Questions tagged [forecasting]
Prediction of the future events. It is a special case of [prediction], in the context of [time-series].
1
vote
1answer
12 views
Asymmetric error measure for forecasts
I am building a model for forecasting some number of activations. My data set has a panel structure.
Now, I want to come up with a forecast performance measure to assess the performance of my model ...
0
votes
0answers
20 views
ARIMA forecast looks lagged
I am trying to make forecast of some time series that are both non-stationary and seasonal.
The overall result looks quite good. However, I constantly see a lag (or even a bias) between the observed ...
1
vote
1answer
17 views
Forecasting using Trend and seasonality
Im new here, also a newbie in statistics.
I was told to do forecasting at work by my boss.
I used to do a naive forecasting before, and i want that to change.
I want to do a real world forecast using ...
0
votes
0answers
49 views
Daily data, R forecasts only yield straight line?
I've tried ets, tbats, and arima - I can't seem to get anything but a straight line out of this.
Example I tried:
...
2
votes
2answers
50 views
Which ARIMA model do I have to select?
I have monthly data since 1990 to January 2019 and I need to make a forecast of the next 6 months so I use a sample of the past ten years(I used a sample of the last ten years due to my job ...
0
votes
0answers
12 views
Conjoint Analysis and Demand Estimation
I have a) part wise utilities from conjoint analysis done in a survey(each demand driver as attribute) and b) demand estimation for our product in future. How can we link both these?
Basically how ...
0
votes
1answer
30 views
Maximum number of Fourier terms in forecast package
I am using the forecast package in R to get some Fourier components - namely, function fourier(ts, K, ..). For a time series <...
0
votes
0answers
17 views
Demand Estimation without data [on hold]
I have a very interesting problem. Our client, a major theme park company wants to set up a park in an asian city. They want to a) understand the total demand to the park every week for the future ...
0
votes
0answers
13 views
Specific data formatting techniques for discontiguous time series? [on hold]
I'm facing a predicting problem for food alerts. The goal is to predict the variables of the most probable alert in the next x days (also any information I could get about future alerts is really ...
3
votes
1answer
32 views
Predictability of a time series
Say we are given a time series $(x_t)_{t \in P}$ where $P$ is the index set of past observations (train set).
Imagine that we have built a model for our data and now want to assess predictability of ...
2
votes
1answer
31 views
Principles behind time-series forecasting intervals
So, this is truly a bit of a general question, but I am not aware of the guiding principles (if there are any) behind forecasting intervals. For whatever time-series model one might be using, whether ...
1
vote
1answer
43 views
ARIMAX - predict
I have the monthly number of patients in a psychiatric facility from Jan 2010 to Dec 2018 - the data shows a seasonal pattern. I want to forecast the number of patients in the facility from Jan 2019 ...
1
vote
1answer
43 views
How to fit a stepwise regression with ARIMA errors using Arima function in R?
I am fitting a regression model with ARIMA errors in R using the Arima function from the ...
1
vote
0answers
23 views
Forecasts are at a different level to base in hts/combinef forecast
I am forecasting a multi-level hierarchy of smoothed series using the hts forecasting package. Some series have forecasts at significantly different levels to the input series.
As pictured below, ...
0
votes
0answers
16 views
Observation Operator - Data Assimilation
In data assimilation, one assumes the existence of a observation operator $\mathcal{H}$ that maps the model-state vector $\bf{x_b}$ to $
\bf{y_b}$ (the model-equivalent of the observations $\bf{y_o}$) ...
0
votes
0answers
35 views
Which are the benefits of using ARIMA vs LSTM for time series forecasting? [duplicate]
I have already read this question: https://datascience.stackexchange.com/questions/12721/time-series-prediction-using-arima-vs-lstm
but I want to know in which circumstances is better ARIMA and in ...
4
votes
1answer
126 views
Strategies for predicting 100 binary choices given the previous 100
Background
As an experimental psychologist, I've long had an interest in binary decision-making tasks. Typically, in such a task, I manipulate a few properties of some hypothetical or real decision, ...
