0
votes
0answers
36 views

How to implement a simple Bayesian Network for Time Series Data?

I'm a computer science grad student, with not much knowledge in Bayesian statistics, so I'm seeking for guidance for the simplest start. I have 10 variables, like demand, price etc. and I want to ...
0
votes
0answers
23 views

What is the source of nonstationarity in this VAR model?

I am trying to forecast a VAR model, which consists out of 5 variables with a monthly frequency. The problem is that the VAR model produces an unstable forecast and I am not sure what the source of ...
1
vote
1answer
61 views

ARIMAX with a specified nonlinear model using the arima function in R

I am interested in fitting an ARIMAX model using R. As known, ARIMAX can be understood as a composition of ARIMA models and regression models with exogenous (independent) variables. I have a time ...
0
votes
2answers
53 views

What's the minimum sample size required to do a time series analysis?

I'd like to know the minimum number of monthly data points required to do time series analysis with the seasonality effect in forecasting. I read some articles & they were saying that 50 or 60 ...
1
vote
0answers
23 views

Predicting Y from a regression model for dY

I have some time series data where I'm modelling temperature as a function of various predictors. On physical grounds, I can expect that $$\frac{dT}{dt} \propto T_a - T$$ where $T_a$ is the ambient ...
1
vote
2answers
44 views

Time series with autoregressive error

How can I in R fit a time series, $x_t$, with external regressors, $v_t$, and an autoregressive error? This time series model is given as follows, $x_t = \beta v_t + \epsilon_t$ where $\epsilon_t = ...
2
votes
1answer
46 views

How to build a function with the result of auto.arima in R?

I use: fit = auto.arima(Y, xreg=X) in R to get ARIMA(1,0,0), result as follows: ...
0
votes
0answers
25 views

How much training data is enough for seasonal time series forecast

I am new to times series forecast. If I have data(single variable and timestamp) with double seasonality periods, which are 288 and 1056. And I use tbats in R to build time series data and then ...
1
vote
2answers
118 views

very high frequency time series analysis (seconds) and Forecasting (Python/R)

I have high frequency data (observations separated by seconds), which I'd like to analyse and eventually forecast short-term periods (1/5/10/15/60 min ahead) using ARIMA models. My whole data set is ...
0
votes
0answers
19 views

How to simulate a structural break time series? [migrated]

I want to know how to simulate the following structural break autoregressive time series: $\begin{cases} Y_t = 0.9Y_{t-1}+\epsilon_t & \text{for }1\le t< 50\\ Y_t = ...
0
votes
0answers
15 views

updating a forecasting model including the new observed data with the historical data

I want to have a one week ahead forecast for my data which includes a four years of daily historic data (three years are used as train set and the 4th year is used as the test set). I can use three ...
1
vote
1answer
142 views

What if the trend is changed?

I want to forecast tourist arrivals using time series analysis. I expected to use monthly data from 2000-2013. But due to the civil war, the trend was changed after 2008 as in the following plot. ...
0
votes
1answer
24 views

Very different Neural Network test errors for same architecture

So I'm doing a time series prediction, and assessing the capability of the ANN to predict that time series. I am using Matlab's neural network toolbox functions, and the training parameters are the ...
1
vote
1answer
31 views

Is it reasonable to use a combination of two forecasting models for a dataset?

I used tbats to fit a model for a 3 years of historic data and the values work fine but as I did not include holidays, holiday predictions are really off. I used arima with regressor (holidays at ...
0
votes
0answers
89 views

Obtaining the SarimaX equation from the arima coefficients

I have a SarimaX model with three regressor variables: ...
1
vote
1answer
44 views

How can one say if a model is poor based on RMSE value

I have a general question about the value of using RMSE to see if a forecasting model is poor. I used the forecast package in R to find forecasting models for ...
0
votes
0answers
24 views

prediction for data including weekly and annually seasonality and dummy variables for holidays

