Tagged Questions

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

learn more… | top users | synonyms

0
votes
0answers
4 views

Cointegration - Why can't I estimate a VAR on the differences?

When talking about variables that are I(1) (the first difference is stationary), Lutkepohl book says: "...in general, a VAR process with cointegrated variables does not admit a pure VAR representation ...
1
vote
1answer
27 views

What are the implications of estimating a covariance matrix from a correlated sample?

Given a sample of $n$ independent observations $x_1,...,x_n$ (where $x_i$ are $p$-dimensional column vectors), the $p \times p$ sample covariance matrix is defined as ...
2
votes
1answer
38 views

Time Series Function - Constant vs Piecewise

I have daily data for online marketing $ spend and the number of clicks to the website gained. I want to determine a function that 'maps' the two together. I cannot use normal linear regression ...
1
vote
0answers
20 views

Fit a VAR model with R

I have a bivariate time series z_t where z_1t is the change in monthly US treasury bills (maturity 3 months) and z_2t the inflation rate,in percentage, of the U.S. monthly consumer price index ...
0
votes
0answers
17 views

ARIMA model in R vs S+ [on hold]

I want to use ARIMA model. I use both S+ and R but I don't know which is better. What are your suggestions on using R or S+ package for time series analysis and ARIMA model?
0
votes
0answers
15 views

Calculating euclidian distace among z-score values

First of all I should say I'm from a biological domain. I'm trying to cluster web visitors based on the time they spent on each web page. Let's suppose my raw data set is in the following ...
1
vote
1answer
54 views

Definition and proof of Strict Stationarity

The definition of strict stationarity I'm using is the following: $(X_1,...,X_n)=^d(X_{1+h},...,X_{n+h})$, for any integer h, and positive integer n. I'm trying to prove that ...
1
vote
1answer
52 views

What are some useful robust and scalable approaches towards anomaly detection of a time series data?

What are some useful robust and scalable approaches/methods towards anomaly detection of a time series data? I am mainly looking for some practical approaches carried out using Python, R, Java, etc. ...
0
votes
0answers
10 views

Correlation index for correlating high volume of timeseries

Is there any way to pre-build some "correlation index" and save it to DB for any given timeseries. For example: ...
0
votes
0answers
34 views

Should I use stationarity test before OLS regression

I need to know if conducting a stationarity test on the variables, such as the Dickey-Fuller test, is important before doing any regression like OLS? if so, if the variable is stationary after ...
0
votes
0answers
17 views

Time series forecasting with multiple series with constraints

Hello and thanks in advance. I am using ARIMA or VAR models to forecast sales revenue. Suppose I have three different time series in each of three categories (making 9 series in total). The first ...
0
votes
0answers
13 views

Infer significance (in trends) in time-series data

I got a dataset with multiple time variables (i.e. 21 fixed measurement times). It is expected that a (downward) trend over time can be discerned in these variables. When plotting scatterplots I find ...
3
votes
2answers
22 views

What is the main idea behind the power spectrum?

Assume that we have a time series and we have calculate the corresponding auto-covariance function. Having the auto-covariance function we can calculate the corresponding power spectrum and having the ...
0
votes
0answers
5 views

Daily time series forecasting by item in R? [migrated]

I have a collection of sales data by item in this format ...
-2
votes
0answers
17 views

Forecasting in R X Axis [migrated]

Good day How do I change the x axis so that it shows the year and month? At the moment the x axis doesn't look right and comes up with 2014.0, 2014.5 and 2015.0. I want to use the forecast package ...
2
votes
1answer
42 views

Asymptotic distribution of a recursive statistic

I have a (time series related) test statistic which is asymptotically normal. I would like to know what is the asymptotic distribution of its maximal value obtained by a recursive estimation. For ...
0
votes
2answers
45 views

What is the purpose of Leads and Lags in a time series?

