To θέμα της συγκεκριμένης διπλωματικής εργασίας είναι η βέλτιστη επιλογή χαρτοφυλακίου, η οποία μπορεί να επιτευχθεί μέσω του προσδιορισμού του βέλτιστου μεγέθους του χαρτοφυλακίου. Στo πρώτο κεφάλαιο, που αποτελεί και την εισαγωγή, διατυπώνεται ο αντικειμενικός σκοπός της διπλωματικής εργασίας και αναφέρεται η δομή της εργασίας. Στο δεύτερο κεφάλαιο αναφέρονται συνοπτικά η σύγχρονη θεωρία χαρτοφυλακίου και το Υπόδειγμα της Αποτίμησης Κεφαλαιακών Στοιχείων (CAPM). Στο τρίτο κεφάλαιο αναφέρονται συνοπτικά 4 μελέτες σχετικά με τον προσδιορισμό του βέλτιστου μεγέθους χαρτοφυλακίου. Στο τέταρτο κεφάλαιο παρουσιάζεται η εμπειρική εφαρμογή. Στο πέμπτο κεφάλαιο παρουσιάζονται τα εμπειρικά αποτελέσματα της ανάλυσης. Στο έκτο κεφάλαιο διατυπώνονται τα συμπεράσματα που προκύπτουν από την ανάλυση και, επιπλέον, αναφέρεται η δυνατότητα για μελλοντική περαιτέρω έρευνα. / The subject of this diploma thesis is the optimal portfolio allocation, which can be achieved through the assignment of the optimal portfolio size. In the first chapter, which consists the introduction, the subjective purpose and the structure of the thesis are given. In the second chapter, the Modern Portfolio Theory and the Capital Asset Pricing Model are referred in brief. In the third chapter, 4 studies relative to the assignment of the optimal portfolio size are referred briefly. In the fourth chapter, the empirical application is presented. In the fifth chapter, the empirical results of the analysis are also presented. Finally, in the sixth chapter, the conclusions are given and, additionally, the possibility for future further research is referred.

Made available in DSpace on 2014-12-17T13:53:33Z (GMT). No. of bitstreams: 1 LuizCSJ_DISSERT.pdf: 1251184 bytes, checksum: 11adb0eaeb2b09775607dded39ab4867 (MD5) Previous issue date: 2012-08-27 / The objective is to analyze the relationship between risk and number of stocks of a portfolio for an individual investor when stocks are chosen by "naive strategy". For this, we carried out an experiment in which individuals select actions to reproduce this relationship. 126 participants were informed that the risk of first choice would be an asset average of all standard deviations of the portfolios consist of a single asset, and the same procedure should be used for portfolios composed of two, three and so on, up to 30 actions . They selected the assets they want in their portfolios without the support of a financial analysis. For comparison we also tested a hypothetical simulation of 126 investors who selected shares the same universe, through a random number generator. Thus, each real participant is compensated for random hypothetical investor facing the same opportunity. Patterns were observed in the portfolios of individual participants, characterizing the curves for the components of the samples. Because these groupings are somewhat arbitrary, it was used a more objective measure of behavior: a simple linear regression for each participant, in order to predict the variance of the portfolio depending on the number of assets. In addition, we conducted a pooled regression on all observations by analyzing cross-section. The result of pattern occurs on average but not for most individuals, many of which effectively "de-diversify" when adding seemingly random bonds. Furthermore, the results are slightly worse using a random number generator. This finding challenges the belief that only a small number of titles is necessary for diversification and shows that there is only applicable to a large sample. The implications are important since many individual investors holding few stocks in their portfolios / Objetiva-se neste trabalho analisar a rela??o entre o risco e o n?mero de a??es de uma carteira para um investidor individual quando as a??es s?o escolhidas atrav?s da estrat?gia ing?nua . Para isso, realizou-se um experimento em que indiv?duos selecionam a??es para reproduzir essa rela??o. 126 participantes foram informados de que o risco do primeiro ativo escolhido seria uma m?dia entre todos os desvios padr?es das carteiras compostas por um ?nico ativo, e o mesmo procedimento deveria ser usado para as carteiras compostas por duas, tr?s e assim por diante, at? 30 a??es. Eles selecionaram os ativos que queriam em suas carteiras sem o suporte de uma an?lise financeira. Para fins de compara??o, tamb?m foi realizada uma simula??o hipot?tica de 126 investidores que selecionaram a??es de um mesmo universo, atrav?s de um gerador de n?meros aleat?rios. Assim, cada participante real pode ser comparado por um investidor hipot?tico aleat?rio frente a mesma oportunidade. Foram observados padr?es nas carteiras dos participantes individuais, caracterizando as curvas para as componentes das amostras. Como esses agrupamentos s?o subjetivos, utilizou-se posteriormente uma medida mais objetiva de comportamento: uma regress?o linear simples para cada participante, com o intuito de predizer a vari?ncia da carteira em fun??o do inverso do n?mero de ativos. Al?m disso, foi realizada uma regress?o agrupada sobre todas as observa??es, atrav?s de an?lise cross-section. A rela??o exponencial negativa ocorre, em m?dia, mas n?o para a maioria dos indiv?duos, muitos dos quais efetivamente desdiversificam quando adicionam t?tulos aparentemente aleat?rios. Os resultados alcan?ados s?o ligeiramente piores usando-se um gerador de n?mero aleat?rio. Esta descoberta desafia a cren?a de que apenas um pequeno n?mero de t?tulos ? necess?rio para que haja diversifica??o e mostra que ? aplic?vel apenas a uma amostra grande. As implica??es s?o importantes uma vez que muitos investidores individuais mantem poucas a??es em suas carteiras