SPACE-TIME EMPLOYMENT MODELING: SOME RESULTS USING SEEMINGLY UNRELATED REGRESSION ESTIMATORS*

1982 ◽  
Vol 22 (3) ◽  
pp. 283-302 ◽  
Author(s):  
Eugene N. White ◽  
Geoffrey J. D. Hewings
Keyword(s):  
Space Time ◽  
Seemingly Unrelated Regression ◽  
Unrelated Regression ◽  
Regression Estimators

PENERAPAN SEASONAL GENERALIZED SPACE TIME AUTOREGRESSIVE SEEMINGLY UNRELATED REGRESSION (SGSTAR SUR) PADA PERAMALAN HASIL PRODUKSI PADI

2021 ◽  
Vol 10 (2) ◽  
pp. 241-249
Author(s):  
Leni Pamularsih ◽  
Mustafid Mustafid ◽  
Abdul Hoyyi
Keyword(s):  
Rice Yield ◽  
Space Time ◽  
Least Square ◽  
Seemingly Unrelated Regression ◽  
Training Data ◽  
Seasonal Effect ◽  
Validation Data ◽  
Central Java ◽  
Unrelated Regression ◽  
Inverse Distance

Ordinary Least Square (OLS) is general method to estimate Generalized Space Time Autoregressive (GSTAR) parameters. Parameter estimation by using OLS for GSTAR model with correlated residuals between equations will produce inefficient estimators. The method that appropriate to estimate the parameter model with correlated residuals between equations is Generalized Least Square (GLS), which is usually used in Seemingly Unrelated Regression (SUR). This research aims to build the seasonal GSTAR SUR model as model of rice yield forecasting in three locations by using the best weighting. Weights used are binary weights, inverse distance and normalization of cross correlation. Data which used in this research are the data of rice yield per quarter in three districts in Central Java, namely Banyumas, Cilacap and Kebumen. The data from the period of January 1981 to December 2014 as training data and the period of January 2015 to December 2018 as validation data. The resulting is a model that has a seasonal effect with the autoregressive order and the spasial order limited to 1 so the model formed is SGSTAR (41)-I(1)(1)3. The best model produced is the SGSTAR SUR (41)-I(1)(1)3 model with inverse distance weighting because it fulfills both assumptions, residuals white noise and residuals normally multivariate distribution. Additionally, it has the smallest MAPE value when compared the other weighting, that is 20%. This MAPE value indicates  that the accuracy rate of forecast is accurate.Keywords: Rice yield, Seasonal, GSTAR, SUR.

scholarly journals PENERAPAN GSTAR-SUR PADA JUMLAH PENUMPANG PESAWAT DOMESTIK DI BANDARA INDONESIA

2020 ◽  
Vol 9 (2) ◽  
Author(s):  
Gilang Habibie, Yundari, Hendra Perdana
Keyword(s):  
Space Time ◽  
Least Square ◽  
Seemingly Unrelated Regression ◽  
Ordinary Least Square ◽  
Unrelated Regression

Generalized space time autoregressive (GSTAR) adalah model ruang waktu yang banyak digunakan di Indonesia. Sebagian besar penelitian model GSTAR menggunakan ordinary least square (OLS) untuk mengestimasi parameter. Namun, estimasi dengan metode OLS pada model GSTAR dengan residual saling berkorelasi akan menghasilkan estimator yang tidak efisien terutama pada data musiman. Metode estimasi yang sesuai untuk residual yang saling berkorelasi adalah generalized least square (GLS), yang biasa digunakan dalam model seemingly unrelated regression (SUR). Penelitian ini bertujuan untuk menganalisis model GSTAR-SUR dan membandingkannya dengan GSTAR-OLS dengan bobot seragam dan jarak. Data yang digunakan adalah data jumlah penumpang pesawat domestik setiap bulan di Bandara Polonia/Kualanamu, Soekarno-Hatta, Juanda dan Ngurah Rai dari Januari 2006 hingga September 2019. Hasil estimasi parameter GSTAR-SUR dengan bobot seragam adalah Polonia/Kualanamu (∅10=-0,494; ∅11=0,046), Soekarno-Hatta (∅10=-0,300; ∅11=-0,828), Juanda (∅10=-0,451; ∅11=0,033) dan Ngurah Rai (∅10=-0,198; ∅11=-0,019). Sedangkan GSTAR-SUR dengan bobot jarak menghasilkan estimasi Polonia/Kualanamu (∅10=-0,492; ∅11=0,026), Soekarno-Hatta (∅10=-0,292; ∅11=-1,186), Juanda (∅10=-0,455; ∅11=0,058) dan Ngurah Rai (∅10=-0,211; ∅11=0,017). Berdasarkan nilai MAPE GSTAR-SUR lebih baik dari GSTAR-OLS dengan nilai MAPE untuk model GSTAR-OLS adalah 12,90% pada bobot seragam dan 13,43% pada bobot jarak. Model GSTAR-SUR menghasilkan nilai MAPE 6,65% untuk bobot seragam dan 7,06% untuk bobot jarak. Model terbaik adalah GSTAR-SUR bobot seragam dengan nilai MAPE 6,65%. Kata Kunci : OLS, GLS, spacetime, korelasi eror

