none

　VaR combines with a variety of risk into a single number. The definition of VaR is: the expected maximum loss or worst loss during a target horizon in a given confidence level. In this paper, we will use two kinds of methods to calculate the C-FaR. In the first method, we assembled 9,600 forecast errors into a pooling data. Then, we sorted the forecast errors into 16 subsamples by the four dimensions. Under the concept of homogeneity, we calculated the C-FaR of each subsample by the percentile method. In the first method, we used two kinds of forecast model, one is the Foster model, the other is AR(4) model. The second method is reverse procedure of the first method, we calculated the C-FaR for each firm first, then created a pooling data of C-FaRs and sorted data by four dimension.

　The empirical result showed that if the firm has low assets, high stock price volatility, and low EPS, than this kind of firm should be more risky. We had significant empirical evidence to show that the higher EPS, the smaller C-FaR is. EPS is the most relevant factor that affects the C-FaR. Moreover, the stock price volatility is the secondary important factor, the higher the stock price volatility, the higher C-FaR will be.

[1]Altman, E. I., “Financial Ratios, Discriminant Analysis and the prediction of corporate bankruptcy”, The Journal of Finance, Vol. XXIII, No.4, September 1968, 589-609.

[2]Amado, P., “The distribution of stock returns: international evidence”, Applied Financial Economics, Vol. 4, 1994, 431-439.

[3]Bekaert G., B. E. Claude, R. H. Campell and T. E. Viskanta, “Distributional characteristics of emerging market returns and asset allocation”, Journal of Portfolio Management, Vol. 24, Winter 1998, 102-115.

[4]Brender, A., “Cash-flow valuation and value at risk”, North American Actuarial Journal, Vol. 3, No.2, 1999, 26-29.

[5]Breuer T., G. Krenn and F. Pistovcak, “Stress Tests, Maximum Loss, and Value at Risk”, July 2002.

[6]Darryll, H., “Evaluation of Value-at-Risk Models Using Historical Data”, Economic Policy Review-Federal Reserve Bank of New York, Vol. 2, April 1996, 39-69.

[7]Duffie D. and J. Pan, “An Overview of Value at Risk”, The Journal of Derivatives, Vol. 4, Spring 1997, 7-49

[8]Foster, G., “Quarterly Accounting Data: Time-Series Properties and Predictive-Ability Results”, The Accounting Review, Vol. 52, No.1, 1977, 1-21.

[9]Henrard M., “Comparison of cash flow maps for value-at-risk”, Journal of Risk, Vol. 3, No.1, Fall 2000, 57-71.

[10]Hull J. and White A., “Value at Risk When Daily Changes in Market Variables are not normally distributed”, The Journal of Derivatives, Vol. 5, Spring 1998, 9-19.

[11]Hull, J. C., Options, Futures, and Other Derivatives, Prentice Hall, 2003.(5 th)

[12]Introduction to business analysis & Valuation, Palepu, Bernard & Healy.

[13]James M. and T. Christopher, “Could Companies Use Value-at-Risk?”, Euromoney, October 1995, 84-86.

[14]Jensen M. C., “Agency costs of free cash flow, corporate finance, and takeovers”, American Economic Review, Vol. 76, 1986, 323-329.

[15]Kataoka, S., “A stochastic programming model”, Econometrica, Vol. 31, 1963, 181-196.

[16]Longin, F. M., “Beyond the VaR”, The Journal of Derivatives, Vol. 8, Summer 2001, 36-48.

[17]Ming-Yuan Leon Li, Hsiou-wei William Lin, “Estimating Value at Risk via Markov Switching ARCH Models-An Empirical Study on Stock Index Returns”, Applied Economics Letters, Vol. 11, 2004, 679.

[18]Philippe Jorion, Value at risk : The New Benchmark for Managing Financial Risk, McGraw-Hill, 2000.(2nd ed).

[19]Roy, A. D., “Safety-first and the holding of assets”, Econometrics, Vol. 20, July 1952, 431-449.

[20]Stein J. C., S. E. Usher, D. LaGattuta and J. Youngen, “A Comparables Approach to Measuring Cashflow-at-Risk for Non-financial Firms”, Journal of Applied Corporate Finance, Vol. 13, No.4, July 2000, 100-109.

[21]Telser, L.G., “Safety first and hedging”, Rev. of Econ, 1955, 410-9.

[22]李吉元 , “風險值限制下最適資產配置”, 國立成功大學財務金融研究所碩士論文, 2003。

[23]張惠渝 , “Optimal asset allocation under VaR constraint”,國立成功大學財務金融研究所碩士論文, 2002。