0
votes
0answers
18 views
Historical average with exponential smoothing model [duplicate]
This topic similar with this one
R Time Series Analysis forecast result always remains same
But I perfrom exponential smoothing model in R.
...
0
votes
1answer
16 views
How to calculate price prediction model accuracy from metrics such as MAE and MSE
I am new to both statistics and machine learning in general. I've tried to construct a price prediction model using the RNN-LSTM architecture. For this problem I have a dataset of one-minute closing ...
1
vote
1answer
25 views
AIC values for auto.arima [closed]
I have a problem with identifying why auto.arima suggest specific coefficients. I have time series with multiple seasonalities and I am trying to forecast future values using STL+ARIMA. I have been ...
0
votes
0answers
18 views
With omitted variables is OLS estimator still the best linear predictor?
Suppose the true model is
$$y = \beta_0 + \beta_1 x_1 + \beta_2 x_2 + \epsilon$$
where $x_1$ and $x_2$ are correlated and $\epsilon$ is white noise. I omit variable $x_2$ and apply OLS to estimate
$...
0
votes
0answers
16 views
Prediction intervals for THieF
I would like to add prediction intervals to a temporal aggregation using the thief package.
Can someone point out either how to automatically plot prediction ...
0
votes
0answers
14 views
Calculating probability of voting results from small sample aize
2 million people voted in a poll for their favourite song. 35,000 votes have been counted so far, of which:
575 votes are for Song A
466 votes are for Song B
393 votes are for Song C
(And the ...
3
votes
1answer
217 views
Which estimation technique minimizes the MAPE?
Suppose we have two estimation techniques:
Linear Least Squares, which aims to minimize squared residuals
Least Absolute Deviation, which aims to minimize absolute residuals
We have a model, which ...
2
votes
2answers
52 views
Forecasting the number of visitors in each hotel in a city
I am looking for some suggestion on what a good approach would be for the following forecasting problem.
Problem statement: There are 100 hotels in a city and I have the monthly data on the total ...
1
vote
2answers
85 views
machine learning algorithms (Xgb, LSTM, others) for time series forecasting
I have seen many kernels that are using machine learning algorithms (Xgb, LSTM, others) on time series forecasting.
A time series data typically has trend and seasonal components.
In general my ...
0
votes
0answers
14 views
Out-of-sample predictive checks for Bayesian TVP models
Comparatively new to Bayesian econometrics so apologies if this is a silly question.
I am running a time-varying parameter regression where the parameters are estimated as in Primiceri (2005). My ...
4
votes
2answers
109 views
How to study auto-correlation of time series when shocks are present?
The time series I want to model has several shocks due to law changes. Basically, I do not have a lot of data that isn't impacted by these shocks/shifts/pulses. Now, I want to study the ACF and PACF ...
3
votes
0answers
43 views
Time series model for demand forecasting?
I have a time series $Y_t$ (example:university applications received in a certain month) which I want to forecast. I have another time series $X_t$ and I know that $Y_t$ is related to past lags of $...
0
votes
0answers
11 views
How to choose the best parameter for the LINEX loss function?
I am using a LINEX loss function to evaluate my forecast. What procedure should I follow to find the best $\alpha$ parameter?
LINEX function: $$L(e) = \exp(\alpha e) - \alpha e - 1$$
Where $e$ is the ...
0
votes
0answers
45 views
ARIMA model with measurement error
I'm interested in forecasting a time series $m_t$ which is contaminated with measurement error $e_t$, so the observed time series is $y_t = m_t + e_t$. I can suppose $m_t$ and $e_t$ are independent ...
0
votes
0answers
23 views
2
votes
0answers
41 views
ARMA process forecasts and maximum likelihood parameters
I have some trouble understanding the forecasting/inference process of ARMA models.
From Hamilton (which I am reading now), we can obtain forecasts at $Y$ from any linear process with r.v. values $X$...
