Forecasting involves estimating the value or distribution of a random variable which has not yet been observed.

learn more… | top users | synonyms (1)

0
votes
0answers
3 views

forecasting with ratio

i have daily data about revenue and number of push notification sends. I am trying to predict revenue/sends by day. there is a day of week effect also and days may have different sends. For example ...
0
votes
0answers
8 views

Interpretation of Regression coefficient

I have 5 variable regression equation. If I added any constant (Fix value, say 100) in all the observation of variable A, another (Or same) fix value in variable B. While rest of three variables are ...
0
votes
0answers
11 views

Forecasting: Exponential Smoothing overfitting

I have a 7 week time series(49 days) and I am told to forecast the next 2 weeks. One approach of mine is to use ets function (of package...
-1
votes
0answers
9 views
0
votes
0answers
18 views

Optim error training ARIMA model in R [duplicate]

I have the code below which trains ARIMA models for a range of order combinations. I'm getting the error below in the step training the ARIMA models. The code worked just fine with the ...
0
votes
0answers
13 views

Estimating the distribution of the mean of a sum of AR time-series

So my problem is this: I am trying to model a population based on a sum of populations. For example, lets say this was the United States Population. I have data for the last 5 years about populations ...
0
votes
0answers
19 views

MAPE vs. MAE for forecast evaluation [duplicate]

If you are trying to judge how well a forecasted model is doing, say like the rolling forecast example from Hyndman's blog, is MAPE a better choice than MAE? Are there reasons to chose mape or mae ...
0
votes
0answers
10 views

Adversarial sequential learning with a linear model

I have a problem with the following characteristics: The value of an observation is a function of its predictors The nature of the relationship between value and predictors changes slowly over time ...
0
votes
2answers
32 views

R auto.arima with intervention: intervention only affects one point

I have a model fitted with auto.arima, the model is ARIMA(0,1,0)x(0,1,0)[6] with seasonal period 6. The data is bi-monthly so there is an annual seasonality. There ...
0
votes
0answers
13 views

Forecast package Prediction Horizon issue in R [migrated]

I am new to R. I was trying to predict using holt method but getting this strange error. I am using forecast package V-7.1 with R (version 3.2.5) and Rstudio (Version 0.99.896). I reinstall all from R ...
2
votes
0answers
12 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 ...
1
vote
0answers
23 views

How to interpret daily vs. hourly “% chance of rain” precipitation forecasts?

Looking at the National Weather Service forecast for daytime precipitation tomorrow, it shows a 70% chance of rain ("showers likely"). I interpret this as meaning that on average it will rain 7 out of ...
2
votes
1answer
21 views

How to calculate consensus of probabilistic forecasts?

Suppose a group of forecasters each made a probabilistic forecast, for example: Forecaster 1: 40% probability that company ABC will add 2 - 3 million subscribers 20% probability 3 - 4 million ...
4
votes
1answer
42 views

How to measure probabilistic forecast accuracy?

Suppose I make a bunch of probabilistic forecasts like: 70% probability that sales growth will be 10-15% in Q1, 10% probability that sales growth will be > 15%, 20% probability that sales growth ...
3
votes
1answer
26 views

Single prediction vs. summing more granular n-step ahead predictions

Say I want to predict the total rainfall for the next 365 days based on a set of predictors and daily historical observations. I could build a model that predicts annual rainfall and make a single ...
0
votes
0answers
15 views

Spss statistics [on hold]

am working on forecasting time series data (of bandwidth utilization across 85 markets)using spss statistics. Can anyone please tell me how to work on it.How auto correlation option in spss statistics ...
0
votes
0answers
6 views

Forecasting techniques for appliance industry [on hold]

How to calculate sales forecast in push environment? Appliance industry. What are the independent variables/factors i have to consider?
0
votes
0answers
16 views

What is Ideal Point Error (IPE)?

I am working on a rainfall forecasting study where I aim to compare my results against observed values or any other model. I have been asked to develop a new performance measurement which is Ideal ...
0
votes
0answers
15 views

Reg-Arima fitted estimates more flexible than forecast

I am fitting a regression model with ARMA errors, and comparing its fitted and forecasted values with a linear regression. I am wondering why a reg-ARMA appears to have a much better fitted estimate ...
2
votes
0answers
49 views

Is it possible to do a time series analysis with more than one explanatory variable?

I am working on a project, and I am absolutely new to forecasting and not so strong in statistics. I have an employee data for the last 7 years, along with the other variables like economic growth, ...
2
votes
0answers
61 views

Random forest for forecasting univariate time series

I read few articles on random forest and its implementation in various fields. But I hardly found any literature on its implementation on forecasting univariate time series. Can it be used for ...
3
votes
1answer
26 views

Selecting ARIMA Order using Rolling Forecast

I'm wondering if a rolling forecast technique like the ones mentioned in Rob Hyndman's blogs, and the example below, could be used to select the order for an ARIMA model? In the examples I've looked ...
0
votes
0answers
13 views

Forecasting with ARIMA in Stata 12 [closed]

How to forecast with ARIMA model using the pop-up dialogue in Stata?
1
vote
1answer
28 views

Historical data appears seasonal, but forecasts from auto.arima are linear

I am surprised how often the auto.arima function from the "forecast" package in R returns straight linear forecasts when there appears to be fairly strong ...
1
vote
1answer
24 views

Rolling Forecast Re-training Step Concept

I'm trying to understand the steps in Rob Hyndman's Multi-step forecasts without re-estimation example below. I'm wondering what the purpose is of ...
0
votes
0answers
45 views

Bayesian Time Series model in R

Similar to the scenario described in this paper, I need to forecast a seasonal time series with only a few periods. I am working with about 2 years of daily revenue data, and I want to forecast the ...
1
vote
0answers
29 views

