Tagged Questions
Time series are data observed over time (either in continuous time or at discrete time periods).
0
votes
0answers
14 views
Wind (speed) - a non-iid random variable?
Over a time period of 1 year, half hourly wind speed data is collected. Is it false to state that the collected data is not-iid? I know that wind is seen as a non-stationary process, but does it also ...
0
votes
1answer
14 views
Special Case Probability
Suppose there exists an ideal system in which you have perfect data 100% c.i. This data tells you that the price of gasoline will move a distance (not displacement) of +/- 10% in the next 7 calendar ...
4
votes
1answer
41 views
Modelling Time Series of Ratios
I’m having difficulties dealing with a time series of relations between two numbers.
I have two time series, essentially a count of "successes" and "trials". What I'm interested in, though, is the ...
0
votes
0answers
11 views
time series decomposition seasonal_decompose
I have two time series and I did a decomposition for both in python using
seasonal_decompose from statsmodels.tsa.seasonal using freq = 7. I'm thinking they have weekly seasonality.
This one shows ...
3
votes
1answer
30 views
How to forecast integer time series in R?
For a while now I used to forecast integer/count time series as I would do for any other continuous time series, meaning : I use models like ARIMA, ETS, THETA, TBATS ... And then I simply round the ...
0
votes
0answers
15 views
Model mean/median change per observation time?
A Cox proportional hazards model makes it possible to investigate how an independent variable affects the risk of a dichotomous state occurring per observation time.
Is it possible to model how an ...
-1
votes
0answers
19 views
How to structure python dataframe containing timeseries sensor data for regression modeling? [on hold]
The dataset:
I have a dataset containing the data of a manufactoring process. The dataset contains the process ID ("Sarzs_no"), the ID of the manufactoring machine ("Unit"), the data logged by two ...
0
votes
0answers
7 views
Autocorrelation, Autocovariance and Large lag Standard Error
I have time series generated data from Monte Carl-Metropolis Simulation. I have estimated correlation coefficients using: $r_k = \frac{c_k}{c_0}$ where $c_0$ is the varaiance and $c_k = \frac{1}{N}\...
0
votes
1answer
30 views
How can a network with only ReLU nodes output negative values?
I'm trying to use an api with a feedforward neural network for time series forecasting.
For dense aggregate data it works fine, but for sparse data it sometimes forecasts negative values, even though ...
2
votes
0answers
18 views
Can I use Survival Analyses if there are gaps?
I am interested to learn if it is possible to use a survival analyses approach when, in the middle of the study, there "gaps."
Specifics: does oiling a motor increase the "time until death" or ...
0
votes
1answer
12 views
Longitudinal panel data classification
My problem context specifically lies in churn modeling, where accounts have account-specific attributes (like industry, number of employees, etc), but also have longitudinal yearly data (product usage ...
0
votes
1answer
28 views
How to interpret autocorrelation plot?
I'm having trouble making sense out of this ACF plot
According to an ADF test, the series is definitely stationary. Also, the presence of autocorrelation is explained by the order 1 lag, as evidenced ...
0
votes
0answers
14 views
Finding when an external effect appears in time series using regression analysis
I have the 'seen' data (post views, PV) of different social media channels over a period of time and I want to see whether the effect of an external factor (EF, for instance, internet accessibility) ...
0
votes
1answer
18 views
Definition of forecasting period in time series
I am new to forecasting time series. The team that I am working with keep referring to forecasting period as lag. For example we have 20 month of data and we would like to create 5 month forecast. Is ...
0
votes
0answers
14 views
Standard Error in Auto correlated Data
I have time-series data generated via Metropolis algorithm - Monte Carlo simulations. Since these data must have some correlation between them, the formula of the standard error for IIDs variable must ...
0
votes
0answers
13 views
GAN for learning the transition density of a Markov process
I have learned about the Generative Adverserial Networks and the way they are used for learning the underlying (complex) distributions of high dimensional data.
Now, my question is: Are there ...
0
votes
0answers
26 views
+50
Pettitt's Test for Change-Point Detection Showing P-Value Larger than 1
I am studying how to use the pettitt.test function from the trend package in R to detect change-point in a time-series. However, ...
