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
7 views

Morgan-Granger-Newbold test only under squared error loss

I've read about the Morgan-Granger-Newbold test but per this explanation (page 4), "the test is valid as a test of equality of forecast accuracy only under squared error loss". What exactly does this ...
5
votes
0answers
26 views

Multivariant time series in R. How to find lagged correlation and build model for forecasting

I'm new in the page and pretty new in statistics and R. I'm working on a project for college with the objective of finding the correlation between rain and water flow level in rivers. Once the ...
1
vote
2answers
63 views

How to produce the minimum forecast error using R?

Considering that we want to use optimize() on the interval [0,1] how can I write an R code for finding the value of β that produces the minimum forecast error without using external packages like ...
0
votes
2answers
35 views

Is there any tool that can do Vector ARIMA modeling in time series

Vector ARIMA model is used in multiple time series analysis. I am just wondering if there is any software or tool can be used to build the model. Some tools,like R, can only be used to predict the ...
1
vote
1answer
35 views

Using results of regression on raw observation values to approximate results of regression on relative change between observations (Simple, Linear)

this is my first time on Stack Exchange so if I did something wrong please tell me. I have a time series dataset. There is an observation $(y,x)$ for each continuous time $t$. Let’s say for each day ...
0
votes
1answer
32 views

Sum of squared errors [duplicate]

Why do we use SSE (the sum of squared errors) in calculations. Why do not we use the sum of errors? Could you explain please?
0
votes
0answers
9 views

Model selection and parameter estimation in forecasting with a Dynamic Linear Model

I am implementing a general purpose prediction tool for time series. I want to tolerate missing values, so I decided to settle for DLMs. To make it as relevant as possible on a large number of ...
0
votes
0answers
16 views

How to compare forecasting methods: based on ARIMA and curve fitting?

I'm making a project connected with identifying the dynamics of sales. My database concerns 26 weeks (so equally in 26 time-series observations) after launching the product. I want to make forecast ...
0
votes
1answer
16 views

Converting SAS EWMA code to Python

I have the following SAS code that uses PROC FORECAST that I would like to replicated with the Python Pandas pandas.stats.moments.ewma ...
1
vote
1answer
39 views

Strange results in Holt forecast

I am trying to understand what could be causing these strange values to appear on applying a Holt model to a vector. The data represents actual sales of an item. ...
0
votes
1answer
21 views

nnetar return negative forecast values

I am confused about using nnetar. All my training time series data are positive numbers, but the forecast results obtained from ...
0
votes
0answers
44 views

What is the difference between forecasting based on ARIMA and logistic curve? R

I'm making a project connected with identifying the dynamics of sales. My database concerns 26 weeks (so equally in 26 time-series observations) after launching the product. This is what my database ...
1
vote
1answer
66 views

Forecasting with holiday dummy variables

I have an example of call center data for 2013. There are 261 days of data (excluding weekends). For 2013, I have included a holiday dummy variable (holiday) for ...
0
votes
0answers
15 views

Wavelets with forecast model

I am new to wavelets decomposition technique and am trying to use it with time series model. What I use now is that use discrete wavelet transform. I use Daubechies with 4 as mother wavelet with ...
1
vote
0answers
35 views

Forecasting and auto-correlation [duplicate]

I'm reading this chapter forecasting principles and practise from a forecasting book. The author has explained a linear regression model. Now this linear regression model will definitely have some ...
1
vote
1answer
34 views

What time series model should be used?

Given the following daily time series data I have used auto.arima in R to build a model. I used freq = 5 because the data is collected only on weekdays (Monday ...
2
votes
2answers
110 views

Special method for forecasting on time-series clusters in R?

I'm doing a project related to identifying sales dynamics. My database contains 26 weeks after launching the product (so 26 time-series observations equally spaced in time). I used two methods ...
1
vote
3answers
161 views

Developing an appropriate time series model to predict sales based on past month record

I have been operating an online business for two years in a row now, so I have my monthly sales data for about two years. My business for every month is certainly affected by seasonal swing ( performs ...
0
votes
1answer
34 views

Want to make a function which allows for recursive window forecasting

I have been looking for a function that can make recursive window out-of-sample forecasts, but seems there is none. So I'm thinking about about making a function that can be used for recursive window ...
0
votes
1answer
31 views

Constant forecasts in SPSS

I have weekly data for the last four years. I am using SPSS to do forecasting. I am getting a constant value in the forecast period. What could be the reason behind it? Is it due to defining weekly ...
1
vote
1answer
20 views

Characterizing relationship between two datasets

I have two data sets of electricity prices in a given region, one with data at 5 minute intervals and one with just the hourly values (which are almost, but not quite, averages of the 5 minute values ...
0
votes
0answers
28 views

Time series forecasting using genetic algorithms

I am a beginner in the field of forecasting. I wish to know which are the best tools that can be used for forecasting future values in a time series using genetic algorithms. Are there any tools in ...
1
vote
1answer
51 views

Suggest models for prediction based on small sample data

I am not a traditional statistics guy. I am from an electrical engineering background. So, spare me for lack of jargon. The model is to be used for predicting agricultural output based on previous ...
0
votes
0answers
24 views

(R) Automatically calculate optimized Arima(p, d , q) value [migrated]

I'm developing automatic forecast Software with JAVA & R. The following steps are used in R to forecast next 18 values: ...
0
votes
0answers
25 views

Forecast mean and variance for group data

Apologies if this is a bit of a simple question, but I haven't been able to find any answer to this over the past week and it's driving me crazy. Background Info: I have a dataset that tracks the ...
0
votes
0answers
7 views

