Questions tagged [time-series]
Time series are data observed over time (either in continuous time or at discrete time periods).
14,506 questions
0
votes
0
answers
19
views
Approaching time series forecasting on estimated data [closed]
I’m working on a monthly forecasting problem at CCU (product–market) level and would really value expert feedback on whether my approach so far is sound, and how best to proceed with modeling.
What I’...
3
votes
2
answers
100
views
Outlier tests for time-series data: difference among methods?
I'm working with big data time-series and am trying to detect outliers. Upon my research I've come across a variety of different simple methods (e.g. here and here) and I'm trying to understand the ...
- 389
0
votes
0
answers
14
views
Guidance on ARDL Bounds Test Specification with Mixed I(1) and Trend-Stationary Regressors
I am currently running an ARDL analysis and need guidance on the correct bounds test specification.
Setup:
The dependent variable is I(1) (stochastic).
Among the independent variables, some are I(1) ...
- 1
3
votes
1
answer
88
views
Is it possible to quanify the minimum amount of information a system must acquire or infer in order to make a reliable prediction about the future?
If a predictive system operates under constraints on information storage, is it possible to formally characterize the minimum sufficient information it must retain or infer from the past in order to ...
- 41
3
votes
1
answer
24
views
GlmmTMB troubleshooting for time series count data
I'm hoping for some help on a rather complicated dataset I've inherited.
For context, we have counted these rods and rings structures in cells over time, as they are experimentally pushed to a new ...
- 31
0
votes
0
answers
8
views
Choosing between Yabu–Perron Model 2 vs. Model 3 before applying Kim–Perron unit-root test
I am using the Yabu–Perron (2009) procedure to detect structural breaks in a time series, and I am unsure how to choose between two deterministic specifications. For my series, both models yield a ...
5
votes
1
answer
123
views
How to statistically project 24-hour throughput based on recent hourly production with very limited data?
I need to develop a mathematical/statistical method to estimate how many orders (packages) can be processed in a 24-hour period, based only on the production observed so far in the current day.
For ...
1
vote
0
answers
60
views
Stationarity in the Explanatory Variable(s) in a Fixed Effects Model
I have a fixed effects model of the form:
$y_t = \alpha + \beta * x_t + \epsilon$.
The response variable $y_t$ is stationary. I estimated $\alpha$ and $\beta$ using ordinary least squares (OLS).
My ...
- 1,073
1
vote
0
answers
20
views
Volatility Estimation and forecasting for Ultra-High frequency data
I am unable find methods for Volatility Estimation in ultra-high frequency settings. I am aware HAR-RV and it's counterparts. These models seem to estimate daily volatility using high-frequency data. ...
0
votes
0
answers
13
views
Papers to use as references for "acceptable" R² values in temperature and humidity prediction
As the title suggests, I am conducting research using four machine learning models to predict the internal temperature and humidity of an environment. One of my metrics is R², along with RMSE and ...
0
votes
0
answers
33
views
What are the different EWMA / EWV formulations and what scenarios are they applicable in?
I’m trying to understand the different formulations of the Exponentially Weighted Moving Average (EWMA) and Exponentially Weighted Variance (EWV) that appear across research papers and online ...
2
votes
0
answers
32
views
Help matching an ordered list of events (no timestamps) to a noisy timestamped time-series
I’m stuck and this is starting to feel pretty convoluted, so I’ll try to be clear.
What I have:
A timestamped stochastic time-series (e.g. market prices). It’s noisy but when an event happens the ...
- 21
0
votes
0
answers
51
views
Outlier detection in many short time series
I have a dataset with ~20.000 entries containing mean values for different groups. The groups are defined with 4 categorical columns and I have the week number, the number of samples per week and the ...
- 1
0
votes
0
answers
23
views
How should impulse responses be interpreted in Local Projections when using log first-differences vs long-differences vs percentage data?
I am estimating a local projection model, where on the lhs I have long log difference of the variable, and on the rhs I have log first difference.
I am unsure how to interpret the coefficient. So ...
- 1
6
votes
1
answer
87
views
How can I evaluate a time‑series forecasting model when I must train on the entire small dataset?
I’m building a Python forecasting pipeline that tries several models:
Holt‑Winters (tuned with Optuna)
ARIMA (via pmdarima.auto_arima)
XGBoost (tuned with Optuna)
...
- 163