Value Investing via Bayesian Inference

Huefner, Bernd; Rueenaufer, Marcel; Boesch, Martin; Jena, Ernst-Abbe Hochschule

doi:10.2139/ssrn.4324080

Cited by 1 publication

(16 citation statements)

References 59 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This can lead investors into the so‐called value trap, as value stocks may be cheap for a fundamentally justified reason 4 . That is why other contributions refine the B/P strategy by including additional metrics of fundamental performance or different proxies for intrinsic value—like Frankel and Lee (1998), Piotroski (2000), Bird and Gerlach (2003), Mohanram (2005), Piotroski and So (2012), Penman and Reggiani (2013, 2018), Lee (2015), Penman et al (2018), Asness et al (2019), Li and Mohanram (2019), Walkshäusl (2020) and Huefner et al (2021). These studies provide evidence for the predictive ability of fundamental quality for future stock returns on the US market before and after the financial crisis.…”

Section: Combining Research On Valuation Accuracy Valuation Bias and ...mentioning

confidence: 99%

“…A main takeaway from the studies in the field of value investing is that capturing “value” requires more than one dimension (cheapness and quality), that is, B/P is not a sufficient indicator of value. Despite a large history of research on the relation of B/P and returns however, it remains unclear under which conditions a stock should be seen as cheap: cheapness portfolios are constructed using quantile‐based approaches, for example, in Piotroski (2000) or Asness et al (2019), or using absolute boundaries, like in Huefner et al (2021). As a starting point for the model development, we use pricing error research.…”

Section: Combining Research On Valuation Accuracy Valuation Bias and ...mentioning

confidence: 99%

“…As a result, using book value as a proxy for cheapness is a conservative measure. Huefner et al (2021) extend B/P by incorporating short‐term residual income (

{STE}_{0}

) into this equation, so that

V^{normalI, 0}

equals a RIM with no residual income after the precise forecast horizon, leading to the following slightly upgraded modeling variant of intrinsic value:

R_{1}^{STE} goodbreak= \frac{V_{0}^{STE}}{P_{0}} goodbreak- 1, with V_{0}^{STE} goodbreak= B_{0} goodbreak+ \frac{()(, {ROE}_{1} goodbreak- r) B_{0}}{(1 + r)} .

…”

Section: Combining Research On Valuation Accuracy Valuation Bias and ...mentioning

confidence: 99%

“…Our analysis primarily anchors on Frankel and Lee (1998), Gao et al (2019), Rueenaufer (2022), and Huefner et al (2021). As alternatives to B/P, Frankel and Lee (1998), Gao et al (2019), and Huefner et al (2021) provide several point‐estimate measures for cheapness that form benchmarks for the Bayesian workflow proposed by Rueenaufer (2022). Huefner et al (2021) derive a parsimonious quality index based on valuation theory similar to Piotroski (2000)'s FScore and prove to be empirically valid.…”

Section: Introductionmentioning

confidence: 99%

“…As alternatives to B/P, Frankel and Lee (1998), Gao et al (2019), and Huefner et al (2021) provide several point‐estimate measures for cheapness that form benchmarks for the Bayesian workflow proposed by Rueenaufer (2022). Huefner et al (2021) derive a parsimonious quality index based on valuation theory similar to Piotroski (2000)'s FScore and prove to be empirically valid. This quality index complements the cheapness measures in our analysis.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Value investing via Bayesian inference

2023

View full text Add to dashboard Cite

Classic value investing à la Graham & Dodd (Security analysis: The classic, McGrawHill, New York, 1934) focuses on selecting stocks that seem cheap relative to their intrinsic value and fundamental quality. We use Bayesian inference to account for a large amount of uncertainty within intrinsic value estimation. We find that an undervalued‐minus‐overvalued factor that invests in cheap quality stocks and sells expensive junk stocks selected via Bayesian inference yields high risk‐adjusted returns and Sharpe ratios for equal‐weighted portfolios. We also find that using value‐weighted portfolios introduces size‐based dilutions and shifts the focus away from actual quality characteristics like profitability, payout, safety, and past growth. Our findings suggest that while the relative benefit of accounting for uncertainty via Bayesian inference is not large over shorter holding periods, it pays off for investment horizons longer than a month.

show abstract

Section: Combining Research On Valuation Accuracy Valuation Bias and ...mentioning

confidence: 99%

Section: Combining Research On Valuation Accuracy Valuation Bias and ...mentioning

confidence: 99%

“…As a result, using book value as a proxy for cheapness is a conservative measure. Huefner et al (2021) extend B/P by incorporating short‐term residual income (

{STE}_{0}

) into this equation, so that

V^{normalI, 0}

equals a RIM with no residual income after the precise forecast horizon, leading to the following slightly upgraded modeling variant of intrinsic value: