The Resampled Method To Improve The Efficient Frontier In Minimizing Estimation Error: The Case Of Malaysia Equity Portfolios

Abu Mansor, Siti Nurleena (2006) The Resampled Method To Improve The Efficient Frontier In Minimizing Estimation Error: The Case Of Malaysia Equity Portfolios. Masters thesis, Universiti Sains Malaysia.

Preview

PDF Download (982kB) | Preview

Abstract

Since the work of Markowitz (1952), Mean-Variance (MV) analysis has been a central focus of financial economics. MV theory is still used as a foundation of the modern finance for asset management. Problems involving quadratic objective functions or loss functions generally incorporate a MV analysis. However, estimation error is known to have huge impact on MV optimized portfolios, which is one of the primary reasons to make standard Markowitz optimization unfeasible in practice. Therefore, in this study we improved the efficient frontier using a relatively new approach introduced by Michaud (1998), i.e., the resampled efficient. Michaud argues that the limitations of MV effiCiency in practice generally derive from a lack of statistical understanding of MV optimization. We support his statistical view of MV optimization that leads to new procedures which can reduce estimation error. Bermula dengan hasil kerja Markowitz (1952), analisis "Mean-Variance" (MV) telah menjadi fokus utama dalam analisis ekonomi kewangan. Kini, teori MV digunakan sebagai asas dalam bidang kewangan moden bagi pengurusan asset. Permasalahan yang melibatkan fungsi objektif kuadratik atau fungsi menyusut, secara amnya turut menggabungkan penggunaan ailalisis MV. Namun, ralat penganggaran memberi impak yang besar terhadap potfo!io yang telah dioptimumkan oleh analisis MV, di mana ia merupakan salah satu sebab utama menjadikan piawai pengoptimuman Markowitz tidak lagi dapat digunakan secara praktikal. Oleh itu, kajian ini memperbalki sempadan cekap menggunakan pendekatan baru yang diperkenalkan oleh Michaud (1998) iaitu pensampelan-semula cekap. Michaud membantah penggunaan kaedah MV kerana secara praktikal batasan "MV efficiency" wujud disebabkan oleh kurangnya pemahaman statistik daripada proses pengoptimuman MV. Kita turut menyokong pandangannya yang seterusnya menjurus ke arah satu kaedah baru yang boleh mengurangkan kesan ralat penganggaran.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > QA1 Mathematics (General)
Divisions:	Pusat Pengajian Sains Matematik (School of Mathematical Sciences)
Depositing User:	HJ Hazwani Jamaluddin
Date Deposited:	28 Nov 2016 08:17
Last Modified:	28 Nov 2016 08:17
URI:	http://eprints.usm.my/id/eprint/31211

Actions (login required)

View Item