The Temporal Characteristic of Closed-end Municipal Bond Fund Discounts/Premiums
Ronald Woan

Abstract
The primary objective of this study is to investigate, identify and classify the characteristics of the temporal behavior of municipal bond closed-end fund discounts/premiums from a class of linear stochastic autoregressive-integratedmoving average (ARIMA(p, d, q)) models. The secondary objective is to examine the ability of the identified and classified models to forecast out-of-sample closed-end fund discounts/premiums. These objectives are consistent with those of earlier study on domestic equity closed-end funds. Comparisons of the forecasting abilities will be made between the classified ARIMA(p, d, q) and random walk models using mean absolute percent error metric (MAPE) as criterion. Classification results: for the monthly series our results show: out of 27 municipal bond closed-end funds, there are seven following random walk model, seven following ARIMA(1,0,0) model, three following ARIMA (1,1,0) model, four following ARIMA(0,1,1) model, two following ARIMA(1,0,2), one following each of ARIMA(1,0,1), ARIMA(2,1,0), ARIMA(2,0,0), and ARIMA(1,1,2) models. For the weekly series our results show: out of 27 municipal bond closed-end funds, there are five following random walk model, thirteen following ARIMA(1,0,0) model, five following ARIMA(0,1,1) model, two following ARIMA(2,1,0) and one following each of ARIMA(0,1,2), and ARIMA(1,0,1) models. Except for one week out of the four weeks examined the forecast results for the weekly municipal bond closed-end funds do not show significant difference between the fund-specific ARIMA (p, d, q) models and the random walk model.

Full Text: PDF     DOI: 10.15640/ijat.v5n1a4