Using 'Shares' vs. 'Log of Shares' in Fixed-Effect Estimations

25 Pages Posted: 13 Sep 2010

See all articles by Christer Gerdes

Christer Gerdes

Stockholm University - Swedish Institute for Social Research (SOFI)

Abstract

This paper looks at potential implications emerging from including shares as a control variable in fixed effect estimations. By shares I refer to the ratio of a sum of units over another, such as the share of immigrants in a city or school. As will be shown in this paper, a logarithmic transformation of shares has some methodological merits as compared to the use of shares defined as mere ratios. In certain empirical settings the use of the latter might result in coefficient estimates that, spuriously, are statistically significant more often than they should.

Keywords: consistency, Törnqvist index, symmetry, spurious significance

JEL Classification: C23, C29, J10

Suggested Citation

Gerdes, Christer, Using 'Shares' vs. 'Log of Shares' in Fixed-Effect Estimations. Available at SSRN: https://ssrn.com/abstract=1675682 or http://dx.doi.org/10.2139/ssrn.1675682

Christer Gerdes (Contact Author)

Stockholm University - Swedish Institute for Social Research (SOFI) ( email )

Kyrkgatan 43B
SE-106 91 Stockholm
Sweden

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
54
Abstract Views
605
rank
468,332
PlumX Metrics