Questions tagged [random-walk]
A stochastic process that describes a path arising from a succession of random steps.
254
questions
1
vote
0
answers
12
views
Non anticipative sampling an ARIMA(1,1,0) process with known terminal value
I have an $\mathrm{ARIMA}(1,1,0)$ process $X_t$, for which I know the values $X_0=a$ and $X_T=b$. I want to sample paths $(X_t)_{t=1..(T-1)}$ consistent with the boundary conditions.
One way to do it ...
1
vote
0
answers
17
views
When are continuous-time models important?
In Econometrics, majority of the models are in discrete-time setting, whereas when you move on to quantitative finance, continuous-time models are most prevalent. I get the theory and idea behind ...
0
votes
0
answers
6
views
Sampling with Random Walks
I feel so dumb having to post this, I pretty sure I'm just missing a "clever" rewrite of the problem. This isn't for homework, it's an old exam which I'm practising on;
...
1
vote
1
answer
52
views
What type of Markov Chain is a random walk of a Knight on a chessboard?
Assume we have the following chessboard and we have a knight that starts at the top left corner of the board. On every move the Knight chooses reachable square (i.e. a valid chess move a Knight can ...
0
votes
1
answer
46
views
Why can de-noising diffusion models be sampled with Gaussian distributions?
In de-noising diffusion models 1 the latent is typically sampled with a unit normal distribution, and then the sample (e.g. image) is generated by iteratively removing noise during the backwards ...
1
vote
0
answers
10
views
lowerbounding the expectation of maximum of $K$ random walking
Let $X_{i,j}$ be $K \times N$ i.i.d. random variables such that $P(X_{i,j} = 1) = P(X_{i,j} = -1) = \frac{1}{2}$, and $S_p = \sum_{q=1}^{N} X_{p,q}$ be $K$ i.i.d. random variables, each of which is an ...
0
votes
0
answers
20
views
Time-Series: Testing for random walks using the Hurst Exponent
Is the Hurst Exponent a good methodology for testing whether a series exhibits a random walk? I have read in some papers and websites that it is known for producing biased estimates and would like to ...
0
votes
0
answers
26
views
Unbiased random walk : why is a random sample not calibrated
To simplify, consider unbiased random walks with absorbing barriers at 0 and 100. A random walk starting at X has an expected probability to hit the barrier 100 of exactly X%.
However, it seems that ...
1
vote
1
answer
53
views
Time-Series: Testing for stationarity and random walks
My goal is to test the weak-form efficient market hypothesis using time-series on prices of various stocks listed on S&P 500. According to theory, a particular stock is said to be weak-form ...
0
votes
0
answers
14
views
The average distance in a 3D noncentral-chi-distribution random walk process after N steps
In the Noncentral Chi Distribution Wikipedia page, the calculated Mean is:
$$ {\sqrt{{\pi\over2}}L_{1/2}^{(k/2-1)} \large(
{\small{-\lambda^2\over2}})}$$
I am calculating the average distance after N ...
6
votes
1
answer
95
views
3-D random walk: average distance after N steps
I am calculating the average distance in a 3-D random walk process after N steps. Each step is one unit long and the angle is randomly distributed around the origin. After N steps, what is the average ...
2
votes
0
answers
42
views
Time series: how much past predicts future
In financial (time series) statistics and forecasting we usually assume that the past of a series can predict the future to some extent. Every financial ad will warn you that investors should not ...
0
votes
0
answers
12
views
What can and can’t you say about a series with a unit root as evidenced by an ADF test? [duplicate]
I have a time series with 500+ observations which has a unit root, as evidenced by an ADF test at the sub 1% significance level.
I want to explain to my class mates why that’s important and change the ...
0
votes
0
answers
15
views
Taking the Z transform and the Fourier transform of a Discrete-Time Random Walk
I saw that we could apply two transforms to the propagator of the Continuous-time random walk (CTRW),
$$P(x,t)= \sum_{N=0}^\infty [\lambda^{*N}(x)w^{*N}(t)*\int_t^\infty d\tau w(\tau)] $$
where the ...
1
vote
0
answers
61
views
What is the difference between a Simple Random Walk and a Random Walk and why is one stationary, while the other is not?
To clarify, by a Simple Random Walk I mean
$$
Y_i =
\begin{cases}
-1 & prob = 1/2\\
1 & prob = 1/2
\end{cases}
$$
$$
X_t = \sum_{i=1}^t{Y_i} \quad \textrm{,}\,X_0 = 0
$$
and by Random Walk I ...
1
vote
0
answers
30
views
Give a random walk on an interval with specified endpoints & extrema, can I find the probability that the max occurs before the min?
