2003
DOI: 10.32468/be.268
|View full text |Cite
|
Sign up to set email alerts
|

La demanda de efectivo en Colombia: una caja negra a la luz de las redes neuronales

Abstract: Noviembre 2003 * Agradecemos la colaboración de Sergio Olarte en la estimación de los modelos lineales univariados.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2

Citation Types

0
2
0
3

Year Published

2006
2006
2018
2018

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 18 publications
0
2
0
3
Order By: Relevance
“…This is particularly convenient in our case as the output and most inputs exhibit non-normal distributions and appear to display some degree of heteroscedasticity (see Table 6, Figures 6 and 7, in the Appendix). Finally, anns have proven to be very effective in time series prediction problems, even better than standard econometric approaches (Kohzadi et al, 1995;Zhang et al, 1999;Misas et al, 2003;McNelis, 2005;Jalil & Misas, 2006;Han & Kamber, 2006;Chaudhuri & Ghosh, 2016;Di Piazza et al, 2016). This is key in our case because, again, nowcasting is a prediction task.…”
Section: Prediction Methodsmentioning
confidence: 68%
“…This is particularly convenient in our case as the output and most inputs exhibit non-normal distributions and appear to display some degree of heteroscedasticity (see Table 6, Figures 6 and 7, in the Appendix). Finally, anns have proven to be very effective in time series prediction problems, even better than standard econometric approaches (Kohzadi et al, 1995;Zhang et al, 1999;Misas et al, 2003;McNelis, 2005;Jalil & Misas, 2006;Han & Kamber, 2006;Chaudhuri & Ghosh, 2016;Di Piazza et al, 2016). This is key in our case because, again, nowcasting is a prediction task.…”
Section: Prediction Methodsmentioning
confidence: 68%
“…A comprehensive review is presented in Bańbura et al (2013). as the output and most inputs exhibit non-normal distributions and appear to display some degree of heteroscedasticity (see Table 6, figures 6 and 7, in Appendix). Finally, ANNs have proven to be very effective in time series prediction problems, even better than standard econometric approaches (see Kohzadi et al, 1995, Zhang et al, 1999, Misas et al, 2003, McNelis, 2005, Jalil & Misas, 2006, Han & Kamber, 2006, Chaudhuri & Ghosh, 2016, Di Piazza et al, 2016. This is key in our case because, again, nowcasting is a prediction task.…”
Section: Prediction Methodsmentioning
confidence: 77%
“…En esta línea de trabajos, Gómez (1998) señala que las innovaciones financieras son esenciales para medir la demanda por dinero, puesto que capturan el efecto directo que tiene su velocidad de circulación, además de corregir los posibles problemas generados por la inestabilidad de la demanda. Otra línea de trabajos, como los de Arango y González (2000) y Misas, López, Arango y Hernández (2003), modelan y pronostican la demanda por dinero, mediante especificaciones no lineales, basadas, entre otros aspectos, en el efecto que tiene la heterogeneidad de los agentes en la demanda agregada por este instrumento.…”
Section: Introductionunclassified