3. Producción
Browse
3 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Note about Detection of Additive Outliers with Fractional Errors(Pontificia Universidad Católica del Perú. Departamento de Economía, 2013)Perron and Rodríguez (2003) claimed that their procedure to detect for additive outliers (_ d) is powerful even when we have departures from the unit root case. In this note, we use Monte-Carlo simulations to show that Td is powerful when we have ARFIMA (p; d; q) errors. Using simulations, we calculate the expected number of additive outliers found in this context and the number of times that the approach Td identifies the true location of the additive outliers. The results indicate that the power of the procedure Td depends of the size of the additive outliers. When we have a DGP with big sized additive outliers the percentage of time that Td detects correctly the location of the additive outliers is 100.0%. A comparison between Td and the procedure TRAMO-SEATS is also included. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Note on the Size of the ADF Test with Additive Outliers and Fractional Errors. A Reapraisal about the (non) stationarity of the Latin-American Inflation Series(Pontificia Universidad Católica del Perú. Departamento de Economía, 2013)This note analyzes the empirical size of the augmented Dickey and Fuller (ADF) statistic proposed by Perron and Rodríguez (2003) when the errors are fractional. This ADF is based on a searching procedure for additive outliers based on first-differences of the data named tau(d). Simulations show that empirical size of the ADF is not affected by fractional errors confirming the claim of Perron and Rodríguez (2003) that the procedure tau(d) is robust to departures of the unit root framework. In particular the results show low sensitivity of the size of the ADF statistic respect to the fractional parameter (d). However, as expected, when there is strong negative moving average autocorrelation or negative autoregressive autocorrelation, the ADF statistic is oversized. These difficulties are fixed when sample increases (from T = 100 to T = 200). Empirical application to eight quarterly Latin-American inflation series is also provided showing the importance of taking into account dummy variables for the detected additive outliers. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Comparative Note about Estimation of the Fractional Parameter under Additive Outliers(Pontificia Universidad Católica del Perú. Departamento de Economía, 2014)In a recent paper, Fajardo et al. (2009) propose an alternative semiparametric estimator of the fractional parameter in ARFIMA models which is robust to the presence of additive outliers. The results are very interesting; however, they use samples of 300 or 800 observations which are rarely found in macroeconomics or economics. In order to perform a comparison, I use the procedure to detect for additive outliers based on the estimator Td suggested by Perron and Rodríguez (2003). Further, I use dummy variables associated to the location of the selected outliers to estimate the fractional parameter. I found better results for the mean and bias of this parameter when T = 100 and the results in terms of the standard deviation and the MSE are very similar. However, for higher sample sizes as 300 or 800, the robust procedure performs better, specially based on the standard deviation and MSE measures. Empirical applications for seven Latin American inflation series with very small sample sizes contaminated by additive outliers are discussed. What we find is that when no correction for additive outliers is performed, the fractional parameter is underestimated.