Date of Award


Degree Type


Degree Name

Doctor of Philosophy (PhD)



First Advisor

Dr. Vikas Agarwal - Chair

Second Advisor

Dr. Ajay Subramanian

Third Advisor

Dr. Jason Greene

Fourth Advisor

Dr. Jayant Kale


Yee Cheng Loon’s dissertation abstract Model uncertainty exists in the mutual fund literature. Researchers employ a variety of models to estimate risk-adjusted return, suggesting a lack of consensus as to which model is correct. Model uncertainty makes it difficult to draw clear inference about mutual fund performance persistence. We explicitly account for model uncertainty by using Bayesian model averaging techniques to estimate a fund’s risk-adjusted return. Our approach produces the Bayesian model averaged (BMA) alpha, which is a weighted combination of alphas from individual models. Using BMA alphas, we find evidence of performance persistence in a large sample of US equity, bond and balanced mutual funds. Funds with high BMA alphas subsequently generate higher risk-adjusted returns than funds with low BMA alphas, and the magnitude of outperformance is economically and statistically significant. We also find that mutual fund investors respond to the information content of BMA alphas. High BMA alpha funds receive subsequent cash inflows while low BMA alpha funds experience subsequent cash outflows.