I have a three years of daily data for number of orders a trucking company receives everyday. Number of orders are high during weekdays and they have a huge decrease for weekend. I used msts to ...
1
vote
1answer
42 views

prediction using historic data with unusual annual trends

I have 4 years of daily data. there is a decreasing trend for the data for the first 3 years but the trend increase for the 4th year. I wanted to find a fitted model using the first 3 years and then ...
1
vote
2answers
252 views

Wrong predictions for weekend, but good predictions for weekdays

I have a set of 3 years of daily data. I saw weekly and annual seasonality in the data so I used msts time series and tbats ...
1
vote
1answer
73 views

Time series forecasting accuracy measures: MAPE and MASE

We come to this toy example showing MAPE and MASE are not consistent when measuring forecasting accuracy. Data consist of 100 white noise and 100 $AR(1)$ time series with length $N=500$, mean $\mu=1$ ...
1
vote
0answers
68 views

Stock closing price forecasting using ARIMA model in R

I have downloaded the daily stock Adjusted Close price of one stock from sep 2011 to till date. As per my study plan, I have plotted some basic plots to understand the daily stock Adjusted closing ...
0
votes
1answer
27 views

Data with weekly and annually seasonality but the first day in time series is not the begining of a week

I know it might look naive but I have a very basic question. I have a three years of historic data which has weekly and annual seasonality. January first as my first data is on Wednesday so my time ...
3
votes
1answer
53 views

Difference between the forecast and simulate functions in the {forecast} package in R

I have been using the forecast package in R to make forecasts based on an ARIMA model and have noticed a difference in the output of the forecast and simulate functions when calculating confidence ...
1
vote
1answer
45 views

No fitted ARIMA model

I wanted to fit an ARIMA model to a daily database for three years but auto.arima couldn't find a model and showed the following error: ...
2
votes
1answer
112 views

Forecasting a seasonal time series in R

Forecasting airline passengers seasonal time series using auto arima Hi, I am trying to model some airline data in an attempt to provide an accurate monthly forecast for June-December this year using ...
0
votes
0answers
17 views

what is the best prediction interval for a forecasting model with daily and annually seasonalitis?

If we have a data set which has daily and annually seasonality, is it reasonable to use the forecasting model for one year ahead? I mean, I want to have a 48 hours forecast for a logistic provider ...
0
votes
0answers
32 views

Creating auto arima for two following time series with two different non linear slopes

I'm trying to model (and predict) the following time series, which consist of two periods (enrollment period and non enrollment) as the following: I believe that this model should consist of two ...
0
votes
0answers
22 views

What does a fitted value mean in dshw forecasting package?

I have a double seasonal data. I wrote the following code to find the best fit model and find fitted values: orders <- read.csv("DataForR.csv", header = TRUE), NumOrders <- orders$Orders, ...
1
vote
1answer
48 views

Transforming a time series with a negative number

I have been given data to forecast however it has a negative figure within the data which then, when doing a log transformation to make the series stationary, the ARIMA script i have written won't ...
1
vote
0answers
33 views

ARIMAX model or ARDL?

I would like to study the impact the advertising of a product on its sales (weekly data for 5 years). As the final aim is to forecast what would be the impact on sales of a change in the advertising ...
1
vote
1answer
35 views

prediction of polls

Just as an example Scotland has poll to decide whether they need to be independent from UK or not. Here is BBC's summary of different polls: ...
0
votes
4answers
208 views

Forecast accuracy calculation

We are using STL (R implementation) for forecasting time series data. Every day we run daily forecasts. We would like to compare forecast values with real values and identify average deviation. For ...
2
votes
1answer
59 views

standard errors of the fitted values of a time series regression

I really want to understand how the math is working here. I am trying to get the standard error of the fitted values for a time series regression model.In the non-time series regression,I know I can ...
3
votes
3answers
69 views

