Great expectations? evidence from Colombia’s exchange rate survey

Latin American Economic Review

Table 12 Out-of-sample forecasts: competing models vs. random walk

Model	1-Month \(\left( \mathrm{MSPE}_{r}-\mathrm{MSPE}_{u}\right)\)	1-Year \(\left( \mathrm{MSPE}_{r}-\mathrm{MSPE}_{u}\right)\)
Extrapolative	−0.0006 (0.001)	0.18*** (0.042)
Adaptive	−0.0004 (0.001)	0.20*** (0.045)
Regressive	0.003*** (0.001)	0.09*** (0.030)
Forward discount	0.003** (0.002)	0.03** (0.016)
Surveyed expectations
All participants	0.009*** (0.002)	0.01 (0.013)
Commercial banks	0.009*** (0.002)	0.01 (0.015)
Stockbrokers	0.009*** (0.002)	0.01 (0.012)
Pension funds	0.009*** (0.003)	0.00 (0.018)

Source: Authors’ calculations. All estimations correspond to rolling regressions. \(MSPE_{r}\) and \(MESPE_{u}\) correspond to “restricted” (Random walk) and “unrestricted” (competing strategies) models. Methodology follows that of Clark and West (2006). Standard errors are in parenthesis
***^, **^, * correspond to significance levels of 1, 5 and 10 %, respectively