scholarly journals Performance Evaluation of a New Hybrid Multivariate Meteorological Model Analysis: A Simulation Study

MATEMATIKA ◽  
2018 ◽  
Vol 34 (1) ◽  
pp. 73-85
Author(s):  
Siti Mariam Norrulashikin ◽  
Fadhilah Yusof ◽  
Ibrahim Lawal Kane
Keyword(s):  
Time Series ◽  
Performance Evaluation ◽  
Simulation Study ◽  
Multivariate Time Series ◽  
Model Performance ◽  
Performance Measurements ◽  
Meteorological Model ◽  
Vector Autoregressive ◽  
Base Process ◽  
Normal Hybrid

Simulation is used to measure the robustness and the efficiency of the forecasting techniques performance over complex systems. A method for simulating multivariate time series was presented in this study using vector autoregressive base-process. By applying the methodology to the multivariable meteorological time series, a simulation study was carried out to check for the model performance. MAPE and MAE performance measurements were used and the results show that the proposed method that consider persistency in volatility gives better performance and the accuracy error is six time smaller than the normal hybrid model.

ROBUST OPTIMAL TESTS FOR CAUSALITY IN MULTIVARIATE TIME SERIES

2008 ◽  
Vol 24 (4) ◽  
pp. 948-987 ◽  
Author(s):  
Abdessamad Saidi ◽  
Roch Roy
Keyword(s):  
Time Series ◽  
Asymptotic Methods ◽  
Multivariate Time Series ◽  
Wald Test ◽  
Statistical Decision Theory ◽  
Affine Transformations ◽  
Statistical Decision ◽  
Vector Autoregressive ◽  
Optimal Tests ◽  
Asymptotically Optimal Tests

Here, we derive optimal rank-based tests for noncausality in the sense of Granger between two multivariate time series. Assuming that the global process admits a joint stationary vector autoregressive (VAR) representation with an elliptically symmetric innovation density, both no feedback and one direction causality hypotheses are tested. Using the characterization of noncausality in the VAR context, the local asymptotic normality (LAN) theory described in Le Cam (1986, Asymptotic Methods in Statistical Decision Theory) allows for constructing locally and asymptotically optimal tests for the null hypothesis of noncausality in one or both directions. These tests are based on multivariate residual ranks and signs (Hallin and Paindaveine, 2004a, Annals of Statistics 32, 2642–2678) and are shown to be asymptotically distribution free under elliptically symmetric innovation densities and invariant with respect to some affine transformations. Local powers and asymptotic relative efficiencies are also derived. The level, power, and robustness (to outliers) of the resulting tests are studied by simulation and are compared to those of the Wald test. Finally, the new tests are applied to Canadian money and income data.

scholarly journals Nowcasting Austrian Short Term Statistics

2018 ◽  
Vol 34 (2) ◽  
pp. 503-522
Author(s):  
Markus Fröhlich
Keyword(s):  
Time Series ◽  
Missing Values ◽  
Multivariate Time Series ◽  
Seasonal Adjustment ◽  
Short Term ◽  
Vector Autoregressive ◽  
Adjustment Program ◽  
Time Series Approach ◽  
Total Turnover ◽  
Vector Error Correction Models

Abstract Early estimates for Austrian short term indices were produced using multivariate time-series models. The article presents a simulation study with different models (vector error correction models, vector autoregressive models in levels – both with unadjusted and seasonally adjusted time-series) used for estimating total turnover, production, etc. In a preliminary step, before time-series were provided for nowcasting, the data had to undergo an editing process. In this case a time-series approach was selected for data-editing as well, because of the very specific structure of Austrian enterprises. For this task basically the seasonal adjustment program X13Arima-Seats was used for identifying and replacing outlying observations, imputation of missing values and generating univariate forecasts for every single time series.

scholarly journals An Investigation Towards The Suitability Of Vector Autoregressive Approach On Modeling Meteorological Data

2015 ◽  
Vol 9 (11) ◽  
pp. 89 ◽  
Author(s):  
Siti Mariam Norrulashikin
Keyword(s):  
Time Series ◽  
Meteorological Data ◽  
Multivariate Time Series ◽  
Model Identification ◽  
Suitable Model ◽  
Multiple Time ◽  
Vector Autoregressive ◽  
Modeling Strategy ◽  
Vector Time Series ◽  
The Impact

In most meteorological problems, two or more variables evolve over time. These variables not only haverelationships with each other, but also depend on each other. Although in many situations the interest was onmodelling single variable as a vector time series without considering the impact other variables have on it. Thevector autoregression (VAR) approach to multiple time series analysis are potentially useful in many types ofsituations which involve the building of models for discrete multivariate time series. This approach has 4important stages of the process that are data pre-processing, model identification, parameter estimation, andmodel adequacy checking. In this research, VAR modeling strategy was applied in modeling three variables ofmeteorological variables, which include temperature, wind speed and rainfall data. All data are monthly data,taken from the Kuala Krai station from January 1985 to December 2009. Two models were suggested byinformation criterion procedures, however VAR (3) model is the most suitable model for the data sets based onthe model adequacy checking and accuracy testing.

