Questions tagged [forecasting]

Prediction of the future events. It is a special case of [prediction], in the context of [time-series].

1,244 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
2
votes
0answers
305 views

Constructing a forecast from bayesian multivariable regression

I've been working my way through Kruschke's Doing Bayesian Data Analysis, and have been able to successfully run a Bayesian multivariable regression using R code provided with the book. Kruschke's ...
2
votes
0answers
147 views

Transforming time series data before change point analysis in R

I have count data (non-financial) from 2010-2014 by week. I am interested in using R and changepoint package to find any significant points of time when the trend changed. I have two questions about ...
2
votes
0answers
62 views

What is the maximum time series data required for ARIMA and ANN modelling?

I have a per hour data in 1 year for a total of 8,640 observations. These data will be used to model ARIMA and ANN to predict a day-ahead forecast. My question is, is these data enough? or too much?
2
votes
3answers
861 views

Can simple exponential forecasting be used for a non stationary series?

I have a non stationary series with trend and seasonal components. I want to use simple exponential smoothing ONLY for forecasting. Does the series need to converted to stationary before using SES? If ...
2
votes
0answers
75 views

Why is the propriety of a scoring rule irrelevant for deterministic forecasts?

By deterministic forecasts Jolliffe (2008) has in mind forecasts to which no representation of uncertainty is attached. Jolliffe (2008) p26 provides a standard explanation of proper scoring rules, ...
2
votes
0answers
160 views

Calculating prediction interval on differentiated VAR(2)

I want to calculate the $l$ step ahead prediction interval of an VAR(2) on three series. Theses series are differentiated once before estimation of the VAR(2) model. I use the functions of the ...
2
votes
0answers
233 views

Poor electrical load forecasts from auto.arima, why?

I have 4 years electrical load data. I split the data into 3 years (75%) training data, 1 year for testing (25%). Also I have the temperature data for each day during the previous period. (The link to ...
2
votes
0answers
635 views

How to use these ACF and PACF plots for forecasting?

I have bi-weekly data for an event for which I am trying to build a forecasting model. When I plot the ACF and PACF, I get the following plots: From what I understand, the plots show that the data ...
2
votes
0answers
79 views

Forecasting seasonal components in X-13ARIMA-SEATS

Forecasting seasonal components is an important practical problem in finance, where products that are highly exposed to monthly seasonality in consumer prices are traded. For example, one can trade ...
2
votes
1answer
53 views

How to predict the risk of an event?

I'm working on a medical problem, where I want to analyze the effect of taking cholesterol medications on the occurrence of heart attack. Once a medication with a specific dosage is prescribed, it'll ...
2
votes
0answers
314 views

Forecasting multivariate time series data stream

I have a multivariate time series data stream. I am looking for a method that can forecast the next value of one of the variables as the data comes in. (It would be a major advantage if there's an R ...
2
votes
0answers
511 views

Time series cross-validation, calculate RMSE for different forecasting horizions

Following Rob J. Hyndman suggestions on how to do cross validation for time series ( http://robjhyndman.com/hyndsight/tscvexample/ ), I modified his original code to evaluate how RMSE (not MAE) ...
2
votes
0answers
974 views

Dynamic regression linear models in R

I have a question regarding Dynamic regression linear models. I wonder if it is possible to implement a MLR model (in R) using 'lm' and creating lagged values of predictors and dependent variables. ...
2
votes
0answers
177 views

How to improve a bad long-term forecasting of time series in common case

I have two time series $d_t(t)$, $d_c(t)$, where I'm modelling charge as a function of time. Lengths of time series, $N$ are equal to $101$ data points. For the $d_t(t)$ (test sample, short-term) the ...
2
votes
0answers
312 views

How to detect a relatively small level shift(leakage) in an hourly water flux time series in an area?

