2012
DOI: 10.2139/ssrn.2193936
|View full text |Cite
|
Sign up to set email alerts
|

Forecasting Inflation with a Random Walk

Abstract: The use of different time-series models to generate forecasts is fairly usual in the forecasting literature in general, and in the inflation forecast literature in particular. When the predicted variable is stationary, the use of processes with unit roots may seem counterintuitive. Nevertheless, in this paper we demonstrate that forecasting a stationary variable with driftless unit-root-based forecasts generates bounded Mean Squared Prediction Errors errors at every single horizon. We also show via simulations… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
5
0

Year Published

2012
2012
2022
2022

Publication Types

Select...
5
1

Relationship

3
3

Authors

Journals

citations
Cited by 11 publications
(5 citation statements)
references
References 20 publications
0
5
0
Order By: Relevance
“…For the milk production form Cross Breed Cow (CBC), the best model is a random walk with drift (or an ARIMA (0,1,0) with drift), Pincheira and Medel. (2016).…”
Section: Resultsmentioning
confidence: 99%
“…For the milk production form Cross Breed Cow (CBC), the best model is a random walk with drift (or an ARIMA (0,1,0) with drift), Pincheira and Medel. (2016).…”
Section: Resultsmentioning
confidence: 99%
“…These adaptative terms are also function of the unknown parameters of the model 3. For a formal derivation and generalization of this result, seePincheira and Medel (2012).…”
mentioning
confidence: 89%
“…Hence, it is not used any available bias-correction estimation as those of Andrews (1993), Andrews and Chen (1994), Hansen (1999), Kim (2003), among others. This option is left because, as shown in Pincheira and Medel (2012) and Medel and Pincheira (2015), among the competing models to the GVAR it is included the RW, which results in a superior alternative for near-unity series. As the RW is used as a numerary model to compare the RMSFE, it results in a demanding benchmark for the GVAR-recalling the aim of this article.…”
Section: And Stock and Watson (2009)mentioning
confidence: 99%
“…In this article, it is used a driftless RW forecast, following the argument given in Pincheira and Medel (2012) and Medel and Pincheira (2015) that driftless RW-based forecast are unbiased. Iterating forward the AR(1) model we have:…”
Section: And Stock and Watson (2009)mentioning
confidence: 99%