All Questions
6,766 questions with no upvoted or accepted answers
4
votes
0
answers
99
views
ARIMA Forecast is 14 Orders of Magnitude Higher than Training Data?
I am dealing with intermittent time series data, i.e. mostly zeros. Here is the particular time series that is giving me trouble:
[0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
0.0,
60.0,
0.0,
0.0,
0.0,
0.0,
36.0,
0....
- 121
4
votes
0
answers
139
views
Time-Varying-Intercept in Logistic Regression
Background
I have a panel of binary response data - I have a different cross section of individuals each month, across many months, and the outcome is 0 or 1. When fitting a logistic regression that ...
- 523
4
votes
0
answers
67
views
Adjustment in a regression for community level aggregation of individual level data
In a cross-sectional study based on geographical multilevel regression, the authors used both individual-level data AND features generated by aggregating the same individual data in the community and ...
- 2,949
4
votes
0
answers
48
views
Calculating similarity/resemblance of time series data? (soil moisture)
I have measured a variable (soil moisture) for multiple samples over time. Soil moisture increases steeply at several points in time (when it rains) and then decreases steadily until the next rain ...
- 75
4
votes
1
answer
63
views
Can regression forecasts of univariate time series be independent (of one another)
Suppose I have short-term forecasts from two univarite regression models of the same time series. I am choosing the models to be as different as possible in structure and assumptions. For instance, ...
- 3,247
4
votes
1
answer
113
views
Methods for drawing population inferences from multiple sub-population datasets
What would be an appropriate model or method for making inferences about a broader population quantity from multiple quantities representing subsets of the population?
Imagine, as an example, that I ...
- 1,312
4
votes
1
answer
128
views
Modeling a time series of ordered vectors
I have a series of ordered vectors, $\pmb{x}^o(1), \ldots, \pmb{x}^o(n)$. Here, $\pmb{x}^o$ means the ordered vector of $\pmb{x}$. For example, if $\pmb{x} = (2,5,1)^\top$, then $\pmb{x}^o = (1,2,5)^\...
- 765
4
votes
0
answers
340
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 ...
- 69.5k
4
votes
1
answer
234
views
Are power law relations between means and standard deviations inherent in normally distributed data?
In a recent paper I submitted for publication I document a power law relation between the means and standard deviations of several time series. That is, when plotting the log of the means of each of ...
- 515
4
votes
0
answers
292
views
How would a Bayesian answer this question from Jeffrey Wooldridge
Jeffrey Wooldridge, a famous econometrician, posed the following question to Bayesians on twitter:
I think frequentists and Bayesians are not yet on the same page, and
it has little to do with ...
user314217
4
votes
0
answers
339
views
Combinatorial symmetric CV vs Combinatorial purged CV
Reading "Advances in Financial Machine Learning", and the author proposes 2 methods of CV: "combinatorial symmetric cross validation" (11.6) and "combinatorial purged cross ...
- 41
4
votes
0
answers
2k
views
RNN vs ResNet for multivariate time series prediction
All others being equal, would a ResNet-based or RNN-based neural network (with/without an attention mechanism) perform better for forecasting a multivariate time series?
Related:
Deep learning for ...
- 277
4
votes
0
answers
165
views
Trend Dampen with SARIMA
Trend dampen exists as a parameter for Holt-Winters in the ExponentialSmoothing class for statsmodels but how can I do something ...
- 1,602
4
votes
0
answers
786
views
Time series - Stationarity and invertibility?
Sometimes when I take material from time series to study, it appears out of nowhere "for a process to be stationary it is necessary for the roots of the characteristic polynomial to fall outside ...
- 572
4
votes
0
answers
138
views
Mixed Effects Model: Writing and Interpreting Models with Two and Three-Way Interaction Terms and No Random Intercept
Question: Have I correctly translated my lmer models into formulas depicting each individual level, as well as the composite formula? Specific questions about my work below.
Information about my ...
- 363
4
votes
0
answers
219
views
What’s the right multilevel model to address this meta-analysis?
I have a sample of about 4,000 $r$ (that is, Pearson correlation), $\chi^2$, $t-$, or $F-$ tests reported in psychology journals. These tests have been drawn randomly from a larger dataset with about ...
4
votes
0
answers
86
views
What assumptions about time series data are neccessary to use a stateless LSTM?
Basically I am trying to model a time series using an LSTM layer, and I was wondering whether I should be using a stateful or stateless LSTM layer. More specifically I was wondering what assumptions ...
- 41
4
votes
0
answers
362
views
Continuous time series classification with lstm in Keras?