Background I'm working on a project which aims to use the history data about a water flux to detect whether there is a leakage happened. The data is hourly collected and among about 4 months. I've ...
2
votes
1answer
84 views

Predict (un)employment variables - very small dataset

I'm new to econometrics (familiar with ML, Python, Data Visualization). I really have no clear idea what model should I use in order to predict (un)employment variables for 2015-2016 (potentially 2020,...
2
votes
0answers
2k views

ARMA-GARCH forecast evaluation: in-sample, out-of-sample, rolling

I need to compare the forecasting ability of different specifications of the ARMA-GARCH model. I would like to compare the model by valuating for each model in-sample forecast and out-of-sample ...
2
votes
0answers
63 views

Predicting Influence of Price on Sales with Limited Stock

I'm trying to develop a model that predicts the volume of sales (either incremental for each day, or total at the end of a period) that factors in price, but I'm having some trouble working around ...
2
votes
0answers
81 views

Determining forecast error of realtime prediction of binary outcomes

Given datasets consisting of a daily prediction and confidence percentage for each of a small number of binary outcomes, what is the proper way to calculate the forecast error of each series and of ...
2
votes
0answers
298 views

Variance on Extreme Seasonal Time Series

I'm trying to come up with a decent method for forecasting a unique seasonal time series that is involving multiple periods of seasonality: Weekly, Monthly, Quarterly and I am stuck because I have ...
2
votes
1answer
150 views

Sequential semi-automatic model selection of time series forecasting

I have a number of univariate time series that I would like to incorporate in a production system. I have daily data from a month and I would like to forecast every day the corresponding values for ...
2
votes
0answers
48 views

Forecasting an individual based on a representative group

I’m trying to forecast demand for an individual based on historical data of many individuals, but I’m having trouble finding examples of this. For example: I want to forecast the demand for a single ...
2
votes
0answers
933 views

tbats with weekly, monthly and yearly seasonality not working

I am trying to predict values based on a dataset which may contain weekly, monthly and yearly seasonal data. To simplify things I am assuming that all months have four weeks (28 days) and the year has ...
2
votes
0answers
574 views

Does “level” in exponential smoothing stand for the “mean”?

In triple exponential smoothing it is said that there are estimates for 3 components: level, trend and seasonal. Does "level" here stand for "mean"? In single exponential smoothing is only the level ...
2
votes
0answers
290 views

How to create sklearn random forest model identical to R randomForest?

In R I usually define Random Forest as follows (an example): ...
2
votes
0answers
163 views

Prediction intervals for levels using a VAR model in second differences

Given a VAR model for the second differences of a vector time series, $\Delta^2 y$, how to obtain the one-step-ahead (and possibly $h$-step-ahead) prediction intervals for the series in levels, $y$? ...
2
votes
0answers
931 views

Time series data prediction with neural network model

I would like to predict stocks of a company for 6 months. I would like to use neural networks for this prediction. Can anyone suggest how many hidden layers and hidden nodes to be used? I have ...
2
votes
0answers
325 views

Confidence interval for sum of forecasts

I've got two time series, let's say X and Y. They are correlated. I can obtain forcast for X and for Y separatly (I'm using VAR model) and confidence intervals for them. Then I would like to make a ...
2
votes
0answers
1k views

R: Calculating prediction intervals (95%, seasonal naive and holt winters)

Could somebody explain to me the theory behind how R calculates the 95% prediction intervals for my 12 step ahead forecasts in (1) a seasonal naive model and (2) a Holt-Winters forecast. My code is ...
2
votes
0answers
64 views

Combining Forecasts: Best Information to Solicit from Forecasters?

