Towards the Estimation of an Efficient Benchmark Portfolio: The Case of Croatian Emerging Market

Abstract

Abstract:The fact that cap-weighted indices provide an ineffi cient risk-return trade-off is well known today. Various research approaches evolved suggesting alternative to cap-weighting in an effort to come up with a more effi cient market index benchmark. In this paper we aim to use such an approach and focus on the Croatian capital market. We apply statistical shrinkage method suggested by Ledoit and Wolf (2004) to estimate the covariance matrix and follow the work of Amenc et al. (2011) to obtain estimates of expected returns that rely on risk-return trade-off. Empirical fi ndings for the proposed portfolio optimization include out-of-sample and robustness testing. This way we compare the performance of the capital-weighted benchmark to the alternative and ensure that consistency is achieved in different volatility environments. Research fi ndings do not seem to support relevant research results for the developed markets but rather complement earlier research (Zoričić et al., 2014).

Factor-Based Optimization of a Fundamentally-Weighted Portfolio in the Illiquid and Undeveloped Stock Market

“…Therefore, unlike in the developed markets, equal weighting (naïve strategy maximizing deconcentration) does not outperform the cap-weighted benchmark index. On the contrary, it performs much worse both in terms of risk (measured by volatility) and return as reported in Dolinar et al (2017). It can be argued, based on the empirical evidence, that in these specific market conditions additional deconcentration leads to unnecessary exposure to unrewarded risk factors.…”

“…Amenc et al (2006Amenc et al ( , 2011a clearly present that poor diversification reduces efficiency and can be traced to a high concentration of market-cap-weighted benchmarks. Taking this into account helps explain why it is much more difficult to outperform the benchmark index in the Croatian stock market than in the developed markets as reported by Dolinar et al (2017) and Zoričić et al (2018a). It cannot be achieved by naïve diversification techniques (such as equal weighting leading to maximum deconcentration) as in the case of the developed markets.…”

Kvantitativna istraživanja Zagrebačke burze

“…Svi portfelji su bili udaljeni od eÞ kasne granice i nisu ostvarivali maksimalne koristi diverziÞ kacije. Analiza se nastavila u Dolinar, Zori i i Kožul (2017), koji uspore uju konstrukciju osnovnog indeksa (engl. benchmark) temeljem nekoliko statisti kih metoda procjene matrice varijanci i kovarijanci i uspore uju performanse tako konstruiranih indeksa s CROBEX-om.…”

Application of semi-deviation as a proxy for the expected return estimation in the Croatian equity market

“…The paper by Zoričić et al (2018a), for instance, demonstrated the importance of conducting research in the illiquid and undeveloped Croatian stock market since their research findings showed that it is possible to estimate volatilities and correlations of stocks (albeit without success regarding outperforming the benchmark index) regardless of such specific environment. Bearing this in mind the research results focusing on the improvement of the expected return estimation can further shed light on the failure of Maximum Sharpe Ratio portfolio estimation attempt by Dolinar et al (2017) and provide insight on how to improve this strand of research in the future. The ultimate goal of such research efforts is to offer an efficient alternative to cap-weighted benchmark even in markets usually found unappealing to major international institutional investors due to its specific characteristics.…”