2
votes
1answer
35 views
Forecasting non-stationary time series using MLP
I noticed that in many tutorials with neural networks people difference their time series prior to training/forecasting.
Suppose that we have a window model with many autoregressive terms (say 365 ...
0
votes
0answers
16 views
Magnitude of non-ergodicity effect on the individual's risk of bankruptcy
Dr. Ole Peters presents the concept of (non-)ergodicity with the following gambling example:
You're given $\$100$ to play a game where you toss a coin once a minute. If it comes up heads, you win $50\...
0
votes
1answer
14 views
Manga translation updates: what kind of data/what model?
Long story short, I'm trying to predict how likely it is for a content creator to release new content or when they are most likely to do so (and possibly how this changes over time). My problem is ...
2
votes
0answers
15 views
How to understand a before-after effect in a longitudinal medical dataset
I am after some suggestions on what statistical analysis I can perform to show a before-and-after effect in a longitudinal electronic healthcare record (EHR). I have N number of EHRs, of varying sizes/...
-2
votes
0answers
8 views
Longitudinal UK voting data [on hold]
I am looking for longitudinal/panel data following the voting history of individuals in the UK electorate. Through the British Election Study and the UK Data Service I only seem to be able to find ...
2
votes
3answers
47 views
Exploring relation between time series
I have the below time series data:
I want to explore the relationship between dependent variable y and the independent variables x1 and x2. My aim is not forecasting. Just finding the relationship ...
0
votes
0answers
21 views
Other than out of sample error, are there any other ways of comparing goodness of fit of two models, when the models come from different families?
I'm asking this within the context of time series, but the question would apply to any regression type problem.
It usually specified that using information criteria like the AIC or the BIC to ...
1
vote
1answer
68 views
Time-series prediction with RNNs: What to expect from the learning process?
When training an RNN for time series prediction, what can one expect to see visually as the model learns? In particular, are plateaus a normal indication that the model is underfitting or do they ...
0
votes
1answer
21 views
Dealing with missing data in Time Series or non-constant time intervals for forecasting in R (ARIMA, Holt Winters, Theta)
I have a time series of sensor data from a machine. This machine is sometimes moved and thus there are big chunks of missing data, here is a plot of the data points:
My goal is to try to start ...
1
vote
1answer
28 views
Changepoint/Step Detection in Univariate Time Series
As a beginner to time series analysis, I'm trying to understand the best way of detecting the points at which my univariate time series shows a change in trend direction (see highlighted example).
I ...
0
votes
0answers
9 views
In R, using the Johansen test for cointegration, how do you know if you should use trend?
As the title, really. In my time series class, we only ever covered using using the option constant, and never trend. But now when playing around, I notice markedly different results. Ie, if I use ...
0
votes
0answers
16 views
Compare forecast interval between ARIMA and ARIMA/GARCH
I tried to compute parameters of ARIMA/GARCH in two step. The first one is to build ARIMA and then fit GARCH using iid Gaussian MLE estimation. The second one is to construct ARIMA/GARCH ...
-1
votes
0answers
27 views
Time Series data with both daily and monthly variables
I have daily data on how many people entered a certain shopping center, and the weather on that day. I wish to find out if there is a relation between the weather and the number of people who entered ...
2
votes
1answer
31 views
how can I make ARIMA more robust to outliers?
I have a very noisy time series like this and I forcast future values with auto.arima from the forecast package in R:
...
0
votes
0answers
4 views
Why is auto.arima modeling an AR(1) process as an MA(1)?
Playing around with auto.arima to see how effective it is at model selection. I first simulated an $AR(1)$ process with $X_{t+1} = 0.9 X_t + \epsilon_t$
...
-1
votes
0answers
46 views
Can AR models with a time trend be written as MA models
How could I prove that AR(1) model with time trend: $y_t = a_0 + a_1t + a_2y_{t-1} + e_t$ to be in the form of a MA model?