0
votes
1answer
19 views
LSTM - random and always-different time between data measurements?
I am working with a time series problem where the time between two data measurements is random, and I am trying, without luck, to find an LSTM architecture that can handle this.
A very simplified ...
2
votes
2answers
63 views
Variance inhomogeneity in time series when forecasting
I am using a time series for monthly temperatures to predict future temperatures.
To this I am using the seasonal ARIMA model and Holt Winters forecast, and my results seems fine.
However, my data ...
0
votes
0answers
20 views
Help in structuring problem to forecast end of testing
I need assistance, please, in structuring the following problem. (I can use the World-Wide Help Manual to do the math and the calculations, I need help in setting up the structure of the analysis).
...
0
votes
0answers
44 views
Programming for hybrid models of arima-ann and arima-svm time series foercasting in rstudio
i am doing my mphil thesis on hybrid modeling of arima-ann and arima-svm for time series forecasting following the G.Peter Zhang's research paper (https://www.sciencedirect.com/science/article/pii/...
0
votes
0answers
29 views
Using ecmpredict in R to forecast from an ECM
I have fit an ECM model to my data using the ecm function, which is part of the ecm package. I would now like to use ecmpredict to predict/forecast future values of my target variable. The function ...
0
votes
0answers
25 views
Forecasting Short Time-Series with other time-series
This is sort of related to a previous question, but now I don't have the requirement of generating customer-level forecasts.
I've acquired a set of card customers every month for the last 3 years. I ...
0
votes
0answers
23 views
Programming for SVM or SVR time series foercasting in rstudio
is there any programming codes for SVM for time series forecasting like neural network has build in function of nnetar in forecast package and we can also do it from caret package. if not, then how ...
2
votes
2answers
80 views
Compute forecasts and 90% forecast intervals for ARIMA(p,1,q) models
Consider the two models (ARIMA(1,1,0) and (ARIMA(0,1,1)):
0
votes
0answers
9 views
Penalized regressions with forecast package and ets in R
Is there a way within the forecast package and ets to remap or penalize residuals based on some user defined function?
E.g.
If one wanted to impose a skew in error minimization, is this possible?
...
0
votes
1answer
33 views
How to perform 1 step ahead forecasts with a VAR function [closed]
Say I am given the parameters of a VAR (2) function with two variables. How would I use this information to perform a 1 step ahead forecast?
Example of what I would have is...
$A_t= 1.5 - 0.5A_{t-1} ...
1
vote
1answer
69 views
What is multi-step time series forecasting?
Disclaimer: New to this field
I am researching ways to forecast a given time-series.
So, I understand what Univariate and ...
-1
votes
0answers
22 views
model tuning for Holt function
I was working with the Holt function from "aTSA" package, which uses default values of ...
0
votes
0answers
24 views
How to obtain an HP filter trend less susceptible to end-point bias?
My understanding is that if a series is stationary, using the HP filter on it does not introduce cyclical artifacts. Also, it has been proposed that in order to overcome the end-point bias one can use ...
1
vote
0answers
14 views
Returns forecast back to closing price?
I'm working with log returns. I've selected an ARMA-GARCH for mean and volatility forecasting and I would like to get the forecasted confidence intervals and plot expressed in terms of the closing ...
1
vote
1answer
46 views
Time series: group and then forecast, or forecast and then group
Let's say we want to forecast revenue by month for the next 12 months, and we have daily revenue data for the last 3 years.
We could then group this data by month, train our model using revenue by ...
0
votes
0answers
15 views
Testing forecast accuracy in Excel [duplicate]
I'm looking for some advice on how to determine how accurate a forecast is.
Basically, what I have is 23 years of competitive results for a particular sport (10000+ matches). The matches are broken ...
1
vote
1answer
28 views
Stationarize count based time series data
I have a count based time series sequence with lot of 0s.
Usually to achieve stationarity we can do the following transform:
...