Forecast accuracy metric for forecasts over different time horizons

I a dataset of 81 oil price forecasts from more than 30 different forecasters. Those forecasts consist of a forecast made on various days in 2014 for the average oil spot price of 2015. For instance, ...
0
votes
0answers
5 views

Forecasting Call Center Wait time with Unknown Staff Levels

I am trying to forecast the median wait time each hour for a customer to get served in a call center. I know the median wait times each hour and the number of customers who called in each hour ...
0
votes
1answer
45 views

Incorporating autocorrelation into forecasts

I have a time series $x_{t}$ which is an AR(1) process with a constant term, e.g. $ x_{t} = c + \phi x_{t-1} + \epsilon_{t} $ How can I incorporate information about the autocorrelation of $x_{t}$ ...
0
votes
0answers
14 views

How define node input backpropagation for time series data prediction

i'd like to ask about the method to determine the number of nodes in input layer back-propagation architecture. i got confused to devide my time series data into variabel independent (nodes in input ...
0
votes
1answer
17 views

Rolling forecasts: training versus forecast accuracy evaluation

Questions: Are rolling forecast examples (like the ones below) only useful for evaluating a model's accuracy, or can a rolling forecast be used to train a model? Are models trained using a rolling ...
0
votes
1answer
26 views

Question about rolling forecast horizon

I'm trying to understand how the rolling forecast example below from Rob Hyndman's blog works. In the final line of the for loop, is ...
1
vote
1answer
39 views

Are rolling forecasts more accurate that full-sample forecasts?

I compared the auto.arima forecast checkts below to the rolling forecast fc and noticed ...
0
votes
0answers
17 views

Time Series Modelling With Two (or more) Periodic Components

I'm trying to create a model to predict hourly electricity usage. Looking at the data, it appears that there are three different components that I'm going to want to capture in my model. First, there ...
0
votes
0answers
11 views

Time-series forecasting for a 1 year data of monthly data points

I am working on a project where I am required to build a time series forecasting model for forecasting the monthly sales of a company. However, the sample size I have is only for a single year which ...
1
vote
1answer
22 views

Very different prediction intervals from ARIMA models where MA order differs by 1

I have fit an ARIMA model to a time series with function auto.arima from "forecast" package in R. I wanted to check prediction intervals for robustness by changing ...
4
votes
1answer
42 views

Forecasting GDP using regression, ARIMA and ETS

I am building a simple model that estimates future change in GDP growth using change in working-age population (%). $$ \Delta GDP_t = \beta_0 + \beta_1 \Delta Pop_{t-1} + \varepsilon_t. $$ I have ...
1
vote
1answer
44 views

Standard data set for testing and comparing forecasting algorithms

What standard data sets are used for testing, evaluating and comparing forecasting algorithms? For example, if you're reviewing a paper that describes a new forecasting algorithm, what data set would ...
0
votes
0answers
7 views

Rolling Hourly Forecast Error [migrated]

When I try to run the code below, I'm getting the following error: Error in Ops.POSIXt(driftmod$coeff[2], time(x)) : '*' not defined for "POSIXt" objects I ...
1
vote
1answer
39 views

Algorithm for weather prediction

I am trying to build a weather prediction app using c#. I am not a stats major and i am trying to understand which simple algorithm can be used to predict temperature and rain fall. I have gathered ...
0
votes
0answers
46 views

Time Series Analysis vs Linear Regression for GDP data?

I am trying to build a simple econometrics model that uses urban population, total factor productivity among other things to predict future GDP of a country. First I approached the problem by using ...
1
vote
0answers
8 views

UK population and NHS spending projections

Say I want to make some projection about the size of the UK population 25 years from now and consider the impact of this population growth on national health spending. Is the following approach ...
2
votes
1answer
41 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 ...
2
votes
0answers
24 views

Holt-Winters vs. comparison to history

I have a timeseries with daily and weekly seasonality that I want to check for anomalies (on data as it comes in live). I could use Holt-Winters forecasting, or I could just compare the data with the ...
0
votes
0answers
6 views

Forecasting Adjusted Time Based Cohort Values Based on Variance

I'm trying to forecast the distribution of sales for a three week cohort with adjustments for the remaining weeks made from the past weeks results. The basic approach would be to adjust the next weeks ...
0
votes
1answer
29 views

Prediction interval, forecast error for a function of a forecast

I have two variables $X$ and $Y$. For each variable I created a forecasting model (using time series) and estimated $X_{t+1}$ and $Y_{t+1}$ and the prediction interval and the error for each. I have ...
0
votes
2answers
18 views

Holt-Winters for Imputation

I have found Holt-Winters seasonal method a very decent method for forecast, specifically for cases where more recent observations are more representative of the near future. The method equally sounds ...
0
votes
0answers
10 views

In Recurrent Neural Network for time series forecasting, what should i take the historic values in test data set?

I am using recurrent neural network to forecast on a time series data. For the test data set, what should I take as the historic lag values y(t−5,t−4,...,t) as I don't have those in test data set. ...
1
vote
0answers
10 views

Detecting Frequency in Noisy Data

I have some very noisy data that seems like it might have a frequency to it. I'm trying to build a model with the data, like the example code below. So I've been experimenting with fourier series ...
0
votes
0answers
23 views

When performing a monthly forecast with regression, can you use serial date numbers that take account the no of days in the month?

For example, take the financial year 2010/11. Should I represent each month as: 1 2 3 4 5 6 7 8 9 10 11 12 ... or ... 40269 40299 40330 40360 40391 40422 40452 40483 40513 40544 40575 40603 Would ...