Time Series Forecasting for MA Models Bayesian Approach
| المصدر: | مجلة البحوث المالية والتجارية |
|---|---|
| الناشر: | جامعة بورسعيد - كلية التجارة |
| المؤلف الرئيسي: | Labeb, Mona R. (Author) |
| المجلد/العدد: | ع2 |
| محكمة: | نعم |
| الدولة: |
مصر |
| التاريخ الميلادي: |
2016
|
| الصفحات: | 287 - 291 |
| ISSN: |
2090-5327 |
| رقم MD: | 866195 |
| نوع المحتوى: | بحوث ومقالات |
| اللغة: | الإنجليزية |
| قواعد المعلومات: | EcoLink |
| مواضيع: | |
| كلمات المؤلف المفتاحية: |
Predictive Distribution | Bayesian Forecasting | Moving Average Models | Normal-Gamma Density | T Distribution
|
| رابط المحتوى: |
عدد مرات التحميل
9
| المستخلص: |
Bayesian analysis of Moving Average models is difficult since the likelihood function is highly nonlinear in the parameters, which complicates the prior specification and posterior calculations. Thus, the integrations involved in Bayesian analysis must be done numer¬ically. This is not easy and time consuming especially in the case of the multiparameter models. A successful solution to the problem suggested by Broemeling and Shaarawy[3]. Broemeling and Shaarawy’s approach is based on calculating the residuals recursively using nonlinear least squares estimates of the model coefficients. Then, the lagged errors of the model are replaced with their corresponding lagged residuals. In this study, the predictive distribution of future observations, which complies with the Bayesian Broemeling and Shaarawy’s approach, is applied. A simulation study results support the adequacy of us¬ing the proposed method. In this study, first, the problem of predictive analysis of MA models is considered. In order to apply the above-mentioned ap¬proximation in forecasting future observations, the one step ahead predictive densities of the general MA(q) processes based on Normal- Gamma prior and Jeffreys’ prior are derived. Second, some statistical tools are computed to the Bayesian proposed method such as the frequency distributions and summary statistics of the predictive mean. |
|---|---|
| ISSN: |
2090-5327 |
عناصر مشابهة
-
Bayesian Forecasting for MA Models
بواسطة: Labeb, Mona R. منشور: (2016) -
NORMAL MATRICES
بواسطة: Sakkijha, Muna Mohammad منشور: (2002) -
Numerical Solutions for Multi-Group Space-Time Neutron Diffusion Equations
بواسطة: Al Ghamdi, Mohammed Falah Homoud منشور: (2013) -
حول أنموذج القياسات المتكررة المتداخل المتقاطع المتداخل
بواسطة: السراي، نجم عبدالزهرة منشور: (2006) -
JACOBIANS OF PLANE QUINTIC CURVES OF GENUS ONE
بواسطة: Al Shammari, Fahd M. منشور: (2002)
