避險基金的主要特性在於具有多樣化、靈活彈性的交易手法策略，而一切的報酬都也伴隨著資產損失的風險，一旦經理人操作失利導致資產下跌，被迫撤銷避險基金，連帶影響著投資者的資金虧損。因此，需要對產業有著一定的瞭解， 以及辨別其中風險大小的敏銳性。對於投資者需承受著如此大的不確定性投資風險，瞭解其撤銷事件發生的因素並推測出將來發生的機率很重要。

在這樣的議題，此篇應用存活分析的統計方法建立傳統的Cox複迴歸模型。然而金融實務上，每筆避險基金的波動趨勢可能會因為相同屬性等類似的操作手法，同時面臨一些共同的風險和衝擊，亦或是在市場上交易時間的相關性問題，都是我們在建立模型時值得考慮的因素。本研究中討論了Copula模型的理論，藉此考慮到時間與時間相關的問題，再經由Cox複迴歸模型和Copula模型各自的分析結果，比較之間模型估計的準確度，期望在考慮更周全的實際原因，能預測更精確、合理化。

In the stock market, hedge fund is popular with the intention of lower overall risk by flexible and various strategies. However, these hedge funds are not risk free. The term of "hedging" means the practice of attempting to reduce risk. Hedge fund failure leads to significant losses, so it is wondering what factors of investment styles may affect the fund risk.

In this paper, we discuss the survival analysis in the Hedge fund data by Lipper/TASS database. As mentioned about survival analysis, Cox proportional hazards model is common approach to predict the risk. However, some of independent theoretical assumptions in Cox model are usually violated in real trading environment. In financial industry, there may be a correlation in proxy and observed times. For that reasons, use Copula model for the dependence structure to improve the performance of prediction.

[1] Belloc, N. B., and Breslow, L. Relationship of physical health status and health practices. Preventive medicine 1, 3 (1972), 409–421.
[2] Breiman, L., Friedman, J. H., Olshen, R. A., and Stone, C. J. Classification and regression trees. Taylor & Francis, 1984.
[3] Brown, S. J., Goetzmann, W. N., and Park, J. Careers and survival: Competition and risk in the hedge fund and cta industry. The Journal of Finance 56, 5 (2001), 1869–1886.
[4] Connor, G., and Woo, M. An introduction to hedge funds. Financial Markets Group, London School of Economics and Political Science, 2004.
[5] Cox, D. R. Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological) 34, 2 (1972), 187–202.
[6] Cox, D. R., and Oakes, D. Analysis of survival data, vol. 21. CRC press, 1984.
[7] Emura, T., and Chen, Y.-H. Gene selection for survival data under dependent censoring: a copula-based approach. Statistical methods in medical research 25, 6 (2016), 2840–2857.
[8] Gehan, E. A. A generalized wilcoxon test for comparing arbitrarily singly-censored samples. Biometrika 52, 1-2 (1965), 203–224.
[9] Gregoriou, G. N. Hedge fund survival lifetimes. Journal of Asset Management 3, 3 (2002), 237–252.
[10] Harrell Jr, F. E., Lee, K. L., and Mark, D. B. Multivariable prognostic models: issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors. Statistics in medicine 15, 4 (1996), 361–387.
[11] Joe, H., and Xu, J. J. The estimation method of inference functions for margins for multivariate models.
[12] Kalbfleisch, J. D., and Prentice, R. L. The statistical analysis of failure time data, vol. 360. John Wiley & Sons, 2011.
[13] Klein, J. P., and Moeschberger, M. L. Survival analysis: techniques for censored and truncated data. Springer Science & Business Media, 2006.
[14] Lawless, J. F., and Yilmaz, Y. E. Semiparametric estimation in copula models for bivariate sequential survival times. Biometrical Journal 53, 5 (2011), 779–796.
[15] LeBlanc, M., and Crowley, J. Relative risk trees for censored survival data. Biometrics (1992), 411–425.
[16] Liang, B., and Park, H. Predicting hedge fund failure: A comparison of risk measures. Journal of Financial and Quantitative analysis (2010), 199–222.
[17] Mantel, N., et al. Evaluation of survival data and two new rank order statistics arising in its consideration. Cancer Chemother Rep 50, 3 (1966), 163–170.
[18] Nelsen, R. B. An introduction to copulas. Springer Science & Business Media, 2007.
[19] Peto, R., and Peto, J. Asymptotically efficient rank invariant test procedures. Journal of the Royal Statistical Society: Series A (General) 135, 2 (1972), 185–198.
[20] Qiu, J., Tang, L., and Walter, I. Hedge fund incentives, management commitment and survivorship. Financial Markets and Portfolio Management 32, 2 (2018), 115–142.
[21] Savage, I. R. Contributions to the theory of rank order statistics-the two-sample case. The Annals of Mathematical Statistics 27, 3 (1956), 590–615.
[22] Shih, J. H., and Louis, T. A. Inferences on the association parameter in copula models for bivariate survival data. Biometrics (1995), 1384–1399.
[23] Tibshirani, R. The lasso method for variable selection in the cox model. Statistics in medicine 16, 4 (1997), 385–395.