I have some summary measures on a time series process for a large number of time intervals, all of the same length. The summary measures are the initial value (i), which I will take to be zero without ...
2
votes
0
answers
122
views
Is a random walk cointegrated with its own lag?
Can a random walk, or more broadly a unit-root process, be considered cointegrated with its own lag? E.g. if $y_t=y_{t-1}+u_t$ with $u_t\sim$ i.i.d., then $y_t$ is I(1), $x_t:=y_{t-1}$ is I(1) and ...
1
vote
0
answers
45
views
Generating function of a random walk
Consider a random walk with $S_n=\sum^n_{i=1}X_i$, where the random i.i.d. steps $X_i$ take values $-1,0,2$ with probabilities $1/9,1/9,7/9$ respectively. Set $S_0=1$.
I would like to calculate the ...
0
votes
0
answers
519
views
Simple Symmetric Random Walk on $\mathbb{Z}$ is null recurrent
Question: Consider a simple symmetric random walk on integers, where from every state $i$ you move to states $i-1$ and $ i+1$ with probability half each. Show that this random walk is is null ...
3
votes
2
answers
115
views
Random walk analysis of a univariate timeseries
As the title describes, I want to conduct a random walk analysis of a univariate time series $Y_t$. What are the tests and steps that you guys would suggest for this purpose?
My current thinking:
...
2
votes
0
answers
94
views
Random walks and martingales
In class, our professor explained that the martingale process is the in between case of random walk type I (innovations are i.i.d.) and random walk type II (innovations are serially uncorrelated).
...
0
votes
0
answers
63
views
Different Random Walk Types and the Variance Ratio test
From my knowledge, we distinguish between two types of random walks. Type I, where the innovations are i.i.d. and Type II, where the innovations are serially uncorrelated.
I want to conduct several ...
0
votes
0
answers
20
views
Find the expected number of steps [duplicate]
Consider the following problem:
Two people $M$ and $T$ walk over a straight line. The steps they take depend on flipping a coin: They move to the left if the result is head and they move to the right ...
5
votes
1
answer
63
views
Random-walk and unit root processes predictable?
I know that a random walk is an AR(1) with a unit root, but there are also higher order autoregressive processes with unit roots. Does the unit root in such a higher order autoregressive process also ...
2
votes
0
answers
66
views
Is every time series that is not predictable a random walk?
The title already reveals my question. I was wondering how specific the characterisitics of a random walk are defined and if every time series that is not predictable belongs to the class of random ...
0
votes
0
answers
23
views
Weak form of market efficiency and random walks
The weak form of market efficiency states that historical prices should not provide predictive information that is not already incorporated in the current price. Hence, predictions based on the past ...
1
vote
0
answers
80
views
Is ARIMA and Random Walk a Nested model?
I have confused about the Radom Walk. If a model restrict some parameter as 0 and the two regressions are the same, which is the Nested model. But in ARIMA model versus Random Walk model, the random ...
0
votes
0
answers
31
views
Expected first passage time for random walk
A random walk on $\{0,1,2.....n\} $ with $p_{0,0} = p_{n,n} = 1$ and $p_{i,i+1} = p = 1-p_{i,i-1} = 1-q$ for $1 \leq i \leq n-1$ .Let $X_0 = i $ and $T$ be the first passage time to either 0 or $n$ ...
0
votes
0
answers
11
views
What is the underlying proccess of the probability of a stock reaching a determined strike price?
Suppose the price of a stock follows a random walk, the price of a derivative "Stock is over $x at time t" would also follow a random walk?
I talk about probabilities in the question ...
13
votes
2
answers
2k
views
Intuition of Random Walk having a constant mean
I am very new to time series analysis.
A random walk is defined as $Y_t=\phi Y_{t-1}+\varepsilon_t$, where $\phi=1$ and $\varepsilon_t$ is white noise. It is said that process is non-stationary for ...
0
votes
2
answers
149
views
Is random walk with drift is random?
I see everywhere in the web that lag-plot or acf are used to see if a time serie is random. If there is no structure in the lag plot then the data are random, and if autocorrelation = 0 then data is ...
1
vote
0
answers
38
views
What is the distribution of the time-to-ruin for a gambler's ruin problem that allows "pauper bets"?
In another question on this site I have derived the distribution for the time-to-ruin in the gambler's ruin problem where the wealth of the gambler follows a discrete-time random walk. In this ...
1
vote
0
answers
17
views
How to invert a random walk [closed]
I have a random walk dynamic parameterized in a function let's say $f(x)$ e given a $x_0$ I can retrieve a curve of this initial value after several simulations. But I need to "invert" this ...
2
votes
1
answer
127
views
Are there good examples of martingale processes that are not simple random walks?
