The effect of investor sentiment on stock market returns and volatility: An application on Borsa Istanbul Indices

This thesis investigates the effect of investor sentiment on stock market returns and volatility. Accordingly, the study constructs an Investor Sentiment Index using daily data from 2010 to 2023 and explores the link between sentiment and stock market indices. Principal Component Analysis (PCA) is employed in the construction of the index, while its effects on returns and volatility are analyzed through the Autoregressive Moving Average with Exogenous Variables (ARMAX) and Exponential Generalized Autoregressive Conditional Heteroskedasticity (EGARCH) models. The findings indicate that investor sentiment has a significant negative effect on returns and a significant positive effect on the conditional volatility of Borsa İstanbul benchmark and sectoral indices. Sub-sample analyses also reveal that investor sentiment played a significant role in stock markets before the Covid-19 period, whereas its influence appears to have weakened in the post Covid-19 period. These results suggest that the effect of irrational decisions driven by non-fundamental information on the markets diminished following periods of crisis. In other words, the noisy trading activity receded into the background and investment decisions became more rational. Lastly, performance analyses using various performance metrics generally indicate that investment performance tends to be low to medium in the sectors where investor sentiment generates high volatility. On the other side, performance is medium to high in sectors where investor sentiment generates low volatility.