Variance Decomposition

14,000,000 Leading Edge Experts on the ideXlab platform

Scan Science and Technology

Contact Leading Edge Experts & Companies

Scan Science and Technology

Contact Leading Edge Experts & Companies

The Experts below are selected from a list of 15690 Experts worldwide ranked by ideXlab platform

Dan Segal - One of the best experts on this subject based on the ideXlab platform.

  • a Variance Decomposition primer for accounting research
    Journal of Accounting Auditing & Finance, 2010
    Co-Authors: Jeffrey L Callen, Dan Segal
    Abstract:

    This pedagogical note introduces the accounting-based Variance Decomposition methodology of Vuolteenaho (2002) in a relatively simple format for the edification of accounting scholars and doctoral students who wish to use Variance Decomposition in their research. In addition to presenting an example that explicates the Variance Decomposition approach, we provide well-documented SAS and STATA programs for estimating Variance Decompositions from cross-sectional time-series data.

  • the information content of sec filings and information environment a Variance Decomposition analysis
    The Accounting Review, 2006
    Co-Authors: Jeffrey L Callen, Joshua Livnat, Dan Segal
    Abstract:

    Using the Vuolteenaho (2002) Variance Decomposition methodology, this study assesses the relative value relevance of cash flow, accrual, and expected return news on SEC and preliminary earnings filing dates, as measured by their contribution to the volatility of unexpected returns. Cash flow news is found to be more valuerelevant than accrual news. Although expected return (risk) news is the least valuerelevant, it is significantly correlated with changes in betas and returns at the preliminary and SEC filing dates, indicating association with changes in firm risk and discount rates. This study also documents that these informational components contain less (more) value‐relevant information at the SEC filing date for firms with a higher proportion of long‐term (short‐term) sophisticated investors after controlling for other dimensions of the information environment.

  • do accruals drive firm level stock returns a Variance Decomposition analysis
    Journal of Accounting Research, 2004
    Co-Authors: Jeffrey L Callen, Dan Segal
    Abstract:

    This paper extends the Variance Decomposition framework of Campbell [1991], Campbell and Ammer [1993], and Vuolteenaho [2002] to address the relative value relevance of accrual news, cash flow news, and expected‐return news in driving firm‐level equity returns. The extension is based on the Feltham‐Ohlson [1995, 1996] clean surplus relations. Using three models, this study shows that all three factors, accruals, cash flows, and expected future discount rates are value relevant. Moreover, accrual news is found to significantly dominate expected‐return news in driving firm‐level stock returns. Operating income news is also found to significantly dominate both expected‐return news and free cash flow news in driving firm‐level stock returns. Furthermore, after splitting net income into cash flow and accrual earnings components in the Vuolteenaho model, accrual earnings news and cash flow earnings news are found to equally drive firm‐level stock returns and to dominate expected‐return news. Further disaggregation of the data yields some evidence that accrual earnings news is a more important factor than cash flow earnings news in driving current stock returns. Overall, the three models indicate that changes in expected future accruals are a primary driver, if not the primary driver, of current stock returns.

  • do accruals drive stock returns a Variance Decomposition analysis
    2003
    Co-Authors: Jeffrey L Callen, Dan Segal
    Abstract:

    This paper extends the Variance Decomposition framework of Campbell (1991), Campbell and Ammer (1993) and Vuolteenhao (2002) to address the relative value relevance of accruals news, cash flow news and expected return news in driving firm-level equity returns. The extension is based on the Feltham-Ohlson (1995, 1996) clean surplus relations. Accruals news is found to significantly dominate expected-return news in driving firm-level stock returns. Operating income news is also found to significantly dominate both expected-return news and free cash flow news in driving firm-level stock returns. Furthermore, after splitting net income into cash flow and accrual earnings components in the Vuolteenhao (2000) model, accrual earnings news is found to significantly dominate both expected-return news and cash flow earnings news in driving firm-level stock returns. Overall, these three results indicate that changes in expected future accruals are the primary driver of current stock returns rather than changes in expected future cash flows or future discount rates.

Kirsten Ohm Kyvik - One of the best experts on this subject based on the ideXlab platform.

Jeffrey L Callen - One of the best experts on this subject based on the ideXlab platform.

  • a Variance Decomposition primer for accounting research
    Journal of Accounting Auditing & Finance, 2010
    Co-Authors: Jeffrey L Callen, Dan Segal
    Abstract:

    This pedagogical note introduces the accounting-based Variance Decomposition methodology of Vuolteenaho (2002) in a relatively simple format for the edification of accounting scholars and doctoral students who wish to use Variance Decomposition in their research. In addition to presenting an example that explicates the Variance Decomposition approach, we provide well-documented SAS and STATA programs for estimating Variance Decompositions from cross-sectional time-series data.

  • the information content of sec filings and information environment a Variance Decomposition analysis
    The Accounting Review, 2006
    Co-Authors: Jeffrey L Callen, Joshua Livnat, Dan Segal
    Abstract:

    Using the Vuolteenaho (2002) Variance Decomposition methodology, this study assesses the relative value relevance of cash flow, accrual, and expected return news on SEC and preliminary earnings filing dates, as measured by their contribution to the volatility of unexpected returns. Cash flow news is found to be more valuerelevant than accrual news. Although expected return (risk) news is the least valuerelevant, it is significantly correlated with changes in betas and returns at the preliminary and SEC filing dates, indicating association with changes in firm risk and discount rates. This study also documents that these informational components contain less (more) value‐relevant information at the SEC filing date for firms with a higher proportion of long‐term (short‐term) sophisticated investors after controlling for other dimensions of the information environment.

