The Model Specification Problem from a Probabilistic Reduction Perspective

Spanos, Aris; McGuirk, Anya M.

doi:10.1111/0002-9092.00262

Cited by 26 publications

(20 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…See Suppes 1966. 5 Spanos and McGuirk have given a detailed analysis of "mis-specification testing," which is a set of tests designed to detect which of a family of formal models is appropriate to the data under analysis (Spanos & McGuirk, 2001). 6 Deborah Mayo's work on statistical inference takes an approach focused on testing, but focuses on severe tests as criteria for rigorous learning through experimentation (Mayo, 2018).…”

Section: Theory Testing and Confirmationmentioning

confidence: 99%

Expanding theory testing in general relativity: LIGO and parametrized theories

Patton

2020

Studies in History and Philosophy of Science Part B: Studies in

View full text Add to dashboard Cite

a b s t r a c tThe multiple detections of gravitational waves by LIGO (the Laser Interferometer Gravitational-Wave Observatory), operated by Caltech and MIT, have been acclaimed as confirming Einstein's prediction, a century ago, that gravitational waves propagating as ripples in spacetime would be detected. Yunes and Pretorius (2009) investigate whether LIGO's template-based searches encode fundamental assumptions, especially the assumption that the background theory of general relativity is an accurate description of the phenomena detected in the search. They construct the parametrized post-Einsteinian (ppE) framework in response, which broadens those assumptions and allows for wider testing under more flexible assumptions. Their methods are consistent with work on confirmation and testing found in Carnap (1936), Hempel (1969), and Stein (1992, 1994, with the following principles in common: that confirmation is distinct from testing, and that, counterintuitively, revising a theory's formal basis can make it more broadly empirically testable. These views encourage a method according to which theories can be made abstract, to define families of general structures for the purpose of testing. With the development of the ppE framework and related approaches, multi-messenger astronomy is a catalyst for deep reasoning about the limits and potential of the theoretical framework of general relativity.

show abstract

Section: Theory Testing and Confirmationmentioning

confidence: 99%

Expanding theory testing in general relativity: LIGO and parametrized theories

Patton

2020

Studies in History and Philosophy of Science Part B: Studies in

View full text Add to dashboard Cite

show abstract

“…In particular, the nominal error probabilities are likely to be very different from the actual ones, rendering the inference results unreliable. Large discrepancies can easily arise in practice even in cases of “minor” departures from the model assumptions; see Spanos and McGuirk ().…”

Section: Statistical Adequacy and Its Role In Inferencementioning

confidence: 99%

“…For instance, the most widely invoked robustness claim relates to dealing with departures from the homoskedasticity and no‐autocorrelation assumptions (see Table ), by using OLS estimators in conjunction with robust standard errors (SEs), known as heteroskedasticity/autocorrelation consistent (HAC) SE; see Hansen () and Greene (). It turns out, however, that the use of such robust SEs often gives rise to unreliable inferences because the relevant actual error (types I and II) probabilities are very different from the nominal ones for a given sample size n and the discrepancy does not improve as n increases; see Spanos and McGuirk ().…”

Section: Traditional Perspective On Misspecificationmentioning

confidence: 99%

Mis‐specification Testing in Retrospect

Spanos

2017

Journal of Economic Surveys

Self Cite

View full text Add to dashboard Cite

The primary objective of this paper is threefold. First, to undertake a retrospective view of Mis-Specification (M-S) testing, going back to the early 20th century, with a view to (i) place it in the broader context of modeling and inference and (ii) bring out some of its special features. Second, to call into question several widely used arguments undermining the importance of M-S testing in favor of relying on weak probabilistic assumptions in conjunction with generic robustness claims and asymptotic inference. Third, to bring out the crucial role of M-S testing in securing trustworthy inference results. This is achieved by extending/modifying Fisher's statistical framework with a view to draw a clear line between the modeling and the inference facets of statistical induction. The proposed framework untangles the statistical from the substantive (structural) model and focuses on how to secure the adequacy of the statistical model before probing for substantive adequacy. A case is made for using joint M-S tests based on custom-built auxiliary regressions with a view to enhance the effectiveness and reliability of probing for potential statistical misspecifications.

show abstract

“…This is because when any of the statistical assumptions are invalid for data Z 0 , inferences based on the estimated model are often unreliable because the nominal and actual error probabilities are likely to be di¤erent. The surest way to lead an inference astray is to apply a :05 signi…cance test when the actual type I error is closer to 1:0; see Spanos and McGuirk (2001).…”

Section: The European Cvar Perspectivementioning

confidence: 99%

“…It is important to stress that respeci…cation in this context does not refer to 'error-…xing'widely used in traditional textbook econometrics, but postulating more appropriate probabilistic structure for fZ t ; t2Ng that would render data Z 0 a typical realization thereof. This is because the traditional 'error-…xing' strategies, such as error-autocorrelation correction and heteroskedasticity/autocorrelation consistent standard errors (see Kennedy, 2008), often render statistical unreliability worse, not better; see Spanos and McGuirk (2001), Spanos (2006a).…”

Section: Can the Two Perspectives Be Reconciled?mentioning

confidence: 99%

The Pre-Eminence of Theory versus the European CVAR Perspective in Macroeconometric Modeling

Spanos

2009

Economics

Self Cite

View full text Add to dashboard Cite

The primary aim of the paper is to place current methodological discussions in macroeconometric modeling contrasting the 'theory first' versus the 'data first' perspectives in the context of a broader methodological framework with a view to constructively appraise them. In particular, the paper focuses on Colander's argument in his paper 'Economists, Incentives, Judgement, and the European CVAR Approach to Macroeconometrics' contrasting two different perspectives in Europe and the US that are currently dominating empirical macroeconometric modeling and delves deeper into their methodological/philosophical underpinnings. It is argued that the key to establishing a constructive dialogue between them is provided by a better understanding of the role of data in modern statistical inference, and how that relates to the centuries old issue of the realisticness of economic theories. --Econometric methodology,'general-to-specific',pre-eminence of theory,cointegrated VAR,statistical adequacy,realisticness of a theory

show abstract

The Model Specification Problem from a Probabilistic Reduction Perspective

Cited by 26 publications

References 7 publications

Expanding theory testing in general relativity: LIGO and parametrized theories

Expanding theory testing in general relativity: LIGO and parametrized theories

Mis‐specification Testing in Retrospect

The Pre-Eminence of Theory versus the European CVAR Perspective in Macroeconometric Modeling

Contact Info

Product

Resources

About