I will analyse stock prices and i don't understand the purpose of leading and lagging. can you please suggest me some preliminary analysis on the stock prices also, this will help me for my thesis.. ...
0
votes
0answers
24 views

clustering analysis of large amount of time series

I would like to cluster a set of time series, which are composed of around 50000 different time series. Are there established algorithms/package that can handle this scalability problem?
1
vote
2answers
102 views

Determine when time-series should be logged (or any other transformation) and applied automatically

Is there any way to test whether a series should be logged or transformed in another way? I have a code of which i use to run lots of different data through to forecast. Some of the data definitely ...
0
votes
1answer
28 views

AR(2) & constant & trend - very poor constant estimates?

Here is a problem that was puzzling me. Suppose I simulate the AR(2) process with constant and trend using the code below (I apologize for inefficiency and inelegance - the aim was to get job done at ...
2
votes
1answer
52 views

Confusing Holt-Winters parameters

I have got a model for forecasting using holt-winters. However the parameters confuse me... The parameters show that there is no trend or seasonality even though there is definite trend and ...
3
votes
3answers
139 views

How do I handle nonexistent or missing data?

I tried a forecasting method and want to check if my method is correct or not. My study is comparing different kinds of mutual funds. I want to use the GCC index as a benchmark for one of them but ...
0
votes
0answers
17 views

how could i handle with missing data or non existent data? [duplicate]

i tried a forecasting method and i want to check if it is correct or not and why? my study is about evaluating mutual funds for two kind of them it is a comparative study and i wan to use gcc index ...
1
vote
0answers
32 views

Regression model for predicting life expectancy

I have average life expectancy at birth data for an 8 year period and I would like to use that 8 year period to predict the trend for average life expectancy for the next 5 years. I would then like to ...
1
vote
1answer
51 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
14 views

Statistical Significance of Turnaround Time

My laboratory recently implemented MALDI-TOF MS for identification of gram negative rods in blood cultures. I collected data retrospectively from laboratory reports comparing the time from isolation ...
0
votes
0answers
17 views

What is the Fourier Transform of a brownian motion?

I looked into this article http://en.wikipedia.org/wiki/Brownian_noise and it says that: If we have a brownian motion $W(t) = \int _{0}^{t} dW(s)$, then given that the spectral density of white noise ...
0
votes
2answers
66 views

How to prove that the Fourier Transform of white noise is flat?

If we take $X_n$ a series a random vector with its components each having a probability distribution with zero mean and finite variance, and are statistically independent. How do we prove that the ...
1
vote
0answers
5 views

Method to estimate times of individual impulses from composite response

I have a detector that registers a sequence of "hits" over a period of time. Each hit produces a signal that has the approximate form ...
3
votes
1answer
20 views

Significant autocorrelation in time series decomposition random component

I'm very new to time series analysis. The data below represents about 8 years of aggregate daily visitors to some tourist attractions. I'm trying to examine the random component of some time series ...
2
votes
0answers
41 views

Detecting a trend to increase, in a time series, in real time

Probably, someone who's into technical analysis of share prices eats stuff like this for breakfast. Me, I couldn't devise a theoretically acceptable approach. I have this thing (private working set, ...
0
votes
0answers
21 views

Adding predictor variables and/ or systematic judgement to time series forecasts

I have a ways to go with my forecasting general education --- but I'm doing a seasonal time-series forecast for predicting sales order volumes. It's mostly software sales, which does have a ...
0
votes
0answers
17 views

Early stopping methods for ANN applied to series prediction

Could anyone give advice or links to advice on early stopping methods for ANN trained with back prop applied to time series prediction? I know some methods for classification tasks but don't the ...
1
vote
1answer
43 views

Peak Hours for Tweeting

I am trying to figure out the peak hours during a 24 hour period for my companies twitter account. We are trying to find the sweet spot to optimize our interactions (RT+Replies+Favorites). I have ...
1
vote
2answers
49 views

Time Series Anomaly Detection with Python

I need to implement anomaly detection on several time-series datasets. I've never done this before and was hoping for some advice. I'm very comfortable with python, so I would prefer the solution be ...
2
votes
0answers
25 views

Why does glmnet in caret give different predictions for different alphas even though lambda is zero?

