Data-Driven Models
Data-Driven Models
Empirical forecasting models · Sources
Primary papers, model variants, source notes, and review signals behind the ARDL / bounds testing page.
Reference material used for orientation; read primary and academic sources first when claims conflict.
[S1] Reference
Pesaran, Shin, and Smith (2001) introduced the bounds-testing approach with F and t critical value tables for five deterministic cases.
Reference
[S2] Reference
Pesaran and Shin (1999) proved that ARDL-based long-run estimates are consistent and asymptotically normal even with endogenous regressors, provided lag orders are adequate.
Reference
[S3] Reference
Narayan (2005) tabulated small-sample critical values for the bounds test with T = 30 to 80.
Reference
[S4] Reference
Kripfganz and Schneider (2020) provided updated critical values and p-values accounting for finite-sample adjustments and additional deterministic components.
Reference
[S5] Reference
Shin, Yu, and Greenwood-Nimmo (2014) developed the Nonlinear ARDL (NARDL) for testing asymmetric cointegration.
Reference
[S6] Reference
Banerjee, Dolado, and Mestre (1998) proposed the t-test version of the error-correction-based cointegration test.
Reference
[S7] Reference
McNown, Sam, and Goh (2018) augmented the PSS bounds test with an additional F-test on the regressors' lagged levels to avoid degenerate cases.
Reference
Continue reading
Open the concept, data series, policy setting, or neighboring model that anchors this page.