I have been researching time series classification with LSTM. I've seen examples where they provide continuous predictions, i.e. the prediction is updated at each time step. Is it possible to train a ...
- 1,239
4
votes
0
answers
138
views
Can we identify whether random effects are nested or crossed from a lme4 fit?
My colleagues and I are working on a suite of lmer post-estimation tools for a R package we are developing. One of the tools is an ICC function that would calculate ...
- 5,890
4
votes
0
answers
381
views
AIC Comparison for MLM with Different Distributions
Thank you in advance for your time and consideration! I am a non-mathematically-inclined graduate student in communication just learning multilevel modeling.
We are running different models - some ...
- 61
4
votes
0
answers
176
views
SARMA model as infinite AR
Can anyone reference an algorithm or paper which can help me convert a general SARMA model to an infinite AR polynomial in backshift operator B? I would like to do this in R somehow.
$$ \frac{\theta(...
- 672
4
votes
0
answers
83
views
How to pick the daily volatility component in Multiplicative Components GARCH modelling?
Recently I've been drawn to the rather interesting Multiplicative Components GARCH model for intraday volatility modelling, a draft paper written on it can be found here: Chanda, Engle, Sokalska, 2005 ...
- 282
4
votes
0
answers
246
views
Time series regression analysis with GAM in a factorial design
I have data from 16 automated sensors that measure a parameter across 4 experimental treatments with 4 replicated experimental units each:
How would I go about to robustly test for significant ...
- 761
4
votes
0
answers
93
views
Can Time Varying Coefficient models with a Kalman filter approximate any non-linear function?
I read that Time Varying Coefficients (TVC) models with non-parametric methods can approximate any non-linear function. This is from "Non-Linear Models: Where Do We Go Next - Time Varying Parameter ...
- 63
4
votes
0
answers
272
views
when fitting a regression model to a time-series, can I use lagged values of the time-series itself?
I'm fitting a regression model $y_t$ to a time series $x_t$ (not a dynamic model involving ARMA terms!). I saw that useful predictors to put in my model are $t$, seasonality variables and lagged ...
- 3,360
4
votes
0
answers
503
views
Portmanteau Test for VAR
I am new into working with VAR models and have a fundamental question regarding model diagnostics.
As suggested in Kilian and Lütkepohl (2017, pp. 52-53), I would like to run a Portmanteau test for ...
- 141
4
votes
0
answers
1k
views
AR(1) model with autoregressive intercept
Let us consider the following model:
$$
y_{t} = c_{t} + \alpha y_{t-1} + v_{t} \\
c_{t+1} = c_{0} + \beta c_{t} + w_{t}
$$
where $v_{t} \in \mathcal{N}(0, \sigma^{2}_{v})$ and $w_{t} \in \mathcal{N}(...
- 668
4
votes
0
answers
508
views
White noise terms in moving average model
As many before, I lack the clear intuition behind the Moving Average model. Eventhough I read quite a few threads on CV.
The Moving Average $MA(q)$ model consists of a constant and White Noise terms.
...
- 310
4
votes
0
answers
88
views
Intuitive explanation of using ACF to determine the order of MA in time series
It is intuitive to know why we can only use PACF to determine the order of AR - since ACF will show good correlations even for the lags which are far in the past, as it also cater for indirect effects ...
- 1,087
4
votes
0
answers
240
views
What is the fundamental assumption for using resampling methods?
Suppose that I observe a set of non-i.i.d. data (time series) $\mathcal{L} = \left\lbrace (y_{t}, x_{t}) \right\rbrace_{t=1}^{T}$ with $x_{t} = (x_{t1},\ldots,x_{tP})$ a real valued vector of $P$ ...
- 83
4
votes
0
answers
584
views
Confused about multilevel analysis and non independence of observations
I'm still struggling with my understanding of multilevel analysis, wondering if it applies or not to my problem. I'v read here the following (where author gives an example of a multilevel model with ...
- 393
4
votes
0
answers
163
views
Coefficient of determination in time series models
Nagelkerke's (1991) generalized $R^{2}$ (below) is a modification of the Cox Snell (1989) generalized $R^{2}$ (the numerator in the below) which is a coefficient of determination based on the log-...
- 30.7k
4
votes
0
answers
228
views
Method to forecast correlate univariate time-series (with trend, seasonality) via regression
I have two univariate time-series with seasonality and trend--dt1 and dt2. I believe that dt1 and dt2 are strongly correlated, both through a few statistical test (see below) and that in my field dt2 ...
- 41
4
votes
1
answer
60
views
Looking for advice: Short-term forecasting using actual forecasts and real time data
First of all apologies, I have very little experience in statistics and my biggest problem is using the correct terminology. I'm here mainly looking for guidance and direction.
