In my thesis there are some uncertainties (for example in geometry: the diameter of cylinder, the height ,.. or the temperature of inlet fluid ) and I want to know what is the effect of them in my ...
1
vote
1answer
69 views
Approximating pi rate of convergence
I have been reading about a method for approximating $\pi$ using two uniform distributions and the ratio of points that lie within the circle compared to the square formed by the two uniform ...
0
votes
0answers
22 views
difference between the the means of subsampling from an unbiased sample
Suppose I have a distribution 𝔽 with mean M. Also, assume we have a set of i.i.d samples of size n denoted by X=$\{x_1,x_2,...,x_n\}$ from 𝔽. As a result, all $x_1,...,x_n$ are independent with ...
1
vote
1answer
72 views
why monte carlo method use random sampling? and not a specific numbers? [duplicate]
in calculating the area of a circle in a square we use random points to calculate the fraction of circle! but why we dont assume a simple grid and put our points in the center of it. this seems more ...
1
vote
1answer
44 views
Monte-Carlo approximation with small samples
Let me suppose I have one function of $y$ given $x$ : $f(y\mid x)$ and $N$ samples of $x$ : $\{x_i\}_{i=1}^N$. Here, I’d like to create a distribution over the space of $y$ based on this function $f$ ...
1
vote
1answer
47 views
Generating samples of a Gaussian vector with independent components above a hyperplane
Let $(Z_1,Z_2,\dots,Z_N)$ be a Gaussian vector with iid components, zero mean, and unit variance. Consider a hyperplane in $\mathbb{R}^N$. I am interested in generating samples of this Gaussian vector ...
1
vote
1answer
36 views
Generating samples from certain regions of a Gaussian distribution
Let $X$ be a Gaussian random variable where for simplicity, $X \sim N(0,1)$. I am interested in generating samples of $X$ in the following cases: $X \mid X \in (a,b)$ where $a < b$ or $X \mid X >...
2
votes
0answers
29 views
statistical errors associated to Monte Carlo sampling
I have $n$ successive observation $A_\mu $ of a quantity $A$ and I need to understand how the expectation values of the square of the statistical error depends from the autocorrelation time but a ...
2
votes
0answers
122 views
Markov Processes and Detailed Balance
Section 2.2.3 of this book:
http://itf.fys.kuleuven.be/~fpspXIII/material/Barkema_FPSPXIII.pdf
discusses the detailed balance condition in the context of Markov chain Monte Carlo algorithms.
First ...
0
votes
0answers
13 views
To Generating a random variable from a non conventional density function i.e. the time dependent diffusion equation
I am interested in generating a random variable, this is, to obtaining a point (x,y)) by a non conventional density function i.e. the time dependent diffusion equation over an irregular domain on $R^2$...
0
votes
1answer
214 views
Variance of Estimator (Monte Carlo Integration)
Copying this question directly from another stack-exchange site, since didn't receive any good answers there.
So I was reading this paper by Lafortune, "Mathematical Models and Monte Carlo algorithms"...
0
votes
0answers
32 views
monte carlo simulation of stock prices - time step
In my quant finance textbook, a geometric brownian motion is simulated, using a user-defined time horizon $T$ with a number of time steps, which the author denotes as $NSteps$. He then calculates the $...
0
votes
0answers
21 views
Monte Carlo sampling for Fourier reconstruction in high-dimension
I have a problem that involves the (discrete) Fourier transform of a high dimensional function. I can somehow compute and store all the coefficients, but I don't wish to sum all the terms (n^d where n ...