scholarly journals PEMODELAN INDEKS HARGA KONSUMEN DI JAWA TENGAH DENGAN METODE GENERALIZED SPACE TIME AUTOREGRESSIVE SEEMINGLY UNRELATED REGRESSION (GSTAR-SUR)

2018 ◽  
Vol 7 (4) ◽  
pp. 337-347
Author(s):  
Mega Fitria Andriyani ◽  
Abdul Hoyyi ◽  
Hasbi Yasin
Keyword(s):  
Price Index ◽  
Consumer Price Index ◽  
Estimation Method ◽  
Space Time ◽  
Least Square ◽  
Seemingly Unrelated Regression ◽  
Residual Correlation ◽  
Central Java ◽  
Previous Time ◽  
Unrelated Regression

The Generalized Space Time Autoregressive (GSTAR) model with Seemingly Unrelated Regression (SUR) estimation method or often called GSTAR-SUR is more efficient to be used for residual correlation than Ordinary Least Square (OLS) estimation method. The SUR estimation method utilizes residual correlation information to improve the estimated efficiency resulting in a smaller standard error. The purpose of this research is to get the GSTAR-SUR model according to Consumer Price Index (CPI) data in four regencies or cities in Central Java namely Purwokerto, Surakarta, Semarang, and Tegal. Based on the assumed white noise assumption, the smallest MAPE and RMSE averages, the best model chosen in this research is the GSTAR-SUR(11)I(1) model with the heavy of normalized cross-correlation with the average MAPE value of 0.4455% and RMSE value of 0.80582. The best model obtained explains that the CPI data in Purwokerto, Semarang, and Tegal not only influenced by the previous time but also influenced by the locations. Meanwhile, the CPI data in Surakarta is only influenced by the previous time, but it is not affected by other locations. Keywords: SUR, OLS, Consumer Price Index

scholarly journals Seemingly Unrelated Regression Approach for GSTARIMA Model to Forecast Rain Fall Data in Malang Southern Region Districts

CAUCHY ◽  
2016 ◽  
Vol 4 (2) ◽  
pp. 57 ◽  
Author(s):  
Siti Choirun Nisak
Keyword(s):  
Time Series ◽  
Covariance Matrix ◽  
Ordinary Least Squares ◽  
Space Time ◽  
Least Square ◽  
Seemingly Unrelated Regression ◽  
Unrelated Regression ◽  
Estimate Parameter ◽  
Seasonal Data ◽  
Variance Covariance Matrix

Time series forecasting models can be used to predict phenomena that occur in nature. Generalized Space Time Autoregressive (GSTAR) is one of time series model used to forecast the data consisting the elements of time and space. This model is limited to the stationary and non-seasonal data. Generalized Space Time Autoregressive Integrated Moving Average (GSTARIMA) is GSTAR development model that accommodates the non-stationary and seasonal data. Ordinary Least Squares (OLS) is method used to estimate parameter of GSTARIMA model. Estimation parameter of GSTARIMA model using OLS will not produce efficiently estimator if there is an error correlation between spaces. Ordinary Least Square (OLS) assumes the variance-covariance matrix has a constant error 𝜀𝑖𝑗~𝑁𝐼𝐷(𝟎,𝝈𝟐) but in fact, the observatory spaces are correlated so that variance-covariance matrix of the error is not constant. Therefore, Seemingly Unrelated Regression (SUR) approach is used to accommodate the weakness of the OLS. SUR assumption is 𝜀𝑖𝑗~𝑁𝐼𝐷(𝟎,𝚺) for estimating parameters GSTARIMA model. The method to estimate parameter of SUR is Generalized Least Square (GLS). Applications GSTARIMA-SUR models for rainfall data in the region Malang obtained GSTARIMA models ((1)(1,12,36),(0),(1))-SUR with determination coefficient generated with the average of 57.726%.

