Questions tagged [unevenly-spaced-time-series]
Time series sampled or measured at unevenly (or irregularly) distributed time points.
177
questions
2
votes
0
answers
19
views
When do ARMA models fail?
I have just started learning about Autoregressive–moving-average model (ARMA). On the Wiki page, it has been mentioned that:
ARMA is appropriate when a system is a function of a series of
unobserved ...
0
votes
0
answers
30
views
Generating a surrogate time series from unevenly spaced time series
I work in the atmospheric sciences and I have data from an automated weather station measuring mean sea level pressure. Due to an extreme event(and consequent loss of electricity)the measurement is ...
0
votes
0
answers
8
views
Hypothesis testing on a moving-average model on unevenly-spaced time series
I have some irregular time series $X$, where $X_t$ are identically distributed, and bounded between 0 and 1. I perform a moving average $Y_t = \sum_{t'} \frac{w(t-t')}{\sum_k w(t-k)}X_{t'}$. The ...
1
vote
1
answer
36
views
What is this type of data called?
An event occurs once per period, such as once per year. Time is measured in discrete units, such as days of the year. Let $A_y$ be the day in year $y$ on which this event occurs. However, we do not ...
0
votes
0
answers
8
views
Predicting the dates of intermittent events
Hello I am trying to predict the date and location of certain events using an LSTM model. The observations of dates are not structured (sometimes no events for many days and sometimes many events on ...
0
votes
0
answers
31
views
Lagged predictors in irregular-time / asynchronous / time-unconstrained data
In growth curve modeling or other approaches, when time is constrained/synchronous/regular (i.e. panel/wave data; all observations occur synchronously), lagged prediction is trivial - simply add t-1 ...
0
votes
0
answers
53
views
Modelling irregularly sampled observations of a continuous time signal with a discrete state space model
I need to model time series whose observations are sampled at arbitrary points in time. By modelling, I mean that I would like to fit a generative (probabilistic) model that can approximately ...
1
vote
1
answer
70
views
Extract features of uneven time series and use it in cross-sectional study
I have a data like below
subj_1 = 10,20,15,30,60,70,90 (in resolution of years - 2011 to 2018)
subj_2 = 10,20,30,40 (in resolution of months - Jan 2011 to Apr 2011)
subj_3 = 10,15,20,30,45,55,60,70,90,...
0
votes
0
answers
24
views
Quantify similarity between time-series with uneven sampling
I would like to find a way to numerically represent the similarity between three time series, with differing sampling rates. In the past I have used other methods in R, including dynamic time warping, ...
1
vote
0
answers
100
views
How can I generate probabilistic forecasts to do probabilistic classification?
I have a collection of univariate, irregularly spaced, financial time series. Each series is labeled by its class. The image below shows some example data.
A note on the data:
The time series could ...
0
votes
1
answer
59
views
Controlling for time elapsed between baseline and treatment
I'm having a mixed model with 5 repeated measurements (time is categorical because the timepoints represent discrete events).
Edit: I have 5 meaningful timepoints: t0 baseline (neutral timepoint); t1 ...
0
votes
0
answers
23
views
Short Time Series Granularity of Timestamps
I have to make a prediction on a time series whereby there are 10 years of data. My first option is to predict the values aggregated to the annual level using SARIMAX (excluding the seasonality ...
2
votes
1
answer
39
views
Interrupted Time Series with Unevenly Distributed Samples
I'm working on causal inference using Interrupted Time Series Design. I have multiple samples per day and am selecting my analysis bandwidth based on pre-treatment RMSE on leave-on-out cross ...
0
votes
1
answer
41
views
Forecasting Prices with interdependence that form a Timeseires
I have already asked a simmilar question, but i thoguth that this was not phrased well and hence i am trying a new post were i ask a better question. Let me know if this is ok. Judging by some of the ...
3
votes
0
answers
36
views
Unevenly spaced multiple time series modelling
In the context of unevenly spaced (multiple) time series (USTS), are there any classical approaches? If they were evenly spaced, we would try ARIMA, or VAR, or even State-Space models.
I've been ...
0
votes
0
answers
15
views
Construct an averaged-out time series from multiple runs with different sample rates
I am heating up different protein solutions and measuring their absorbance as it changes in time. I am running the same experiment multiple times for each condition. I would like to eventually get a ...
