# Tagged Questions

Time series are data observed over time (either in continuous time or at discrete time periods).

17 views

### SARIMA model on original (unstable variability) or transformed (stabilized) series?

If my series requires a log-transformation to stabilize variability, do I apply the sarima function to the log-transformed series or the original series? Does the ...
22 views

### How to bootstrap to get probability of reaching a value or greater? [closed]

I am trying to bootstrap in order to estimate the probability of reaching a certain value (or greater) reaching 1.3568 or a higher value based on the data. I am attempting bootstrapping as a method to ...
46 views

### Missing data imputation in time series in R

I have got hourly temperature data from 2012 to 2016 as follows: ...
20 views

### Questions concerning GARCH modelling in R (mean equation, forecast evaluation) [duplicate]

I apologise, if these question are trivial, but I am currently trying to estimate a family of GARCH models for a selection of return series as part of an undergraduate project for which I am having to ...
43 views

### Dickey-Fuller unit root test with no trend and supressed constant in Stata

I have seen in several papers that the $p$-value for the Dickey-Fuller (DF) test is reported for the test including trend and constant, then without the trend, and in the end in the absence of both. ...
17 views

### ACF does not support ADF conclusion

I have 2 stocks price series : Below are the two price series and their ACF respectively. ...
43 views

### Time series decomposition results interpretation

I have a long multi-seasonal time series, and the stl() decomposition got me this: The remainder is definitely not white noise. Then what should be the next step ...
7 views

### Select an interval/subset of multi-seasonal time series data in R [migrated]

I have half hourly data from 2011-01-01 to 2016-06-27 and I would like to use the data before 2016-06 as my training data, and the remaining be my test data. Currently I used a very silly methods, but ...
21 views

### Defining overlapping periods

I have a dataset containing the abundance of migrating bird species. In the figure below you can see that there are two "bell" shapes that are overlapping somewhere around September. One of the bell ...
11 views

### Converting annual series into quarterly series using MARSS in R? [closed]

I am trying to generate quarterly values for a series which is available in annual frequency using two other series using MARSS package in R. ...
34 views

### explanation of a timeseries bootstrap to a layperson

I am trying to explain the output of a time-series bootstrap to someone who knows nothing about them. I recently learned about them myself and wanted to make sure my explanation was correct. Is this ...
22 views

### approximate probability of price change over time

Given a set of prices (X) where X is on hourly intervals, How would I estimate the likelihood of X reaching price Y within 50 hours? Note that X is financial data, thus (I believe) applying a normal ...
13 views

### Prediction of multiple time series with classification

I have multiple time series of air passenger demand with specific classification data. Data looks like this (some rows may lack some data): ...
34 views

### How to forecast from VECM (in R)?

I am interested in forecasting with a vector error correction model (VECM). I am facing a problem of not being able to transform a cointegrated series into a VECM model using the stationary series. ...
28 views

### Forecasting ARIMA with predict vs forecast in R [closed]

Data consisting of 30 values is stored in a time series time. After applying ARIMA modelling on time, I used ...
26 views

### How do I replicate the Time Series Momentum effect using freely available CME Futures Data? [closed]

I am attempting to replicate Figure 1 from Moskowitz et al. (2012) in R using freely available futures data from the Chicago Mercantile Exchange (CME). The code loads futures data, calculates ...
19 views

### Support Vector Classifier - Opposite Classification

I'm using a support vector machine (SVC from the SKLearn library in Python) to classify some time series data, aiming to predict the severity of injury to babies. A rough summary of the method is ...
11 views

### How to test the significance of long term effect coefficient

I have a time-series model like this: $y_t=\alpha+\beta_0 y_{t-1} + β_1 r_{t-1} + x_t' β_2 + \epsilon_t$ in order to get the long term effect, I use $β_1^*=\frac{β_1}{1-β_0}$ to measure, this is ...
18 views

### How to determine correct changepoints from Posterior Probabilities (bcp R package)?

I am using the bcp package in R to determine change points in a time series. The output that this package gives is a distribution of posterior probabilities. As far as I can understand, the peak ...
19 views

### Techniques to forecast demand from a transaction log

Suppose we have a log file of transactions. Which, have at least the variables: Customer, Product, ...
27 views

### What is the difference between ARMA+Fourier and TBATS model?

I am just wondering that, in terms of the multi-seasonal time series forecast, what is the difference between using auto.arima find the ARMA order, then fit <...
9 views

### Appropriate method for sequence clustering of customer journey data

I have a large amount of customer journey data in the form of inbound contacts. That means, for each customer I have all the inbound contacts, be it calls, emails or anything else with a time stamp. I ...
25 views

### Order of ARMA models

Why we usually do not exceed ARMA(5,5) models in practice? Is there any mathematical justification for this?
53 views

### Seasonal plot for time series with multiple seasonalities

My data is like the following, half hourly multi-seasonal time series from 2011 to 2016. ...
19 views

### Weights in Loess

I have a good working knowledge of how the loess model works but am curious as to how weights work in conjunction with the model. Obviously, this method weights locally, but many statistical packages (...
21 views

### Interpreting BATS model information using forecast package in R

I have a forecast object in R. When I look at the summary I can see 'Model Information: BATS(1, {1,1}, -, -)' What do these numbers in the parentheses stand for?
30 views

### A (simple) example where LSTM works but a regular Neural Network (NN) fails?

In the spirit of the answer from maple on this thread: Using RNN (LSTM) for predicting the timeseries vectors (Theano) I created some simple sine wave data to fit with a LSTM. It worked well! ...
6 views

### What statistical test should be used to compare two independent samples over time (pre- and post-test) for binomial variables?

A typical question is: Do you have a paid job? 1 Yes 2 No I have a treatment group and a comparison group (not matched--in fact they're quite different from each other) and I'd like to statistically ...
21 views

### Random Forest for time series

I am learning about random forest approaches and was wondering if it is suitable for multiple time series all used to predict the same response variable. For example, three different methods to ...