  • do accruals drive firm level stock returns a Variance Decomposition analysis
    Journal of Accounting Research, 2004
    Co-Authors: Jeffrey L Callen, Dan Segal
    Abstract:

    This paper extends the Variance Decomposition framework of Campbell [1991], Campbell and Ammer [1993], and Vuolteenaho [2002] to address the relative value relevance of accrual news, cash flow news, and expected‐return news in driving firm‐level equity returns. The extension is based on the Feltham‐Ohlson [1995, 1996] clean surplus relations. Using three models, this study shows that all three factors, accruals, cash flows, and expected future discount rates are value relevant. Moreover, accrual news is found to significantly dominate expected‐return news in driving firm‐level stock returns. Operating income news is also found to significantly dominate both expected‐return news and free cash flow news in driving firm‐level stock returns. Furthermore, after splitting net income into cash flow and accrual earnings components in the Vuolteenaho model, accrual earnings news and cash flow earnings news are found to equally drive firm‐level stock returns and to dominate expected‐return news. Further disaggregation of the data yields some evidence that accrual earnings news is a more important factor than cash flow earnings news in driving current stock returns. Overall, the three models indicate that changes in expected future accruals are a primary driver, if not the primary driver, of current stock returns.

  • do accruals drive stock returns a Variance Decomposition analysis
    2003
    Co-Authors: Jeffrey L Callen, Dan Segal
    Abstract:

    This paper extends the Variance Decomposition framework of Campbell (1991), Campbell and Ammer (1993) and Vuolteenhao (2002) to address the relative value relevance of accruals news, cash flow news and expected return news in driving firm-level equity returns. The extension is based on the Feltham-Ohlson (1995, 1996) clean surplus relations. Accruals news is found to significantly dominate expected-return news in driving firm-level stock returns. Operating income news is also found to significantly dominate both expected-return news and free cash flow news in driving firm-level stock returns. Furthermore, after splitting net income into cash flow and accrual earnings components in the Vuolteenhao (2000) model, accrual earnings news is found to significantly dominate both expected-return news and cash flow earnings news in driving firm-level stock returns. Overall, these three results indicate that changes in expected future accruals are the primary driver of current stock returns rather than changes in expected future cash flows or future discount rates.

Mogens Fenger - One of the best experts on this subject based on the ideXlab platform.

Pedro Domingos - One of the best experts on this subject based on the ideXlab platform.

  • a unified bias Variance Decomposition for zero one and squared loss
    National Conference on Artificial Intelligence, 2000
    Co-Authors: Pedro Domingos
    Abstract:

    The bias-Variance Decomposition is a very useful and widely-used tool for understanding machine-learning algorithms. It was originally developed for squared loss. In recent years, several authors have proposed Decompositions for zero-one loss, but each has significant shortcomings. In particular, all of these Decompositions have only an intuitive relationship to the original squared-loss one. In this paper, we define bias and Variance for an arbitrary loss function, and show that the resulting Decomposition specializes to the standard one for the squared-loss case, and to a close relative of Kong and Dietterich’ s (1995) one for the zero-one case. The same Decomposition also applies to variable misclassification costs. We show a number of interesting consequences of the unified definition. For example, Schapire et al.’ s (1997) notion of “margin” can be expressed as a function of the zero-one bias and Variance, making it possible to formally relate a classifier ensemble’s generalization error to the base learner’ s bias and Variance on training examples. Experiments with the unified definition lead to further insights.

  • a unifeid bias Variance Decomposition and its applications
    International Conference on Machine Learning, 2000
    Co-Authors: Pedro Domingos
    Abstract:

    This paper presents a unified bias-Variance Decomposition that is applicable to squared loss, zero-one loss, variable misclassification costs, and other loss functions. The unified Decomposition sheds light on a number of significant issues: the relation between some of the previously-proposed Decompositions for zero-one loss and the original one for squared loss, the relation between bias, Variance and Schapire et al.’s (1997) notion of margin, and the nature of the trade-off between bias and Variance in classification. While the biasVariance behavior of zero-one loss and variable misclassification costs is quite different from that of squared loss, this difference derives directly from the different definitions of loss. We have applied the proposed Decomposition to decision tree learning, instancebased learning and boosting on a large suite of benchmark data sets, and made several significant observations.

  • ICML - A Unifeid Bias-Variance Decomposition and its Applications
    2000
    Co-Authors: Pedro Domingos
    Abstract:

    This paper presents a unified bias-Variance Decomposition that is applicable to squared loss, zero-one loss, variable misclassification costs, and other loss functions. The unified Decomposition sheds light on a number of significant issues: the relation between some of the previously-proposed Decompositions for zero-one loss and the original one for squared loss, the relation between bias, Variance and Schapire et al.’s (1997) notion of margin, and the nature of the trade-off between bias and Variance in classification. While the biasVariance behavior of zero-one loss and variable misclassification costs is quite different from that of squared loss, this difference derives directly from the different definitions of loss. We have applied the proposed Decomposition to decision tree learning, instancebased learning and boosting on a large suite of benchmark data sets, and made several significant observations.

Related terms

Variance Decomposition - 15 days free trial to Access Experts & Abstracts