0
votes
0
answers
37
views
A times series problem with variable length and time shifted sequences
I would like to get some guidance (maybe papers, algorithms to try) on a times series problem and I don't know how to approach it, as I am a novice in the domain. The problem brings several challenges ...
0
votes
1
answer
55
views
causal effects when y is continuous and discontinuous over time
I am interested in estimating the causal effects of A(treatment) on Y(outcome). Here treatment is a binary variables (yes vs no). Outcome is a continuous variable(weight), and this is normalized to Z ...
2
votes
0
answers
46
views
Regression for hierarchical time series
I have a dataset with time series A, B and C from different countries. These time series have different starting points, missing values, and irregular intervals (only weekdays).
Instead of forecasting,...
0
votes
0
answers
17
views
Covariance from time series with asynchronously observed components
Let $(X_t) = (X^1_t, \cdots, X^d_t)$ be a time series in $\mathbb{R}^d$ with
covariance matrix $C_t := \big(\mathrm{Cov}[X^i_t, X^j_t]\big)_{i,j}$.
Suppose that $X\equiv(X_t)$ satisfies some ...
0
votes
1
answer
30
views
How to get daily returns from irregularly spaced price time-series?
I have a timeseries that has irregularly spaced time indices as below
...
0
votes
0
answers
9
views
Difference of 1 time series vs many others
I have many time series that span for 30 periods but they might be unbalanced over time i.e. some individuals may lack an observation on a given time period. I'd like to know if a given series is ...
1
vote
0
answers
44
views
Feature creation based on irregular time series with strictly monotonic values
I am given the following problem to run predictive maintenance on the following mess:
I have some IoT sensors out in the field, but I cannot easily change the software on them. Also, data collection ...
0
votes
1
answer
64
views
Unevenly spaced time-series forecasting and anomaly detection for an industrial usecase
I am currently working on a PhD project for a car manufacturing company, which basically consists of creating a predictive maintenance application for the machines that are currently used to fill the ...
1
vote
0
answers
26
views
How to create an ML training dataset from unevenly spaced multivariate timeseries?
I have a time series dataset with multiple features X_n from which I want to predict an output y. However, both the x and y values are unevenly spaced and were sometimes collected at different ...
0
votes
0
answers
83
views
Best R package for analysis of DEGs in a time-series RNA-seq?
I have been reading quite a bit in the last couple of days, but I haven't found a definitive answer.
I want to do a DE analysis of time-series RNA-seq data in R with the following restrains:
Over 6 ...
1
vote
0
answers
18
views
Predicting events - seizures in epilepsy. A question about time series models matching with observations
I've been keep a diary of epilepsy seizures, and would like to attempt prediction modelling as an help for better management of anti consultant therapy.
Could you help to suggest models that fit with ...
0
votes
0
answers
24
views
Analyzing the relationship between language and poll data over time - R
I'm looking at linguistic markers (e.g. use of first-person plural pronouns “we,” “us,” “our,” “ours”) in political speeches of two candidates over time.
One hypothesis is that the use of those ...
1
vote
0
answers
33
views
How to analyse simple internet downtime log?
I have a log of internet downtime (timestamp + downtime in seconds) and I'd like to analyse it to try and spot trends, especially if I can see that it normally happens around specific times of the day,...
0
votes
0
answers
23
views
Standard error of mean for samples from a semi-regular time-series
I am quite a novice in statistics, but am currently facing a problem in my research where I would like to know how much I can trust the mean value from a set of 72 samples. Ideally, the approach would ...
1
vote
0
answers
74
views
Cross Correlation between highly unevenly spaced time series
I have the following problem.
I have 2 time series, one on a yearly basis (2010 - 2020) and one on a daily basis (01/01/2010 - 31/12/2020).
I looking for methods how I can investigate the correlation ...
0
votes
0
answers
40
views
Should you bin data when creating moving average to generate a forecast?
Let's say I have insurance claims that are created on a daily basis on Monday through Friday but sometimes there will be days in which we don't get a claim, perhaps it'll be a week or two that we don'...
0
votes
0
answers
17
views
Time series methods that allow for intepretation of the coefficients of independent variables
For our project, we have to work with the social media text data of several hundred musicians. The data does not have equal time intervals, as musicians could send out messages twice a day or once a ...
