Consistent forecast intervals when the forecast-period exogenous variables are stochastic

Article Abstract:

Researchers may encounter difficulties in deriving prediction intervals when the values of the exogenous variables are uncertain, or when estimates are used in place of true values. This is also true even in the presence of a linear k-variable regression model, a normal dependent variable and jointly normal exogenous variables since the distribution of the forecast error remains non-normal. A bootstrap method shows promise as an alternative to the traditional asymptotic normal theory in the face of stochastic forecast-period exogenous variables.

Methods, Economic forecasting

---

Bayesian modeling of ARFIMA processes by Markov chain Monte Carlo methods

Article Abstract:

The application of a sampling-based Bayesian approach using Markov chain Monte Carlo methods for autoregressive fractionally integrated moving average (ARFIMA) models results in a viable and more relatively more accurate solution than those created by other statistical methods. This is done by using a partial linear regression coefficients of the ARFIMA process to obtain the posterior distribution of the model parameters corresponding to the likelihood function.

Research, Bayesian statistical decision theory, Bayesian analysis, Markov processes

---

Outlier detection in regression models with ARIMA errors using robust estimates

Article Abstract:

A new outlier detection procedure is evaluated. The detection procedure works better when there are a large number of outliers in a regression model.

Argentina, Econometrics & Model Building, Statistical Data Included, Models, Econometrics, Identification and classification, Regression analysis, Business models, Outliers (Statistics)

Similar abstracts:

• Abstracts: Forecasting growth with time series models. Time series analysis supported by power transformations
• Abstracts: Consistent specification testing via nonparametric series regression. Consistent testing for serial correlation of unknown form
• Abstracts: Optimal tests for parameter instability in the generalized method of moments framework. Monitoring structural change
• Abstracts: Small-sample confidence intervals for impulse response functions. Impulse response analysis in vector autoregressions with unknown lag order
• Abstracts: Multi-step error variances for periodically integrated time series. Sensitivity of univariate AR (1) time-series forecasts near the unit root

This website is not affiliated with document authors or copyright owners. This page is provided for informational purposes only. Unintentional errors are possible.