Paper: arXiv 2305.19708

Authors: Battulga Gankhuu

Abstract

In this study, we introduce new estimation methods for the required rate of returns on equity and liabilities of private and public companies using the stochastic dividend discount model (DDM). To estimate the required rate of return on equity, we use the maximum likelihood method, the Bayesian method, and the Kalman filtering. We also provide a method that evaluates the market values of liabilities. We apply the model to a set of firms from the S&P 500 index using historical dividend and price data over a 32–year period. Overall, the suggested methods can be used to estimate the required rate of returns.

Complexity vs Empirical Score

  • Math Complexity: 8.5/10
  • Empirical Rigor: 5.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper employs advanced stochastic models like Markov-Switching VAR, Kalman filtering, and Bayesian estimation, which indicates high mathematical complexity. The empirical application uses 32 years of S&P 500 data to test the methods, showing solid backtesting and data implementation.

Research Flowchart

  flowchart TD
  A["Research Goal: Estimate Required Rate of Return"] --> B["Input: Historical Data"]
  B --> C["Stochastic Dividend Discount Model DDM"]
  C --> D["Estimation Methods"]
  D --> E["Computational Processes"]
  E --> F["Key Findings Outcomes"]
  subgraph D ["Estimation Methods"]
      D1["Maximum Likelihood"]
      D2["Bayesian Method"]
      D3["Kalman Filtering"]
      D4["Liability Valuation"]
  end
  subgraph E ["Computational Processes"]
      E1["Estimate R_e Equity"]
      E2["Estimate R_d Debt"]
      E3["32-Year Application"]
  end
  subgraph F ["Key Findings Outcomes"]
      F1["Validated Methods"]
      F2["Applicable to Private Public Firms"]
      F3["S&P 500 Results"]
  end

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes new estimation methods (ML with regime‑switching, Bayesian, and Kalman filtering) for required rates of return on equity and liabilities using a stochastic dividend discount model.

Source sentence
In this study, we introduce new estimation methods for the required rate of returns on equity and liabilities of private and public companies using the stochastic dividend discount model (DDM).

Assumes 4

  • There are n companies and they will not default in the future. model
    Source sentence
    In this paper, we assume that there are n companies and the companies will not default in the future.
  • Required rates of return are random variables and must satisfy ke > -1, so the DDM is written in exponential form. model
    Source sentence
    ... is an undesirable result. For this reason, we need to write the above DDM equation in the following form Pi,t = exp{˜ke i,t}Pi,t−1 −di,t
  • All companies in the empirical analysis never default. market
    Source sentence
    We assume for all companies, that a default never occurs.
  • Some private companies may not pay dividends; a subset nd (0 ≤ nd ≤ n) of companies pay dividends. model
    Source sentence
    As some private companies may not pay dividends, we suppose that there are nd (0 ≤nd ≤n) companies that pay dividends.

Data

Recognised sources: Refinitiv / LSEG (Datastream, Eikon, Tick History)

Costs

Not applicable The paper reports no trading or execution result.

Finds 2

  • Log required rates of return for Johnson & Johnson and PepsiCo are white‑noise processes, while JPMorgan’s log required rate follows an AR(0)–ARCH(1) model and is covariance‑stationary. statistical
    Source sentence
    the log required rate of returns of Johnson & Johnson and PepsiCo, which are demeaned by intercepts are white noise processes, while the log required rate of return of JPMorgan can be modeled by AR(0)–ARCH(1) process
  • For the three companies, a Bayesian VAR(1) model is appropriate with a zero prior expectation matrix (Π0 = 0). theoretical
    Source sentence
    By using Akaike’s and Schwartz’s information criterion, we deduce that for the three companies, an order of simple VAR(p) process is p = 1.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 7 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.