Chow forecast test

I have a question about the chow forecast test. I don't understand how you can proof this test. You have: (y_1;y_2)=(X_1 0; X_2 I_(n2))(B;y)+(e_1;e_2) and H_0 is equal to y=0. The restricted is equal ...
0
votes
0answers
38 views

Forecasting daily electricity price

I'm trying to make a model to forecast the electricity price, a time series model with R and i have some questions Our data are daily price of the past 3 years from north pool countries, and we are ...
0
votes
0answers
15 views

Which method(s) for forecasting time series of event durations

I have the $N$ individuals each observed for $T$ days. For each individual I have some basic demographic data. Each $n$ individual, during the observed time $T_n$ may experience event $E$ which is ...
0
votes
0answers
38 views

over estimating ARIMA model

When an ARIMA model over estimates, i.e if the forecast from the model is always higher than the actual value, what's the cause? The model i used was SARIMA (1,1,0)x(1,0,0). Below is the time series ...
2
votes
0answers
26 views

Sales forecasting to account for regression

I have a very beginner question. I am attempting to forecast total 2014 unit sales of a large number of products. The data I have has 10 points for each individual product, which are the total unit ...
1
vote
1answer
64 views

Is it abnormal that out-of-sample fit is better than in-sample?

I'm using Eureqa, as machine learning tool to fit a formula to my data. I found out that the formula fits my test data better than my training data! Is this abnormal?
0
votes
1answer
95 views

R time-series forecasting with neural network, auto.arima and ets

I've heard a bit about using neural networks to forecast time series. How can I compare, which method for forecasting my time-series (daily retail data) is better: auto.arima(x), ets(x) or ...
1
vote
0answers
124 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 ...
1
vote
0answers
24 views

Daily Sales Data - Week Days Only, No Holidays

I'm trying to predict the daily sales for a take out restaurant. They are located in the downtown core of a large city. Their primary customers are office workers on their lunch breaks, and as such ...
1
vote
1answer
183 views

Time series forecasting using R

I have many time series(retail data). Some with trends, some seasonal, and some with neither. With period day, week or month. I need to make forecast, for each time serie. I'm looking for the most ...
2
votes
1answer
65 views

Forecasting irregular time series (with R)

There are several methods to make forecasts of equidistant time series (e.g. Holt-Winters, ARIMA, ...). However I am currently working on the following irregular spaced data set, which has a varying ...
0
votes
0answers
20 views

R: One period our cross validation with time series

I have quarterly data with one causal variable (X) and one dependent variable (Y). 30 such observations. I have the X variable for a quarter, and I'm seeking to predict that quarter's Y. The ...
1
vote
0answers
7 views

Joint vs. marginal prediction intervals for path forecasts (with k-family wise error rate)

I am trying to become comfortable with the bootstrapping of joint prediction regions described in this paper: http://www.nccr-finrisk.uzh.ch/media/pdf/wp/WP748_A3.pdf This calculates the prediction ...
0
votes
0answers
84 views

Short term road traffic forecast modeling using neural networks toolbox in matlab

I have a hourly time series data of road traffic (i.e. count of the number of vehicles passing on a particular segment of road) collected over 7 days a week (Mon to Sun) for two weeks starting from 9 ...
1
vote
0answers
71 views

Time series modeling with R on weekly data

I am trying to do time series modeling and forecasting using R based on weekly data like below - ...
0
votes
1answer
39 views

Why are fitted values different from one-step ahead forecasts?

Let's say I fit an ARIMA model on a time series up to date t. I want to forecast the 10 next values without refitting the model but also using the latest data available for each date. So forecast ...
0
votes
0answers
35 views

Dynamic regression and Panel Models

Would I use the same type of multiple regression approach to build a forecast model for sales in one region as I would if I wanted to forecast sales in 5 regions. I was told that I should use an ARIMA ...
0
votes
0answers
33 views

fpp forecasting using AWS ubuntu

Is the package fpp (or any of its previous incarnations like forecast) supported in Ubuntu 12.04 using AWS? It is the only package that R downloads but when you load the library it throws an error. ...
0
votes
1answer
42 views

NIST exponential smoothing formula

I am trying to relate data and results in NIST website with the formula defined in previous page from the same website. But I am missing something here: Does initial trend & season indices ...
4
votes
1answer
99 views

Holt-Winters exponential smoothing formula

I am trying to implement Holt-Winters exponential smoothing in Java program (I understand that R and Python have implementations of these algorithms, but I can't use those due to other reasons, so ...
1
vote
1answer
73 views

How to get the true mean forecast using the Arima package with a Box-Cox transformation

In the Arima package, using a Box-Cox transformation give wrong results when later applied to the forecast method. For example, consider this data: ...
0
votes
0answers
18 views

Covariances between forecasts from different time-series models

I'm trying to compute the variance of an average of forecasts. But I'm not sure on how to get the covariances required to compute the variances. Here is the situation: Three ARMA(p,q) models for a ...
1
vote
1answer
33 views

Autoregressive moving average or feed-forward neural network

When we have to make a forecast, the books tell us that the main method is the autoregressive moving average model. In my opinion there is another big tool, the feed forward neural network (FFNN). So ...
1
vote
0answers
33 views

Using fitted ARIMA model to forecast new time series

I'm new to ARIMA analysis and I'm trying to understand how fitted ARIMA model can be used to forecast new time series, given starting point only. Should the model be refitted or the estimated ...