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

learn more… | top users | synonyms

2
votes
1answer
88 views
+50

Fourier transform and the multivariate normal

I am wondering about how to specify multivariate normal distributions for vectors that have undergone a Fourier transform. For instance: Say we have the mean vector $\boldsymbol{\mu}$ and covariance ...
3
votes
3answers
31 views

Statistical test for increasing incidence of a rare event

I have following simulated data of 2500 persons regarding the incidence of a rare disease over 20 years ...
6
votes
4answers
282 views

Why does the variance of the Random walk increase?

The random walk that is defined as $Y_{t} = Y_{t-1} + e_t$, where $e_t$ is white noise. Denotes that the current position is the sum of the previous position + an unpredicted term. You can prove that ...
2
votes
1answer
66 views

How can I recreate a Weibull distribution given mean and standard deviation and the shape and scale parameters are unknown?

Figure 2 is a Weibull distribution of three different wind farms in Canada. These 3 probability distributions were combined in a study to obtain a common wind speed model. I will be using this common ...
1
vote
1answer
102 views

Time series with correlated observations: How to start analysis?

We have a time series dataset: Daily arrivals of asylum seekers. Goal is to model this variable. In particular we would like to attempt Arima modeling and/or fitting a distribution. Before we get to ...
0
votes
0answers
15 views

Poisson vs. Gaussian in Geomagnetic Data

I've been studying geomagnetic signals using a threshold approach to detect pulse events in the data. The question here is what is the significance of the crossover of stddev and mean as the ...
0
votes
0answers
29 views

How to test whether a random walk have a upward or downward trend

I have applied Kalman Filtering Method to get the estimates for time-varying coefficients (using DLM package in R). The model is like $S_{t} = \alpha_t * A_t + \beta_t * W_t + \gamma_t * A_t * W_t + ...
2
votes
1answer
51 views

Identification of navigation pattern (lapping, pacing, random and direct) from X,Y co-ordinate in known physical layout

I have X, Y and Z co-ordinate of the movement patterns of a person for 30 days over some known physical layout. This is unevenly spaced time-series data with maximum frequency of 2Hz while in motion. ...
0
votes
2answers
18 views

Detrending a series that moves about zero

How can I avoid my de-trending model from blowing up? Do I need an additive model rather than a multiplicative model? If so, is there anything I would consequently need to take into account? Can I ...
0
votes
0answers
6 views

Coherence vs. Magnitude Squared Coherence

Currently I am writing my master thesis. The theory part is about the turbulent wind field generation, where the coherence (not magnitude squared) is used: $$\text{coh}(f) = ...
0
votes
0answers
7 views

Mixed effects model for repeated measures to test for factors that are either constant or dynamic within an individual over time

I am dealing with a rather complicated dataset with repeated measures of the same individuals at various time points (samples were collected at different time points and different number of samples ...
0
votes
1answer
20 views

Simulation of time series with R [on hold]

I'm new on time series. I'm trying to solve an exercise on the simulation of an ARMA process. The problem is the following: Generate 100 simulations, each with n=60 elements of an ARMA(1,2) process ...
0
votes
1answer
14 views

non-invertible weakly stationary AR processes

ok, so I know (for example) that $X_t = 2X_{t-1} + e_t$ for iid $e_t$ is stationary. But how do I go about proving the condition $Cov(X_r, X_s) = Cov(X_{r+t}, X_{s+t})$ for all integer $r, s, t$ ...
0
votes
0answers
6 views

Package ‘JPSurv’ - Trends in incidence rates [on hold]

Has anyone ever used the JPSurv package in R to look at trends in incidence rates? The original software put out by the NIH - Joinpoint - is not compatible with my computer (a macintosh) and so I ...
0
votes
1answer
29 views

How can i predict data just for specific days in R? [on hold]

I would like to know how to estimate data in specific period of time in R. for example, in my problem i should estimate data from 26th October 2005 to 31st October 2005 in monitoring station and I ...
0
votes
0answers
11 views

Difference between clipped time series, PRBS, PN sequence and their application in signal processing

A real valued time series can be converted into binary series through the process of clipping. Clipping, or hard limiting, a time series is transforming a real valued time series Y into a binary ...
-2
votes
0answers
21 views

Help¡ How do I solve this problem time series? Subject: Geophysical time series [on hold]

A problem of interest in the analysis of geophysical time series, involves a simple model for observed data containing a signal and a reflected version of the signal with unknown amplification ...
0
votes
0answers
8 views

Can I run an SVM on sparse temporal data without a regular time interval?