Transforming time series to compensate for change in variance

I have a time series (shown below) that comes from a sensor whose calibration was changed in the middle of last year. As part of this change, the sensor's reading of the variance (or volatility) of ...
0
votes
0answers
51 views

Four tricky time series questions with a “seasonal twist”

A ski-hotel has the most guests in the third quarter in every year (check the data below after the four questions). Can you answer these four questions (every year has 4 values, the first is quarter ...
0
votes
0answers
37 views

Reproducing ARIMA error terms

When forecasting a moving average (MA) model using R's forecast, why does using residuals(fit) produce different results than ...
0
votes
0answers
29 views

Time series Data Analysis and Forecasting by country and time factor

cty year qtr tl Argentina 2009 Q4 3 Argentina 2010 Q1 2 Argentina 2010 Q2 7 Argentina 2010 Q3 7 Argentina 2010 Q4 10 Argentina 2011 Q1 7 Argentina 2011 Q2 7 Argentina 2011 Q3 1 Argentina 2011 ...
1
vote
0answers
19 views

Ensemble model performs better with worse performing consitutent models?

I have a forecast model I am developing that uses some very unreliable input data, missing data (due to sensors or comms failures) is the rule, not an exception. The quantity being forecast is a daily ...
2
votes
2answers
91 views

Which forecasting method for load profiles

I'm new to this forum and I'm quite new to forecasting. Currently I'm trying to learn the basics about exponential smoothing, ARIMA etc. Now I want to forecast the total energy consumption of a rather ...
0
votes
0answers
29 views

Techniques to forecast discrete events in a time series?

I'm currently looking at time series data for patients who have been admitted to a hospital. The time series itself models risk probabilities, where high risks are marked by peaks. At various points ...
0
votes
0answers
23 views

What is the procedure to compare two different period time series

I am currently working on the task that I would like to compare two different period time series like Sales in 2012 vs Sales in 2013. Kindly suggest me any statistical procedure.
0
votes
0answers
21 views

Forecasting ar(p) for several counties

I have a data set of prices, these prices vary across time and across area. I have 18 areas with 32 time periods. What i want to do is forecast these prices, i have found that a AR(3) process fits ...
0
votes
0answers
41 views

Obtaining the Psi Weights of a seasonal ARIMA in R

I am trying to quantify the effect of a future random shocks on my seasonal ARIMA model. If I have understood the theory correctly, the easiest way is to express my seasonal ARIMA model in its "random ...
0
votes
1answer
67 views

Standard techniques for forecasting revenue growth of a company?

I was curious what sort of time series models were the standard for doing this type of analysis. I have weekly sales data for the company - I could cook up my own time series model but would like to ...
0
votes
0answers
21 views

training period selection forecast (error analysis)

I have been lately testing the best training period length to perform a forecast. I have tested it for various days of training period length, among them 60 days and 30 days. My methodology is quite ...
0
votes
0answers
32 views

Statistical Methods for Calculating Vending Machine Refill

Am looking into statics to help support a project I am undertaking. The project scope concerns intelligent replenishment / refill of vending machines. During an onsite service, a technician must ...
0
votes
0answers
68 views

Arima model - multi step forecast

The following code shows a forecast of the next 24 hours of my electricity prices with two exogenous variables. My problem is, that I don't know how to build a forecast for the next 3 days or more ...
0
votes
0answers
51 views

Forecasting time series with missing data and irregular intervals

I have a data set of medical drug stock levels at health centres and I want to forecast monthly consumption over the following 3-6 months. However about 30%-40% of the data is missing and some of the ...
0
votes
1answer
38 views

MAPE is high for daily sale prediction

I have daily sales data from 2011 to 2013. I have to do prediction for 2014.I have used arima and exponential method to predict the daily sale, but it is not giving the better result. MAPE is around ...
0
votes
0answers
51 views

Forecasting agricultural commodity prices with R

I would like to create a predictive model in order to forecast the price of an agricultural raw material. I got time series for the prices and the production of this raw material, and also for the ...