A Note on the Efficiency of Seemingly Unrelated Regression

1988 ◽  
Vol 42 (2) ◽  
pp. 137-139 ◽  
Author(s):  
James K. Binkley ◽  
Carl H. Nelson
Keyword(s):  
Seemingly Unrelated Regression ◽  
Unrelated Regression

Workplace disability and job satisfaction in Britain: A co-worker test?

2021 ◽  
pp. 0143831X2110142
Author(s):  
Getinet Astatike Haile
Keyword(s):  
Job Satisfaction ◽  
Negative Relationship ◽  
Organisational Culture ◽  
Seemingly Unrelated Regression ◽  
Unrelated Regression ◽  
Significant Negative Relationship ◽  
Using Data

The article examines the link between workplace disability (WD) and workplace job satisfaction (JS) using data from WERS2011. Controlling for a rich set of workplace characteristics including organisational culture, the study finds a significant negative relationship between JS and the share of disabled respondents within workplaces. Notably, Seemingly Unrelated Regression (SUR)-based analysis distinguishing between disabled and non-disabled respondents reveals that the negative relationship found is specific to non-disabled respondents. Moreover, disability equality policies are found to be significantly positively related with disabled respondents’ JS while they are negatively related with the JS of their non-disabled counterparts. The article ponders if there is a co-worker aspect to the WD–JS link and whether HR policies may need to take heed of co-worker dynamics in this respect.

Determinan Kelaparan di Indonesia Tahun 2015-2019

2021 ◽  
Vol 2021 (1) ◽  
pp. 547-556
Author(s):  
Daniel M V Mone ◽  
Efri Diah Utami
Keyword(s):  
Sustainable Development ◽  
Sustainable Development Goals ◽  
Fixed Effect Model ◽  
Fixed Effect ◽  
Seemingly Unrelated Regression ◽  
Unrelated Regression ◽  
Effect Model ◽  
Development Goals

Sustainable Development Goals (SDGs) adalah sebuah perencana aksi berskala global yang disepakati oleh para pemimpin dunia, termasuk Indonesia dengan tujuan mendorong pembangunan sosial, ekonomi dan lingkungan hidup. Salah satu dari 17 tujuan SDGs adalah mengakhiri kelaparan. Berdasarkan data yang dirilis Badan Pusat Statistik, salah satu pendekatan untuk mengukur tingkat kelaparan adalah proporsi penduduk dengan asupan kalori minimum di bawah 1400 kkal/kapita/hari.  Proporsi penduduk dengan asupan kalori minimum di bawah 1400 kkal/kapita/hari di Indonesia masih cukup tinggi dan terus mengalami peningkatan dari tahun 2017 hingga 2019. Penelitian ini bertujuan untuk menganalisis bagaimana gambaran umum dari tingkat kelaparan dan variabel-variabel yang diduga mempengaruhinya, serta  bagaimana pengaruh variabel-variabel tersebut terhadap tingkat kelaparan di Indonesia tahun 2015-2019. Hasil dari penelitian ini dapat digunakan untuk merumuskan kebijakan-kebijakan guna penuntasan kelaparan di Indonesia. Metode analisis yang digunakan adalah regresi data panel dengan menggunakan  fixed effect model yang diestimasi dengan metode Seemingly Unrelated Regression (SUR). Hasil dari penelitian ini menunjukkan bahwa variabel yang berpengaruh signifikan terhadap tingkat kelaparan adalah pengeluaran makanan dan harga beras, sedangkan jumlah penduduk miskin dan pendapatan perkapita tidak berpengaruh signifikan.

scholarly journals Robust Bayesian seemingly unrelated regression model

2018 ◽  
Vol 34 (3) ◽  
pp. 1135-1157
Author(s):  
Chamberlain Mbah ◽  
Kris Peremans ◽  
Stefan Van Aelst ◽  
Dries F. Benoit
Keyword(s):  
Regression Model ◽  
Seemingly Unrelated Regression ◽  
Unrelated Regression ◽  
Seemingly Unrelated Regression Model
Sign in / Sign up

Export Citation Format

Share Document