I have data of occurrences with timestamps that could be days or months apart. I'd like to enter the values natively as follows. Are there any SVM algorithms that can support such an input? day 1: ...
1
vote
3answers
3k views

Time series: one I(1) and one I(0) variable, should I use VAR/VEC, test for cointegration?

Like the title says, I've got two time series, one is stationary to begin with and thus has no unit root, the other time serie is stationary after one-time differencing. I want to create a model out ...
0
votes
1answer
343 views

Handling stationarity issues in proc ucm/state space time series models

Hope I'm able to find someone who can answer this question. The previous one didn't get answered! Proc ucm is the SAS implementation (using state space concepts) to isolate the unobserved trend, ...
3
votes
1answer
163 views

Using a rolling window in time series regression

I am learning about regression. I have done some cross sectional regressions which are fine. I recently did a simple time series regression. So I have a y & x vectors each containing 1000 ...
0
votes
0answers
16 views

Evaluating correlation of 2 time series

I did some research on this website and I found a few questions about correlation between 2 time series. However, all of them end-up with cross-correlation as answer, which is not really what I want. ...
0
votes
0answers
14 views

Vector Autoregressive Model: residual's kurtosis proportional to number of lags?

I have some transformed data set (windspeeds that are nearly-weibull-distributed). I transformed this data which results in near-normal distribution (close to no excess kurtosis and skewness of zero). ...
0
votes
0answers
21 views

How to choose which test to use to determine if a time series is non stationary?

I want to determine if my time series is non stationary. I looked many articles and have learned there is not just one formula - ADF. It seems you must use some series of tests and assumptions. But I ...
1
vote
1answer
74 views

Using monthly product usage data to predict customer churn

I've been reading tons of papers detailing methods on predicting customer attrition, but none of them have mentioned using product usage data over time. We keep detailed logs of how many times User A ...
1
vote
1answer
26 views

How to detect variable seasonality pattern

We have predicted and actual (daily) data for past 3 years. We use 90 days of data for prediction. Generally our predictions are very accurate, but we receive unusual traffic for few days/weeks ( like ...
4
votes
2answers
53 views

Analyze trend given a set of points

Suppose I have a set of N values representing EUR/USD rate... [ 1.10 , 1.20 , 1.25, 1.20, 1.19 ] Which is the simplest way for analyzing if values tend to raise or tend to fall? I'm looking for a ...
0
votes
0answers
13 views

What techniques infer dependencies between time series?

I'm working on an ML project. We have an app where users can track 1) binary variables and 2) quantities over time on a scale from one to ten. For example, at a given time they may track whether they ...
0
votes
1answer
14 views

How do I perform a Wald Test with multivariate Granger Causality Analysis

I am doing a Granger Causality Analysis for three economic variables (GDP, CO2 emissions and Total Energy Consumption) of Puerto Rico. I am using a Toda-Yamamoto Procedure implemented in R R. I am ...
0
votes
0answers
16 views

What does the sigma^2 figure mean when fitting a model to a time series in R?

I have a time series in R, and I am using the arima function to fit it to a SARIMA model. I would like to use the parameters it returns to write the time series equation by hand, but in order to do ...
0
votes
0answers
10 views

Prerequisites for time series and ARIMA

I am working on forecasting sales for 2016. The details of the problem is: 2014 - sales happened only between Jan-Apr 2015 - Sales happened only between Jan-Apr The sales in rest 8 months of the ...
0
votes
1answer
87 views

How to approach time series regression with monthly dependent variable and quarterly independent variables

I am building a regression model where my goal is to obtain a monthly forecast of the dependent variable for the next 2 years. I have a monthly historical series available. For my independent ...
2
votes
1answer
208 views

Forecasting model inputs that are both auto-correlated and are calibrated over time?