scholarly journals Soft Computation Vector Autoregressive Neural Network (VAR-NN) GUI-Based

2018 ◽  
Vol 73 ◽  
pp. 13008 ◽  
Author(s):  
Hasbi Yasin ◽  
Budi Warsito ◽  
Rukun Santoso ◽  
Suparti
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Autoregressive Model ◽  
Stock Price ◽  
Time Series Data ◽  
Multivariate Time Series ◽  
Series Data ◽  
Percentage Error ◽  
Vector Autoregressive ◽  
Price Data

Vector autoregressive model proposed for multivariate time series data. Neural Network, including Feed Forward Neural Network (FFNN), is the powerful tool for the nonlinear model. In autoregressive model, the input layer is the past values of the same series up to certain lag and the output layers is the current value. So, VAR-NN is proposed to predict the multivariate time series data using nonlinear approach. The optimal lag time in VAR are used as aid of selecting the input in VAR-NN. In this study we develop the soft computation tools of VAR-NN based on Graphical User Interface. In each number of neurons in hidden layer, the looping process is performed several times in order to get the best result. The best one is chosen by the least of Mean Absolute Percentage Error (MAPE) criteria. In this study, the model is applied in the two series of stock price data from Indonesia Stock Exchange. Evaluation of VAR-NN performance was based on train-validation and test-validation sample approach. Based on the empirical stock price data it can be concluded that VAR-NN yields perfect performance both in in-sample and in out-sample for non-linear function approximation. This is indicated by the MAPE value that is less than 1% .

scholarly journals Interdependence between confirmed and discarded cases of dengue, chikungunya and Zika viruses in Brazil: A multivariate time-series analysis

2019 ◽  
Author(s):  
Juliane F Oliveira ◽  
Moreno S. Rodrigues ◽  
Lacita M. Skalinski ◽  
Aline ES Santos ◽  
Larissa C. Costa ◽  
...  
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Multivariate Time Series ◽  
Var Model ◽  
Vector Autoregressive ◽  
The Real ◽  
Series Analysis ◽  
Multivariate Time Series Analysis ◽  
Epidemiological Impact ◽  
New Perspective

AbstractThe co-circulation of different arboviruses in the same time and space poses a significant threat to public health given their rapid geographic dispersion and serious health, social, and economic impact. Therefore, it is crucial to have high quality of case registration to estimate the real impact of each arboviruses in the population. In this work, a Vector Autoregressive (VAR) model was developed to investigate the interrelationships between discarded and confirmed cases of dengue, chikungunya, and Zika in Brazil. We used data from the Brazilian National Notifiable Diseases Information System (SINAN) from 2010 to 2017. There were three peaks in the series of dengue notification in this period occurring in 2013, 2015 and in 2016. The series of reported cases of both Zika and chikungunya reached their peak in late 2015 and early 2016. The VAR model shows that the Zika series have a significant impact on the dengue series and vice versa, suggesting that several discarded and confirmed cases of dengue could actually have been cases of Zika. The model also suggests that the series of confirmed and discarded chikungunya cases are almost independent of the cases of Zika, however, affecting the series of dengue. In conclusion, co-circulation of arboviruses with similar symptoms could have lead to misdiagnosed diseases in the surveillance system. We argue that the routinely use of mathematical and statistical models in association with traditional symptom-surveillance could help to decrease such errors and to provide early indication of possible future outbreaks. These findings address the challenges regarding notification biases and shed new light on how to handle reported cases based only in clinical-epidemiological criteria when multiples arboviruses co-circulate in the same population.Author summaryArthropod-borne viruses (arboviruses) transmission is a growing health problem worldwide. The real epidemiological impact of the co-circulation of different arboviruses in the same urban spaces is a recent phenomenon and there are many issues to explore. One of them is the misclassification due to the scarce availability of confirmatory laboratory tests. This establishes a challenge to identify, distinguish and estimate the number of infections when different arboviruses co-circulate. We propose the use of multivariate time series analysis to understand how the weekly notification of suspected cases of dengue, chikungunya and Zika, in Brazil, affected each other. Our results suggest that the series of Zika significantly impact on the series of dengue and vice versa, indicating that several discarded and confirmed cases of dengue might actually have been Zika cases. The results also suggest that the series of confirmed cases of chikungunya are almost independent of those of dengue and Zika. Our findings shed light on yet hidden aspects on the co-circulation of these three viruses based on reported cases. We believe the present work provides a new perspective on the longitudinal analysis of arboviruses transmission and call attention to the challenge in dealing with biases in case notifications when multiple arboviruses circulate in the same urban environment.

Sign in / Sign up

Export Citation Format

Share Document