Background: I have a ...
- 41
4
votes
0
answers
338
views
Biased estimates of Hurst exponent in R/S analysis
I've used the standard R/S algorithm for estimating the Hurst exponent in Mathematica*, and tested it on fBm and fGn for $H\in\{0.05,0.1,\ldots,0.95\}$, generating 1000 time series for each $H$. The ...
- 1,264
4
votes
0
answers
394
views
Frequency analysis of categorical/binary data
I want to do frequency analysis with a data set of consecutive binary values, such as "Rainy - Sunny - Rainy - Rainy - Rainy - Sunny - ...". Using this data, I want to extract the frequency (= the ...
- 41
4
votes
0
answers
109
views
Thomas Sargent's intuition as to why every covariance stationary series has an infinite-order Wold representation
In his classic book "Time Series Analysis", James Hamilton references Thomas Sargent (["Dynamic Macroeconomic Theory"], 1987, pp. 286-290) as a "nice sketch of the intuition behind this result [Wold ...
- 4,792
4
votes
1
answer
3k
views
Adding noise to time series data to increase training data
I am dealing with a weekly time series forecasting problem and I am currently investigating the use of an LSTM to make a multi-step forecast for a univariate time series. I actually have a ...
- 591
4
votes
0
answers
4k
views
Multivariate ARIMA modelling in R
I am currently using the Marima package for R invented by Henrik Spliid in order to forecast multivariate time series with ARIMA. Overview can be found here:
https://cran.r-project.org/web/packages/...
4
votes
0
answers
223
views
Benchmark data sets for anomaly detection algorithms in multivariate time series
as per title, which datasets are commonly used to benchmark novel methods to detect anomalies in multivariate time series? I'm particularly interested in moderately high-dimensional (10-40 components),...
- 18.4k
4
votes
0
answers
367
views
Proving whether a series is stationary
I want to prove whether the following equation is stationary or not:
$$
x_t = (x_{t-1} + \epsilon_t) (1+k(x_{t-1}+\epsilon_{t})^2)^{-1/2}
$$
Also written like:
$$
x_t = (x_{t-1} + \epsilon_t) \frac{1}...
- 41
4
votes
0
answers
813
views
Time Series sampled at varying frequency - Employ Linear Mixed Model to compare trends?
I hope that this question has not be asked like this elsewhere, if so I could not find it during my google research..
I have the following problem: I have data sampled from different sensors("ID") ...
- 291
4
votes
0
answers
1k
views
Awful performance of LSTM on noisy time series after stationarisation
Note. The post is quite long because I added some thought process for the sake of seeing the big picture. So grab a coffee and indulge yourself. For tldr the actual question on the bottom.
I put my ...
- 348
4
votes
1
answer
4k
views
Relation between AR(p) stationarity and causality
Let's take an AR(p) model $\phi(L)y_t=z_t$ where $\phi(L)=1-\phi_1-...-\phi_pL^p$ and L is the lag operator. I have just studied that if there are no roots of the polynomial on the unit circle,
$1/\...
- 61
4
votes
0
answers
2k
views
Treating outliers for time series forecasting in Python
What is the best way to treat outliers in a time series forecasting model? In particular, for product demand modeling?
Based on what I've read so far, the following methods can be applied:
...
- 739
4
votes
0
answers
259
views
Stationary Distribution of Multiplicative Autoregressive Model
I know for the additive autoregressive model the stationary distribution of $\{X_t\}$ can be found, if it exists, in the following way:
\begin{align}
X_t &= \alpha X_{t-1} + \epsilon_t\\
\...
- 765
4
votes
1
answer
328
views
Establishing the minimum required training set size, when cross validating time series data
I want to evaluate and compare how well various models perform with regards to modelling time series data (the data in question is daily revenue). It seems that cross validation error might be a ...
user205721
4
votes
0
answers
123
views
Normal Covariance Estimation
I have a hierarchical model and I'm struggling to develop an estimator of the covariance of a normal distribution. This is my specific problem. There are $n$ latent $p$-dimensional vectors,
$$\...
- 1,327
4
votes
0
answers
309
views
Tests of stationarity in irregularly (unevenly) spaced time series
I need to do check if my time series data is stationary or not. However, the data is so irregular that cannot be transformed into evenly spaced. Any suggestion?
- 41
4
votes
0
answers
573
views
Is it valid to use random forests for feature selection in a time series problem?
I'm working on a time series problem, with additional predictors. While I'm exploring various ways to approach the problem, one possible way is to turn the time series problem into a supervised ...
- 739