How does one account for model inputs that are both a) auto-correlated and b) calibrated over time? I'm interested in forecasting the outcomes of sporting events. Let's say that each team has a score ...
0
votes
0answers
19 views

What is the best way to extract time-series shared by two variables?

I have one dependent and several independent variables. I want to extract the time-series of the independent variable that is shared with the dependent variable. In other words, I want to extract only ...
0
votes
0answers
14 views

Covariance of ARMA (2,1)

I am preparing for an exam and need help. Consider the following estimated ARMA(2,1) model, y(t) = 0,05 + 0,83y(t-1) + 0,13y(t-2)- 0,15e(t-1) + e(t): Given the unconditional variance and 1st order ...
0
votes
0answers
7 views

Correlation computing time series data of unequal sample size

I am working on a computing a correlation between two variables X and Y. Both are time series and were recorded during the same period. 6/25/15. However X was recorded much more often than Y. ...
0
votes
0answers
10 views

Which time series model to use?

Hi I have a large data set of objects, each containing a list of the same attributes. The data is arranged in a time series so that the value for an attribute for an object is indexed by its time. ...
1
vote
1answer
23 views

Time series analysis with known outliers

Let's say I have a time series of site usage data that I would like to analyze. The data is for people visiting my site, with a known seasonality that I can easily calculate, but in addition, there ...
1
vote
0answers
7 views

Touch times to authenticate user

for a project I gathered touch data of different users when they tap a rhythm repeatedly on the touch screen in a game. ...
1
vote
0answers
19 views

Transfer function of pure ARMA time series model

Is it theoretically justifiable to calculate/use the transfer function of a pure ARMA model? I would like to be able to use the transfer function representation to put the state equations into their ...
1
vote
1answer
21 views

Which is the best way to check (with some certainty) if the mean of a time series is a constant?

I am testing the time series output by a light sensor, and trying to know when dawn and dusk end. I used a cusum test to check when light level starts changing, and now I need to know when it ...
0
votes
0answers
6 views

X11 deseasoning: too few datapoint for S3x3 moving average?

Do I have too few data points to use a $S_{3\times3}$ moving average? I have the following dataset for January months, ...
1
vote
2answers
181 views

Does it make sense to use dynamic time warping when clustering time series that all have the same length and sampling interval?

Comparing Euclidean distances with dynamic time warping (DTW): Will Euclidean distance perform better than DTW when clustering time series that all have the same length and sampling interval? Are ...
0
votes
0answers
51 views

Marketing Data with many zeros

I am working on a marketing data which is a time series data with marketing spend done through different channels and revenue generated. The data looks like this : My data contains too many zeros ...
2
votes
1answer
127 views

How can I test and quantify the change in distribution over multiple years?

I have a data set of energy usage values taken every half hour for a year, for four years. How can I test for, and quantify, an improvement (i.e. decrease) in energy usage, per-year? I have initially ...
2
votes
1answer
30 views

Do we need to detrend when do Cross-Correlation between two time series?

I have a group of time series variables and I want to found out the relationship among them. The method I use is to calculate pair-wise correlation between two time series and found out those with ...
0
votes
0answers
8 views

Deciding the lag while testing for timeseries data stationarity

I am currently reading up on time series forecasting using ARIMA in SAS. I just began to go through what has been explained here : ...
1
vote
2answers
36 views

AR(2) model is causal

AR(2) model is : $$X_t=\phi_1X_{t-1}+\phi_2X_{t-2}+W_t$$ Where $W_t\sim N(o,\sigma^2)$ I want to prove AR(2) model is causal . So , I tried as : $$X_t-\phi_1X_{t-1}-\phi_2X_{t-2}=W_t$$ ...
1
vote
1answer
35 views

Dealing with nonstationarity and autocorrelation

Relationship between interest rates and retail sales. I have a time series sample of quarterly data for 10 years. My dependent variable is retail prices and independent variables are interest rates, ...
0
votes
0answers
20 views

Getting an error message “Error in if(reached.threshold < min.reached.threshold)…” while training network using neuralnet package

I'm using R to create train and test a neural network on a time series (the annual sales of a company over a large period of time). As using the package's default learning algorithm (resilient ...