Bootstrap Inference of Level Relationships in the Presence of Serially Correlated Errors: A Large Scale Simulation Study and an Application in Energy Demand

摘要: By undertaking a large scale simulation study, we demonstrate that the maximum entropy bootstrap (meboot) data generation process can provide accurate and narrow parameter confidence intervals in models with combinations of stationary nonstationary variables, under both low high degrees autocorrelation. The relatively small sample sizes which meboot performs particularly well make it useful tool for rolling window estimation. As case analyze evolution price income elasticities import demand crude oil Turkey by using quarterly between 1996---2011. Our approach be employed to tackle wide range macroeconometric estimation problems where are common issue.