Stock-return predictability and model uncertainty / Doron Avramov.

Format:

Book

Manuscript

Microformat

Thesis/Dissertation

Author/Creator:

Avramov, Doron.

Contributor:

Stambaugh, Rob, advisor.

University of Pennsylvania.

Language:

English

Subjects (All):

Penn dissertations--Finance.

Finance--Penn dissertations.

Penn dissertations--Managerial science and applied economics.

Managerial science and applied economics--Penn dissertations.

Local Subjects:

Penn dissertations--Finance.

Finance--Penn dissertations.

Penn dissertations--Managerial science and applied economics.

Managerial science and applied economics--Penn dissertations.

Physical Description:

vii, 85 pages : illustrations ; 29 cm

Production:

2000.

Summary:

We investigate the implications of uncertainty about the return-forecasting model for the investment opportunity set. Asset allocations are computed through various approaches that differ in their treatment of model uncertainty. The optimal portfolio choices can differ to economically significant degrees, especially for short-horizon high risk-tolerance investors. We decompose the variance of predicted stock returns into several components, including model uncertainty and parameter uncertainty. The model-uncertainty component can be significantly higher than the parameter-uncertainty component, especially when predictive variables, such as dividend yield and book-to-market, are at their recently observed levels, and there is substantial prior uncertainty about whether returns are predictable.

Notes:

Adviser: Rob Stambaugh.

Thesis (Ph.D. in Finance) -- University of Pennsylvania, 2000.

Includes bibliographical references.

Local Notes:

University Microfilms order no.: 99-76397.

OCLC:

187484901