風險值大多是在假設資產報酬為常態分配下計算而得的，但是這個假設與實際的資產報酬分配不一致，因為很多研究者都發現實際的資產報酬分配都有厚尾的現象，也就是極端事件的發生機率遠比常態假設要來的高，因此利用常態假設來計算風險值對於真實損失的衡量不是很恰當。 針對這個問題，本論文以歷史模擬法、變異數-共變異數法、混合常態模型來模擬報酬率的分配，並依給定的信賴水準估算出風險值，其中混合常態模型的參數是利用準貝式最大概似估計法及EM演算法來估計；然後利用三種風險值的評量方法：回溯測試、前向測試與二項檢定，來評判三種估算風險值方法的優劣。 經由實證結果發現： 1.報酬率分配在左尾臨界機率1％有較明顯厚尾的現象。 2.利用混合常態分配來模擬報酬率分配會比另外兩種方法更能準確的捕捉到左尾臨界機率1％的厚尾。 3.混合常態模型的峰態係數值接近於真實報酬率分配的峰態係數值，因此我們可以確認混合常態模型可以捕捉高峰的現象。 關鍵字：風險值、厚尾、歷史模擬法、變異數-共變異教法、混合常態模型、準貝式最大概似估計法、EM演算法、回溯測試、前向測試、高峰 / Initially, Value at Risk (VaR) is calculated by assuming that the underline asset return is normal distribution, but this assumption sometimes does not consist with the actual distribution of asset return. Many researchers have found that the actual distribution of the underline asset return have Fat-Tail, extreme value events, character. So under normal distribution assumption, the VaR value is improper compared with the actual losses. The paper discuss three methods. Historical Simulated method - Variance-Covariance method and Mixture Normal .simulating those asset, return and VaR by given proper confidence level. About the Mixture Normal Distribution, we use both EM algorithm and Quasi-Bayesian MLE calculating its parameters. Finally, we use tree VaR testing methods, Back test、Forward tes and Binomial test -----comparing its VaR loss probability We find the following results: 1.Under 1% left-tail critical probability, asset return distribution has significant Fat-tail character. 2.Using Mixture Normal distribution we can catch more Fat-tail character precisely than the other two methods. 3.The kurtosis of Mixture Normal is close to the actual kurtosis, this means that the Mixture Normal distribution can catch the Leptokurtosis phenomenon. Key words: Value at Risk、VaR、Fat tail、Historical simulation method、 Variance-Covariance method、Mixture Normal distribution、Quasi-Bayesian MLE、EM algorithm、Back test、 Forward test、 Leptokurtosis

周邊注射安非它命能夠影響動物受試在表現與時間知覺有關的操作式制約行為作業，歷來被研究者認為是大腦多巴胺神經系統與動物時間知覺系統有關的主要證據之一。本研究所共同採用的研究方法為先注射多巴胺受體專屬拮抗劑再於大鼠受試周邊腹腔注射安非它命的方式探討安非它命影響大鼠時間知覺的大腦機制為何。實驗一利用區辨性增強低頻反應作業觀察周邊注射多巴胺受體專屬拮抗劑何者可以反制周邊安非它命對此作業的影響效果，結果發現多巴胺D1受體拮抗劑SCH23390與D2受體拮抗劑raclopride均可反制周邊安非它命的效果。實驗二同樣利用區辨性增強低頻反應作業，但是將SCH23390與raclopride分別注入海馬迴、背側中區紋狀體、腹側側邊紋狀體、依核、內側前額葉皮質以及腹側頂蓋區等六個部位，觀察何種多巴胺受體拮抗劑可在那些大腦部位產生反制周邊安非它命的效果。結果發現SCH23390可在海馬迴、依核、內側前額葉皮質以及腹側頂蓋區等四個部位產生反制周邊安非它命的效果，而raclopride可在腹側側邊紋狀體與內側前額葉皮質兩個部位產生同樣的反制效果。實驗三利用高峰時距作業觀察SCH23390在海馬迴與內側前額葉皮質是否能反制周邊安非它命對此作業的影響效果，結果發現SCH23390僅在海馬迴會影響大鼠受試的正常表現，特別是在與周邊安非它命同時注射的時候。綜合以上結果顯示，周邊注射安非它命能夠使大鼠受試在區辨性增強低頻反應作業當中表現出時間知覺變快的傾向，這個效果需要同時透過大腦內的海馬迴、依核、內側前額葉皮質以及腹側頂蓋區的多巴胺D1類受體和腹側側邊紋狀體與內側前額葉皮質的多巴胺D2類受體。 / The central dopaminergic system has been hypothesized to play a role in time perception based on the results that peripheral injections of d-amphetamine alter the responses in time-related operant conditioned behavioral tasks. The present study investigated the effect by injecting specific dopamine receptor antagonists before peripheral d-amphetamine injections in rats. Data from Experiment I showed that both peripheral the dopamine receptor D1 antagonist SCH23390 and D2 antagonist raclopride could attenuate the response alteration on differential reinforcement of low-rates responding task induced by peripheral d-amphetamine. By using the DRL task, Experiment 2 employed the microjeciton technique to determine the neural substrates for the DA receptor antagonist to attenuate the effect of peripheral d-amphetamine. The infusion sites for DA receptor antagonist were the hippocampus, the dorsomedial striatum, the ventrolateral striatum, the nucleus accumbens, the medial prefrontal cortex, and the ventral tegme ntal area. The results showed that SCH23390 infused into the hippocampus, the nucleus accumbens, the medial prefrontal cortex, the ventral tegmental area could attenuate the effect induced by peripheral d-amphetamine, and such attenuation effects were also observed for raclopride infused into the ventrolateral striatum, the medial prefrontal cortex. Experiment 3 tried to confirm the results of Experiment 2 by microinjecting SCH23390 in hippocampus and medial prefrontal cortex under peak-interval task. Only SCH23390 in the hippocampus altered the subject's normal performance in this task especially when combined with peripheral injection of d-amphetamine. In conclusion, that the response alteration on the DRL task induced by peripheral injection ofd-amphetamine suggests the subject's timing perception being accelerated. These effects of d-amphetamine were mediated by simultaneous activation of multiple dopamine receptor subtypes including D1 receptors located in the hippocampus, nucleus accumbens, medial pref rontal cortex, ventral tegmental area, as well as D2 receptors located in the ventrolateral striatum, medial prefrontal cortex.