No Need to Run Millions of Regressions

Jan-Egbert Sturm

No 288, CESifo Working Paper Series from CESifo

Abstract: We argue that in modelling cross-country growth models one should first identify so-called outlying observations. For the data set of Sala-i-Martin, we use the least median of squares (LMS) estimator to identify outliers. As LMS is not suited for inference, we then use reweighted least squares (RLS) for our cross-country growth models. We identify 27 variables that are significantly related to economic growth. Subsequently, applying Sala-i-Martin's approach for the data set without outliers hardly reveals any additional information. Variables that are insignificant according to the RLS method are generally not significantly related to economic growth under the Sala-i-Martin approach.

Keywords: Sensitivity analysis; outliers; economic growth (search for similar items in EconPapers)
JEL-codes: C21 C52 O40 (search for similar items in EconPapers)
Date: 2000
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (5)

Downloads: (external link)
https://www.cesifo.org/DocDL/cesifo_wp288.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ces:ceswps:_288

Access Statistics for this paper

More papers in CESifo Working Paper Series from CESifo Contact information at EDIRC.
Bibliographic data for series maintained by Klaus Wohlrabe ().