Discussion Paper
No. 2011-14 | May 26, 2011
Massimiliano Caporin and Francesco Lisi
Comparing and Selecting Performance Measures Using Rank Correlations

Abstract

The financial economics literature proposes dozens of performance measures to be used, for instance, to compare, analyze, rank and select assets. There is thus a problem: which measures should be considered? The authors extend the current literature by comparing a large set of performance measures over more than one thousand of equities included in the Standard & Poor’s 1500 index. They evaluate performance measures by mean of rank correlations, exploiting the possible dynamic evolution of the rank correlations, and proposing a method for the identification of the subset of measures which are not equivalent. Their empirical study highlights that recent and more flexible measures provide different asset ranks compared to classical approaches, and that the set of equivalent performance measures is not stable over time.

Data Set

JEL Classification:

C10, C40, G11

Links

Cite As

[Please cite the corresponding journal article] Massimiliano Caporin and Francesco Lisi (2011). Comparing and Selecting Performance Measures Using Rank Correlations. Economics Discussion Papers, No 2011-14, Kiel Institute for the World Economy. http://www.economics-ejournal.org/economics/discussionpapers/2011-14


Comments and Questions



Anonymous - Referee Report 1
June 06, 2011 - 10:10
See attached file
[ Download attached file ]

Massimiliano Caporin - Reply to Referee 1
June 07, 2011 - 10:00
Many thanks for the comments, we will accomodate all of them in the paper revision

Anonymous - Referee Report 2
July 04, 2011 - 08:41
See attached file
[ Download attached file ]

Massimiliano Caporin - Reply to Referee 2
July 18, 2011 - 12:38
Many thanks for the comments. We took them into account, and we are preparing a refined version of the paper.With respect to your first comment, you are right, the critical values are really associated to the sample size. In turn, this, in our case, corresponds to the number of assets in the study, and not to the length of the time series. In fact, we are computing the rank correlation between two measures of performance computed for all assets. Furthermore, within an equity screening program, the number of assets under study is generally large, thus reducing the possible problem you correctly evidence.