In R, when using caret to train an elastic net regularization model, I find that different values of alpha give different predictions when the lambda parameter equals zero. This should not be the ...
0
votes
0answers
38 views

Test for autocorrelation

I wanted to test if there's significant autocorrelation in my data. Here's the reproducible code(R!) and the result. It looks like that dwtest and bgtest and acf are all too much different. Can ...
1
vote
0answers
25 views

Does the density of daily data impact forecast accuracy?

I know it might be trivial but does the density of daily values impact the forecast accuracy? For example, if a call center receives less than 50 calls for weekdays and less than 10 calls for weekend, ...
1
vote
0answers
33 views

mixed results for stationarity tests and structural breaks

Following situation: I want to forecast a time series of the number of trucks on the motorway in some country. Here how the regular week looks like: I have data for 4 years and divide the huge time ...
3
votes
0answers
18 views

Correlation on ordered subset

Imagine a hypothetical scenario in which a ball is thrown along a straight line. During flight, the position is continually sampled; however, at some distance, the sampling fails and only noise is ...
0
votes
1answer
33 views

Multiple regression model

I have a multiple regression equation which as four quarters (maybe called them as parameters) ...
0
votes
0answers
19 views

“Iterating”? For MA and AR processes

I am not sure what is being done here, but I keep seeing statements like Given $X_t - \phi X_{t-1} = Z_t$ $...(1)$ then $$X_t = -\phi^{-1}Z_{t+1} + \phi^{-1}X_{t+1}$$ $$ = ... $$ $$= ...
1
vote
0answers
22 views

Statistical test: Does actual time series data deviate from forecast?

I have made a prediction of future sales based on an ARIMA model. The ARIMA model is based on past data, during which there has been no marketing activity. During the period predicted by ARIMA, I will ...
2
votes
0answers
32 views

“Frequency” value for seconds/minutes intervals data in R

I'm using R(3.1.1), and ARIMA models for forecasting. I would like to know what should be the "frequency" parameter, which is assigned in the ts() function, if im ...
0
votes
0answers
11 views

Finding ACVF and two random variables

let $X_t = 0.5X_{t-1} + Z_t$ where $Z_t$ ~ $ WN(0,\sigma^2)$ I want to find the ACVF of both $X_t$ and $Z_t$, but I am a little bit confused. Say for $X_t$ $$\gamma(h) = Cov(0.5X_{t-1} + Z_t, ...
1
vote
1answer
18 views

How to construct appropriately reverting geometric AR(1) process?

Suppose I have a mean-reverting AR(1) type process, $X_{t+1} = X_t + \theta(\mu - X_t) + \epsilon_t$ where $\theta > 0 $ and $\mathrm{Var}(\epsilon_t) = \sigma^2$. This process is clearly ...
0
votes
0answers
32 views

Determine the causes of change in time with mixed models

I have a database with several continuous variables measured in two times. I searched for a change in time in my dependent variables in this way: ...
0
votes
0answers
25 views

Organizing data using time series multivariate regression?

I am trying to understand how I can organize the following data since none of what I learned in my undergrad econometrics course works. I am running out of ideas. I am trying to measure how the ...
0
votes
0answers
17 views

standardization within time series and across groups (nested data)

I read through the previous threads concerning standardization of variables, but unfortunately have not found an answer whether it is justifiable or necessary to z-standardize values across groups ...
1
vote
1answer
37 views

Stochastic Volatility Model

In Kim et al. (1998) stochastic volatility model is specified as: $y_t=\beta\exp({\frac{h_t}{2}})\varepsilon_t,\quad t\geqslant1$ $h_{t+1}=\mu+\phi(h_t-\mu)+\sigma_\eta\eta_t$ $h_1\sim ...