Back to Basics: Is Statistical Significance all that Matters?
Nektarios Michail and
Constantinos I. Massouras
No 2014-3, Working Papers from Central Bank of Cyprus
We examine whether statistical significance can convey all the information necessary for the econometrician to judge the performance of his models. We find that in some cases, the t-statistic and the R-squared can be biased due to high correlation between the variables and variables can appear significant even though their correlation with the dependent variable is very low. The solution we propose is a back-to-basics approach: examine correlations between variables and variable variances in order for a correct interpretation of the regression outcome.
Keywords: correlation; statistical significance; hypothesis testing; t test; F test (search for similar items in EconPapers)
JEL-codes: C12 C21 C31 (search for similar items in EconPapers)
Pages: 16 pages
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed
Downloads: (external link)
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
Persistent link: https://EconPapers.repec.org/RePEc:cyb:wpaper:2014-3
Access Statistics for this paper
More papers in Working Papers from Central Bank of Cyprus Contact information at EDIRC.
Bibliographic data for series maintained by Anna Markidou ().