Portfolio efficiency analysis with SFA: the case of PSI-20 companies

Abstract

This study aimed to assess the technical efficiency (TE) of individual companies and their respective sectors that are traded on the Portuguese stock market. We accomplished this by combining the internal input variables (e.g., 'market value and return') with exogenous variables (e.g., 'interest income', 'depreciation', 'cost of goods', 'employees' and 'net sales') into a Stochastic Frontier Analysis (SFA) model. The TE of the PSI-20 (Portuguese Stock Index) was estimated using factors that affect efficiency variability. The main advantage of using the SFA approach is its potential to discriminate between measurement error and systematic inefficiencies in the estimation process. The results demonstrated that TE is higher for enterprises in the industrial, construction and distribution sectors, whereas the commercial banking sector has the lowest TE scores. The 'employees' and 'depreciation' are the variables which most contribute to stock market inefficiency. KEYWORDS Stochastic Frontier Analysis; stock market efficiency; PSI-20; portfolio efficiency JEL CLASSIFICATION C22; G15

Using stochastic frontier analysis instead of data envelopment analysis in modelling investment performance

“…One intriguing empirical finding is that there was very little evidence of technical inefficiency in our SFA models. This finding is similar to that of Ferreira & Oliveira (2016) and may be an indication that, for our data, the market is good at estimating both the mean return and the volatility of assets. It may also be a limitation of modelling with one input or a feature of stocks drawn from market indices.…”

“…Estimation risk is the tendency of statistics like the sample mean and standard deviation to underestimate small values and overestimate large ones when we have several values. As far as we know, no previous frontier-fitting method has dealt with estimation risk, and SFA studies for assets (Santos et al, 2005;Ferreira & Oliveira, 2016) do not show the frontier to let us check plausibility of fit. We resolve the issue by introducing shrinkage estimators instead of the sample ones.…”

“…For more than 20 years data envelopment analysis (DEA) has been accepted as the method to fit frontiers and estimate efficiencies of various financial assets (see, for example, Liu et al (2015)). We know of only two attempts to use stochastic frontier analysis (SFA), its close relative, to fit frontier to a set of assets (Santos et al, 2005;Ferreira & Oliveira, 2016) (though it is used more broadly in finance (Daraio et al, 2020)). This is surprising.…”

Diversidade do conselho de administração das empresas cotadas no psi-20

“…Criado em 31 de dezembro de 1992 a partir de um valor base de 3000 pontos de índice, o Portuguese Stock Index (PSI-20) representa não só o principal índice da Euronext 19 Lisboa, como também o principal índice de referência desta "praça" financeira. De acordo com Ferreira & Oliveira (2016), o PSI-20 funciona como indicador de benchmark para outros produtos financeiros e apresenta uma dupla finalidade: (i) serve de indicador da evolução do mercado de capitais português e (ii) atua como base de negociação para contratos de futuros e opções.…”

Effect of the ICT Ecosystem Structure on the Sustainable Growth of ICT Firms: A Metafrontier Analysis on China, South Korea, the United States, and Japan

“…In measuring the firms' efficiency, we choose variables based on the theoretical background. We use net sales for the output variable (e.g., see [8,16,18,[24][25][26][27]), the total capital for K (e.g., see [8,16,17]), the number of employees for L (e.g., see [8,[16][17][18][24][25][26]), and the cost of revenue for M (e.g., see [17,24,28,29]). These are available through the ThomsonONE database [7] and are standardized to compare data from firms with different accounting rules.…”