Are there non-trivial examples of martingale processes that aren't simple random walks?
I'm trying to better understand the difference between martingales and simple random walks. They look pretty ...
2
votes
0
answers
84
views
Fast uniform sampling of walks from directed graph
Given a directed graph $G=(V, E)$ my goal is to sample a set of walks $W\subset\mathcal{W}$ where $\mathcal{W}$ is the set of all walks in $G$. I want each walk to be sampled with the uniform ...
4
votes
1
answer
92
views
What is the distribution of time's to ruin in the gambler's ruin problem (random walk)?
In a gambler's ruin problem, where the gambler starts with a fixed amount of wealth. What is the distribution of times to ruin. That is, if each bet has a fixed payout.
As I understand it, this is a ...
0
votes
1
answer
50
views
MCMC: Rejecting samples outside the prior support?
I wish to implement a MCMC procedure for a posterior density which has non-trivial prior support. To clarify, this means that the parameter space has certain regions (i.e., combinations of parameters) ...
1
vote
0
answers
54
views
Is CPU utilization a predictable time series? [closed]
I've been wondering whether metrics about CPU and resource utilization is a time series which can be predicted or rather a random walk which I cannot learn from. Can recognizing a pattern in the data ...
3
votes
1
answer
55
views
Explain formally how expected time to hit 0 from two is the sum of the expected time to hit 1 from 2 and 0 from 1
I have a symmetric random walk on the integers with probability $p$ and $q$ of going up and down respectively started at $X_0 = 2$.
Let
$$
T^0 = \min\{ n > 0: X_n = 0\}, T^1 = \min\{ n > 0: X_n =...
4
votes
2
answers
109
views
Appropriate distribution for simulating a random walk between two known points, with known min/max values
I have a 1-D random walker. It starts at a value of x at time t=0. It ends with a value of y ...
2
votes
1
answer
58
views
Why iterations of Gibbs sampling for a bivariate Gaussian distribution can be seen as random walk?
In Section 4.4 of the excellent technical report Probabilistic Inference using Markov Chain Monte Carlo Methods, the author tries to analyze the performance of Gibbs and Metropolis algorithm with ...
2
votes
2
answers
71
views
Random Walk why is $E[X_{t}] = \mu t$
Question
A Random Walk can be defined as follows. $Z_t$ ($t=1,2,3,\ldots$) is a noise term with a Normal$(\mu,\sigma^2)$ distribution. Define $X_0=0$ and
$$X_t = X_{t-1}+Z_t$$
for $t=1,2,3,\ldots.$
I ...
0
votes
1
answer
92
views
How do we define the kernel to calculate the acceptance ratio for Metropolis-Hastings Markov Chain Monte Carlo?
I am having a lot of difficulty understanding how to apply the algorithm to a real scenario.
The part that confuses me is that we are looking for a target distribution (the real distribution of our ...
4
votes
1
answer
95
views
distribution of maximum random walk distance
Related to this question.
Suppose I flip a fair coin $N$ times and keep track of the difference between the total number of heads and tails as I am doing it. At the end of the $N$ coin flips, I have ...
2
votes
1
answer
58
views
If $y_t$ and $x_t$ are cointegrated, then are $y_t$ and $x_{t-d}$ also cointegrated?
Assume that $x_t, y_t$ are $I(1)$ series which have a common stochastic trend $u_t = u_{t-1}+e_t$. Particularly, consider the following DGP
\begin{align}
y_t&=\alpha_y+u_t+a_t \tag{1} \\
\end{...
1
vote
1
answer
38
views
Random walk variance in R less than expected
I am trying to prove via some Monte Carlo simulation that the variance of a random walk equals $t*σ^2$ in R. I am running the following code, 180 times, to find the variance of 180 different random ...
3
votes
2
answers
149
views
Which one is more likely to be random walk?
Consider the two series in the chart below: $walkA$ and $walkB$.
They are based on the same steps, although the steps come in a different order.
Indeed, $stepsA$ and $stepsB$ have identical sample ...
0
votes
1
answer
129
views
Can a ARIMA(0,0,0) model be stationary?
I have a time series of a stock and use its log differenced daily returns. I have conducted an ADF test for a presence of unit roots, a KPSS test as well and both confirms stationarity in the time ...
0
votes
0
answers
39
views
Random walk and variance [duplicate]
If yt is pure random walk the variance Var(yt-yt-k) will (increase, decrease or remains constant) as lag k increases?
2
votes
0
answers
35
views
Same results for RandomWalk and Snowball sampling algorithms
I am trying to find the best sampling algorithm to obtain a sampled graph that exhibits the same distribution compared to the original graph. The metric I am using at the moment is PageRank.
The ...