Suppose Statistician $m=1$ produces a set of $h$-step-ahead point forecasts $\hat{x}_{t+h|t, 1}$ of $x_{t+h}$ where $x_{t+h} \in [0,1]$. Also, this point forecast could come with: a predictive ...
2
votes
0answers
511 views

auto.arima and DLM give different values for loglikelihood

I want to estimate an ARIMA model on my timeseries, then represent it in state space format, mainly because it will be more responsive to change in pattern. I used ...
2
votes
0answers
559 views

Online time series forecasting with DLM

I have estimated a univariate time series model, consisting of a random walk and an AR component. Now the goal is to make forecast about a couple of steps ahead as new data comes in, in an online ...
2
votes
0answers
93 views

Simple ways to forecast US GDP

Forecasting US GDP sure is hard, even the Fed's FRB/US gets it wrong. I am an undergrad doing a US GDP forecasting project, and was wondering if there were simpler ways to do so and produce decent ...
2
votes
0answers
256 views

How to extrapolate future probability density functions if you have a time series of them as input?

This is my current situation: I am given an observations vector $\textbf{X}$ of continuous variables with a time component $T$ (not equallly distanced). My supervisor approximates densities with ...
2
votes
0answers
366 views

Time Series using STS( Basic Structural Model)

I am using Basic Structs to forecast my time series. My forecast is exactly overlapping my data. I am sure no model can predict with 100% accuracy. I know I am missing something, can someone point me ...
2
votes
0answers
153 views

How to evaluate a Bayesian forecast?

Suppose that I have a predictive posterior, which is an attempt to predict some one-step ahead forecasted value $\hat{y}_{T+1}$. How do I assess if my posterior has done a good job or not? If we had ...
2
votes
0answers
4k views

Training/ Test Data with Time Series Model — Forecast with Training Model, or with Model based on Full Data?

Okay, I have a couple books on time series forecasting, but perhaps I need to read a couple more. Here's my question. You want to be able to validate a forecasting model. So you split the data into "...
2
votes
0answers
532 views

Forecast of spot electricity prices

I recently started a job in power trading. But due to a sudden change in employment I am required to work on econometric models to gauge the supply and demand side of national power markets. So ...
2
votes
0answers
5k views

auto.arima and Arima (forecast package)

I am facing a strange issue with the auto.arima() function. On a dataset named data, I run the following code ...
2
votes
0answers
727 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 ...
2
votes
0answers
279 views

Why only full ARIMA models in auto.arima?

It seems that the auto.arima function in the "forecast" package in R only considers full ARIMA models. By "full" I mean that if an AR lag $k$ is included, AR lag $j$...
2
votes
0answers
189 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 ...
2
votes
0answers
152 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
0answers
3k views

Forecasting using auto.arima

I have the weekly revenue data for an electronics company the decomposed plot of which is as follows: I have decided to keep the seasonality and apply a suitable forecasting technique. I tried auto....
2
votes
0answers
1k views

Forecasting call volumes over short intervals using R

I am trying to do a basic forecast of call volumes using the forecast library for R. I am not having too much trouble forecasting on a daily or monthly interval, however when I try to forecast on an ...
2
votes
0answers
3k views

Forecasting daily data with trend, yearly, day of the week, and moving holiday effects

I'm expanding a question I posed earlier because I think it was lacking detail. I'm attempting to forecast daily demand for a restaurant that sells take away food, primarily to office workers on ...
2
votes
0answers
303 views

are there any nonparametric forecasting methods?

Are there any good statistical non-parametric forecasting methods besides machine learning methods like neural networks/decision trees etc. for time series analysis ? If so, are there any R packages ...
2
votes
0answers
1k views

Overlap in time series training sets

I have a time series prediction problem where the aim is to forecast the average value of $y_t$ over the next $T$ periods, given all the information available up to point $t$. For example, I want to ...
2
votes
0answers
210 views

My prediction errors are correlated. Now what?

This is partly an R question and partly a stats question: I am trying to do batch forecasts using the auto.arima function from the forecast package. I have over 1000 items to forecast so doing it by ...
2
votes
0answers
1k views

Updating ARIMA model

My question is about updating the parameters of a regression with ARIMA errors model as new (monthly) data becomes available each month. Similar question were asked here before: Updating ARIMA ...

1
3 4
5
6 7
25