1
vote
0answers
25 views
Comparing time-series data for single day of week
Comparing time-series data for single day of week
I've been provided time-series data for customer wait time (seconds) taken at 5 minute intervals for 15 separate Tuesdays from this year (midnight to ...
0
votes
0answers
15 views
Derivation of a log-likelihood function for AR(1) process
The question is:
"Suposse that: y$_t$=$\beta$y$_t$$_-$$_1$+s$_t$e$_t$; e$_t$~N(0, $\sigma$$^2$)
s$_t$=exp{$\beta$y$_t$$_-$$_1$}
Derivate the log-likelihood function for y$_0$=0
Assume that $\sigma^2$...
1
vote
0answers
27 views
1
vote
1answer
22 views
In prediction, when should I use rolling windows vs. nonoverlapping ones?
Suppose I have daily time series data and I want to predict a month in advance using a set of features. I have lots of them so I'll be using regularized linear regression. To create the response I can ...
0
votes
0answers
11 views
How do I treat a seasonal timeseries to get a white noise autocorrelation plot?
I have a timeseries which is clearly seasonal and has trends. I would like to treat the data (e.g. differencing), to get a white noise autocorrelation plot.
Here is the autocorrelation plot for the ...
1
vote
1answer
28 views
Can I use a VAR in first differences despite having co-integrated data?
I have two variables. Both are I(1), so non-stationary in levels but stationary in first differences.
However, having run some tests, I find that both are co-integrated. Based on my statistics ...
1
vote
0answers
10 views
Using the Volume of Sales obtained today to predict volume of Sales at the Event
I wonder if anyone can help.
I have a set of data on event ticket sales. I have information on eventdate, location, capacity, cumulative sales, sales date, total sales.
I want to be able to build a ...
1
vote
1answer
31 views
+50
Testing Hypothesis with Time series and Location Data
I have Data on Prices of house. Along with these variables.
1) Location
i)Latitude-Longitude
ii)City and State
2) Attribute of house.
...
0
votes
1answer
26 views
how to determine Time Series Model? Additive Multiplicative?
I am new to time series Analysis, and I have noted that there's only two kind of models: Additive or multiplicative.
I want to know if there's other cases where we can find a combination of both.
For ...
0
votes
0answers
22 views
+50
How to approach SSM models for time series forecasting in general?
I have worked on SSM model using KFAS package (https://cran.r-project.org/web/packages/KFAS/KFAS.pdf) in R. Package suggests me to use one of the Box_Jenkins method to implement SSM. So we convert ...
1
vote
0answers
9 views
Data trend evaluation methods
I have conducted an experiment whose objective is to assess the collected data's patterns and to tell if the data is in general increasing or decreasing and, if possible, to compare the "trend" of two ...
0
votes
0answers
32 views
How to Split Time Series Data to train/test for RNN [duplicate]
Let's say I have a set of time series data with 32 time steps.
My goal is to predict what the data value would be for the next time step, given data for 30 previous time steps. Would it be okay to ...
0
votes
2answers
18 views
MAPE results for the 4-week post-sample period
I'm trying to get the same results reported in the paper Taylor, J.W. (2003) Short-term electricity demand forecasting using double seasonal exponential smoothing. Journal of the Operational Research ...
2
votes
1answer
80 views
How can I predict logistic model? [closed]
The data is like this.(of course, I have a more data)
...
1
vote
1answer
21 views
ACF and PACF seems to be pointing to two different processes
I have the following ACF and PACF plots for a time series. I'm very new to time series so I might be interpreting this wrong, but it seems like the ACF is indicating an MA(1) process because it tails ...
0
votes
0answers
15 views
Is AR(1) appropriate for measuring a specific pattern in my data?
I am analyzing time series data in which participants rated their thoughts in real time. I am trying to model the shape of the data.
Details on the time series (I have about 2,500 of these time ...
0
votes
1answer
19 views
How to understand the spectral measure for the spectral representation of a wide-sense stationary process?
Let {$a_n$} be a wide-sense stationary process and {$X_n$} be its spectral representation (discrete Fourier transformation? ).
Let $b_n$ be the covariance function of $X_n$.
According to the ...
