CoChat
Sign Up
Cited by 962Economic Growth and ProductivityEconomic Growth and DevelopmentMonetary Policy and Economic Impact

I Just Ran Four Million Regressions

Open access
Sala-i-Martin, Xavier·1997·National Bureau of Economic Research
DOI 10.3386/w6252
Open this paper in CoChat — free account

Abstract

In this paper I try to move away from the Extreme Bounds method of identifying" Instead of analyzing the" extreme bounds of the estimates of the coefficient of a particular variable distribution. My claim in this paper is that, if we do this, the picture emerging from the" empirical growth literature is not the pessimistic Robust" that we get with the" extreme bound analysis. Instead, we find that a substantial number of variables can be found" to be strongly related to growth.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3386/w6252

Cites

12 of 12 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Extreme bounds analysis has been used in a wide variety of contexts to evaluate factors driving political and economic outcomes.

    “Extreme bounds analysis (EBA) has been used in a wide variety of contexts to evaluate factors driving a number of political and economic outcomes”

    From Correlates of Voter Turnout (2023) · cites this paper as Sala-i-Martin, 1997

    The Introduction (p. 5) describes the use of extreme bounds analysis to assess which variables are robustly related to economic growth, and the Results (p. 11) apply it to 59 variables. The paper does not establish its use across a wide variety of contexts or to evaluate political outcomes; political measures appear here as possible predictors of growth, not as outcomes. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • The two most common EBA decision criteria are those proposed by Leamer (1983) and Sala-i-Martin (1997).

    “To determine robust turnout predictors, we used the two most common EBA decision criteria proposed by Leamer (1983) and Sala-i-Martin (1997)”

    From Correlates of Voter Turnout (2023) · cites this paper as Sala-i-Martin (1997)

    The Introduction (p. 5) describes Leamer’s extreme-bounds test, and “Moving Away from Extreme Tests” (p. 6) proposes Sala-i-Martin’s alternative for judging robustness. The paper thus supports the attribution of the two criteria, but it does not establish that they are the two most common EBA decision criteria. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Sala-i-Martin finds Leamer's standard to be overly restrictive in most cases.

    “Sala-i-Martin (1997) finds Leamer's standard to be overly restrictive in most cases”

    From Correlates of Voter Turnout (2023) · cites this paper as Sala-i-Martin (1997)

  • Sala-i-Martin proposes to conclude a variable is robustly related to the outcome when a large percentage-say 90-95%-of the coefficient's distribution is either above or below zero.

    “Sala-i-Martin (1997) proposes to look at the entire distribution of coefficients and conclude a variable is robustly related to the outcome variable when a large percentage-say 90-95%-of the coefficient's distribution is either above or below zero.”

    From Correlates of Voter Turnout (2023) · cites this paper as Sala-i-Martin (1997)

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 2

  1. Leamer, Edward E. (1983). "Let's take the con out of econometrics", American Economic Review, 73, 3, (March), 31-43
  2. Leamer, Edward E. (1985). "Sensitivity Analysis Would Help", American Economic Review, 75, 5, (June), 31-43

Cited by

Sorted by citations

Related

Authors
Sala-i-Martin, X.
Venue
National Bureau of Economic Research
Publisher
National Bureau of Economic Research
Published
1997-11
DOI
10.3386/w6252
OpenAlex
W1913804012
Cited by
960
References
12
Citations by year
2026: 24 · 2025: 20 · 2024: 22 · 2023: 14 · 2022: 24 · 2021: 38 · 2020: 19 · 2019: 24 · 2018: 38 · 2017: 29 · 2016: 27 · 2015: 21 · 2014: 51 · 2013: 51 · 2012: 47
Type
report
Language
en
Open access
Locations
  • National Bureau of Economic Research (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • Repositori digital de la UPF (Universitat Pompeu Fabra) (submittedVersion, cc-by-nc-nd)
  • National Bureau of Economic Research (submittedVersion)
  • RECERCAT (Consorci de Serveis Universitaris de Catalunya) (submittedVersion, cc-by-nc-nd)
Topics
  • Social Sciences › Economics, Econometrics and Finance › Economics and Econometrics › Economic Growth and Productivity
  • Physical Sciences › Computer Science › Information Systems › Economic Growth and Development
  • Social Sciences › Economics, Econometrics and Finance › General Economics, Econometrics and Finance › Monetary Policy and Economic Impact
Keywords
economic growth determinants, growth regressions, growth determinants

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review