Determination of the best weight matrix for the Generalized Space Time Autoregressive (GSTAR) model in the Covid-19 case on Java Island, Indonesia

Huda, Nur’ainul Miftahul; Imro’ah, Nurfitri

doi:10.1016/j.spasta.2023.100734

Cited by 8 publications

(8 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Pada data ruang waktu dapat digunakan model GSTAR (Generalized Space Time Autoregressive) untuk memodelkan data tersebut. Data dengan pola stasioner dapat dimodelkan dengan model GSTAR [12] [7]. Sementara itu, data yang tidak stasioner (umumnya memiliki pola tren atau musiman) dapat dimodelkan dengan model Integrated GSTAR (GSTARI) atau model Seasonal GSTAR (S-GSTAR).…”

Section: Pendahuluanunclassified

Spatial Weighting Selection in GSTAR and S-GSTAR Models for Temperature Prediction

Utami,

Mukhaiyar,

Mardiyah

et al. 2024

View full text Add to dashboard Cite

Recent research in time series analysis indicates that events at a particular location are not only influenced by events at previous times but also by proximity between locations. Events influenced by both space and time can be modeled using a space-time model. GSTAR model is one such space-time model. In its development, time series data exhibiting seasonal patterns are modeled using Seasonal GSTAR (S-GSTAR). The GSTAR and S-GSTAR models are used to model temperature in the Banjar, Cilacap, and Sleman Districts. The purpose of employing both methods is to compare the best model for modeling temperature at these three locations. Spatial weights used include inverse distance weighting using the Euclidean distance formula, uniform weighting, and cross-correlation normalization weighting. Ordinary Least Squares (OLS) is the estimation method used in this study. The best model obtained is S-GSTAR with inverse distance weighting, as this model has the smallest RMSE value.

show abstract

Section: Pendahuluanunclassified

Spatial Weighting Selection in GSTAR and S-GSTAR Models for Temperature Prediction

Utami,

Mukhaiyar,

Mardiyah

et al. 2024

View full text Add to dashboard Cite

show abstract

“…The weight matrix that is characteristic of the GSTAR spacetime model can be used to identify the model. The relationship that occurs between a variety of geographical locations is depicted by this matrix (Huda & Imro'ah, 2023).…”

Section: Weight Matrixmentioning

confidence: 99%

Looking at GDP from a Statistical Perspective: Spatio-Temporal GSTAR(1;1) Model

Huda,

Imro'ah,

Arini

et al. 2023

JTAM

View full text Add to dashboard Cite

The gross domestic product (GDP) is a significant indicator for evaluating the performance of an economy. The GDP of a nation can be used to get a sense of the size and health of that nation's economy. Indonesia is the only nation from Southeast Asia to be represented in the G20. All G20’s countries play vital roles in creating the economic landscape of the region, the world, and everything in between. This research is focused on the increase of the GDP in Indonesia, Malaysia, Singapore, Thailand, and Brunei Darussalam. The spatial influence of GDP can be seen in the growth of each nation's infrastructure and industrial sector, for example. at the regional level, the increase of a country's GDP can also have an effect on the countries that are its neighbors. Using the GSTAR model, the aim of this study is to investigate the spatial and temporal influences on the GDP statistics of five different countries. The GSTAR model is distinguished by the presence of a weight matrix, which is one of its distinguishing features. In addition, the aim of this research is to select the most appropriate weight matrix for the purpose of representing the spatial effect on GDP statistics. Uniform, queen contiguity, and inverse distance weight matrices are the types of weight matrices that are utilized. Calculating each weight matrix, estimating relevant parameters, and performing diagnostic tests are the primary activities involved in this investigation. As a consequence of this, a weight matrix that is uniform in its distribution is the one that performs the best. The spatial and temporal correlations of GDP data may be accurately represented by the GSTAR model when it is equipped with a uniform weight matrix. This model is applied to five different countries.

show abstract

“…The location weight matrix is a matrix that expresses the relationship of the observation area measuring N × N and is symbolized by W. Some weighting matrices that can be applied to the GSTAR model include uniform weights, distance inverse, and cross-correlation normalization [11]. The chosen weighting matrices can impact the accuracy and the prediction results [12]. Some research about GSTAR has discussed the modified weighting matrices in order to get better prediction results.…”

Section: Introductionmentioning

confidence: 99%

The Implementation of the Generalized Space-Time Autoregressive (GSTAR) Model for Inflation Prediction

Hestuningtias,

Kurniawan

2023

ENTHUSIASTIC

View full text Add to dashboard Cite

The macroeconomic indicator used to measure a country’s economic balance is inflation. The increase in the price of goods and services causes an increase in inflation, which impacts the decrease in the value of money so that people’s purchasing power for goods and services will decrease and result in slow economic growth. One way to determine future inflation is by forecasting. The Generalized Space-Time Autoregressive (GSTAR) model is a time series model involving time and location. This study aims to predict future inflation using the GSTAR model, which uses differencing without uniform location weights, inverse distance, and normalized cross-correlation. The results showed that the models obtained were the GSTAR (2,1) and GSTAR (5,1)I(1) models. The best model to predict inflation is the GSTAR (5,1)I(1) model with the normalized cross-correlation weight, which had Root Mean Square Error (RMSE) value of 0.5743, which was smaller than the GSTAR (2,1) model.

show abstract

Determination of the best weight matrix for the Generalized Space Time Autoregressive (GSTAR) model in the Covid-19 case on Java Island, Indonesia

Cited by 8 publications

References 27 publications

Spatial Weighting Selection in GSTAR and S-GSTAR Models for Temperature Prediction

Spatial Weighting Selection in GSTAR and S-GSTAR Models for Temperature Prediction

Looking at GDP from a Statistical Perspective: Spatio-Temporal GSTAR(1;1) Model

The Implementation of the Generalized Space-Time Autoregressive (GSTAR) Model for Inflation Prediction

Contact Info

Product

Resources

About