0
votes
0
answers
60
views
Equivalent of "lm" for irregular time series forecasting in R
I have a two column data frame corresponding to time series of the form (Date, Value). I want to predict future values of Value based on this data. I don't need anything fancy, just a quick and dirty ...
1
vote
1
answer
24
views
How to perform autoregression analysis with higher-resolution explanatory data
I have two time series of data, shown in the below plot. My response data is an annual total (brown, plotted in the middle of the year totalled), my explanatory data is a monthly summary index (black)....
0
votes
0
answers
40
views
Fill missing values when aggregating a time series from minutes to hours
I am attempting to predict future values using AWS Forecast, and my data is by minute. However, due to data size constraints, I need to aggregate this data to hourly.
The problem is that I am missing ...
1
vote
0
answers
80
views
Can I use Granger causality for missing data/ irregular time series?
I have two time series and I want to look at their Granger causality. My data is from two irregular time series. Irregular here means sampling was done sporadically across 3 years. In some months, ...
0
votes
0
answers
22
views
Time Series Classification with Unequal Time Between Events and Number
I have a problem where I'd like to predict whether a customer is going to convert. I have event data for these customers over time and the histogram for time to conversion follows a 1/x pattern where ...
0
votes
0
answers
25
views
Measuring frequency of change in time series data with inconsistent time intervals?
Context
I'm tracking auction house prices for items in Guild Wars 2 in a database. They provide an API that allows me to get the item's current buy/sell offer quantities and prices at that moment. As ...
0
votes
0
answers
41
views
Time dependent representation for time series events with different time gaps?
In natural language processing, we can treat characters as evenly spaced time series in RNN models where time gaps are independent of the sequence and only sequential positions matter.
If I want to ...
0
votes
0
answers
13
views
Statistical Test for Trends in Samples from a Possibly Changing Distribution
I have some data of quantitative measurements of the language in books from the years 1800 to 2000. For each year I have between 0 and 50 samples, mostly about 10 samples per year. If I bin the data ...
1
vote
0
answers
135
views
Calculating EWMA & EWMV of concurrency from duration & interval
I'm looking to calculate the exponential moving average & exponential moving variance of a continuous series of request/responses, using each response's duration and the interval (time delta) ...
0
votes
1
answer
13
views
Creating an index using transactional data
I have a dataset of a series of leases.
Variables we have: precinct, date (in quarters), lettable area, price as well as a few others.
These assets are not homogenous, although are comparable.
In some ...
0
votes
0
answers
121
views
What is the best method to predict the water consumption of EACH customer for the next month?
Say we have a dataset that has the following attributes:
customer_id: There are a total of 1000 customers, each of them with a unique customer_id
observation_date: The date on which we last observed ...
2
votes
0
answers
47
views
Does it make more logical sense to model the discrete FFT output as a categorical variable or a numerical variable?
I am training a time-series data classifier and some of my features are the output of CT FFT. The results are of course discrete frequencies. I understand that they are in numerical order and higher ...
2
votes
0
answers
57
views
Spot unusual patterns in a discrete intermittent time series
I have a multitude of daily time series representing the volume of a certain product arriving per day at a station. There are as many time series as their are stations, and they each look like the ...
2
votes
2
answers
415
views
Data leakage in temporally overlapping train-test split
Question: In the sliding window train-test split strategy, will there be data leakage if, say, I train on a dataset $X_{t}$ to predict values $y_t$ that were collected after my test data $X_{t+1}$?
...
1
vote
0
answers
35
views
Forecasting with Irregularly Missing Data
Suppose I am supplying $N = 1000$ vendors, and I am looking for a way to predict their demand for my product over $T = 90$ days. Concretely, I hope to take some features for each vendor, such as their ...
0
votes
0
answers
617
views
Comparing time series data with different interval
I have time series data for one day (temperature) measured every 5 seconds and would like to increase the period between measurements and somehow calculate the level of error/similarity/correlation (I'...
0
votes
1
answer
106
views
How to detect a drop in regularity / increase in spontaneity of time data?
I have been tasked with detecting changes in regularity for multiple datasets. Each dataset is linked to a different type of event, and each dataset consists of a few hundred timestamps representing ...