本研究選取之資料期間為2020年1月21日至2021年1月20日，共253筆的日資料，藉由時間序列分析，可看出這段時間的市場走勢以及受COVID-19之影響程度，並選取3檔在美國具有影響力的ETF做資料分析，分別探討在COVID-19疫情下，科技產業、黃金商品、以及原油期貨波動的顯著程度。被解釋變數設定為各檔ETF之日交易量，而解釋變數分別是該ETF之價格、落後一期交易量、以及每日確診人數，同時，因本研究設定受到COVID-19影響程度之指標為確診人數，因此將門檻變數設定為確診人數。
本研究採用Granger and Teräsvirta (1993)和Teräsvirta (1994)所提出的平滑移轉迴歸檢定方法，進而進行平滑移轉模型設定及參數估計。其中，本研究發現那斯達克100ETF之落後一期交易量以及每日確診人數，不論是小於門檻值或大於門檻值時，皆會出現顯著的影響效果，而那斯達克100ETF之價格在小於門檻值時呈現顯著的影響效果，但在大於門檻值時則呈現不顯著的影響效果。再者，黃金ETF之落後一期交易量以及每日確診人數，不論是小於門檻值或大於門檻值時，皆會出現顯著的影響效果，而黃金ETF之價格在小於門檻值時呈現顯著的影響效果，但在大於門檻值時則呈現不顯著的影響效果。最後，原油ETF之落後一期交易量以及原油ETF之價格對原油ETF之日交易量呈現顯著影響效果，但確診人數對原油ETF日交易量則呈現不顯著的影響效果。

The data period selected in this study is from January 21, 2020 to January 20, 2021, with a total of 253 daily data. Through time series analysis, we can see the market trend during this period and the impact of COVID-19 And select 3 ETFs with influence in the United States for data analysis to explore the significant degree of fluctuations in the technology industry, gold commodities, and crude oil futures under the COVID-19 epidemic. The explanatory variables are set as the daily trading volume of each ETF, and the explanatory variables are the price of the ETF, the trading volume one period behind, and the number of people diagnosed daily. At the same time, the index of the degree of impact from COVID-19 is set by this study as The number of confirmed cases, so the threshold variable is set as the number of confirmed cases.
In this study, the smooth migration regression verification method proposed by Granger and Teräsvirta (1993) and Teräsvirta (1994) was used to carry out the smooth migration model setting and parameter estimation. Among them, this study found that the lagging trading volume of the Nasdaq 100 ETF and the number of daily diagnoses, whether it is less than the threshold or greater than the threshold, will have a significant impact, and the price of the Nasdaq 100 ETF is at When it is less than the threshold value, it shows a significant effect, but when it is greater than the threshold value, it shows an insignificant effect. Furthermore, the lagging trading volume of the gold ETF and the number of daily diagnoses, whether it is less than the threshold or greater than the threshold, will have a significant impact, and the price of the gold ETF will have a significant impact when the price is less than the threshold. Effect, but when it is greater than the threshold, it shows an insignificant effect. Finally, the lagging trading volume of crude oil ETFs and the price of crude oil ETFs have a significant impact on the daily trading volume of crude oil ETFs, but the number of confirmed cases has an insignificant effect on the daily trading volume of crude oil ETFs.

章節目錄
第一章 諸論 1
第一節 研究背景與動機 1
第二節 研究目的 5
第三節 研究架構與研究流程 6
第二章 理論與文獻探討 7
第一節 ETF的價格與交易量 7
第二節 ETF與一般股票的交易型態比較 9
第三節 ETF權值股交易量的波動 10
第四節 股票市場與COVID-19 10
第五節 COVID-19與ETF交易量 12
第三章 研究方法 13
第一節 單根檢定 14
一、 ADF檢定 14
二、 PP檢定 15
三、 KPSS檢定 16
第二節 平滑移轉迴歸模型 16
一、迴歸模型設定 16
二、線性檢定 17
三、轉換函數之決定 18
第四章 實證結果與分析 21
第一節 資料來源與分析 21
一、QQQ(Invesco那斯達克100指數ETF) 21
二、IAU(iShares黃金信託ETF) 23
三、USO(United States石油ETF) 24
第二節 單根檢定 28
第三節 線性檢定 30
第四節 轉換函數檢定 32
第五節 模型之參數估計與檢定 33
一、COF-Q參數估計 34
二、COF-G參數估計 36
三、COF-O參數估計 38
第五章 結論與建議 39
參考文獻 41

圖目錄
圖1-1-1 美國每日確診人數 2
圖1-1-2 2020年那斯達克100ETF之月交易量 3
圖1-3-1 研究架構與流程 6
圖3-2-1 邏輯型函數圖形 19
圖3-2-2 指數型函數圖形 19
圖4-1-1 QQQ那斯達克100ETF之各解釋變數走勢圖 22
圖4-1-2 IAU黃金ETF之各解釋變數走勢圖 23
圖4-1-3 USO原油ETF之各解釋變數走勢圖 25

表目錄
表4-1-1 各變數之敘述統計量 26
表4-2-1 各變數之單根檢定結果 29
表4-3-1 QQQ那斯達克100ETF模型線性檢定及門檻變數(確診人數)最適落階期 30
表4-3-2 IAU黃金ETF模型線性檢定及門檻變數(確診人數)最適落階期 31
表4-3-3 USO原油ETF模型線性檢定及門檻變數(確診人數)最適落階期 31
表4-4-1 COF-Q轉換函數模型檢定 32
表4-4-2 COF-G轉換函數模型檢定 32
表4-5-1 COF-Q邏輯型平滑移轉迴歸(LSTR)函數模型參數估計 34
表4-5-2 那斯達克100ETF各變數對確診人數之區間影響 35
表4-5-3 COF-G邏輯型平滑移轉迴歸(LSTR)函數模型參數估計 36
表4-5-4 黃金ETF各變數對確診人數之區間影響 37
表4-5-5 COF-O線性函數模型參數估計 38

Bai, J., and Perron, P. (2003), “Computation and Analysis of Multiple Structuralchange Models”, Journal of Applied Econometrics 18, pp.1–22.
Ben, D, I., Franzoni, F., and Moussawi, R. (2014), “Do ETFs Increase Volatility?”,  NBER Working Paper Series; Cambridge.
Borkovec, M., and Serbin, V. (2013), “Create or Buy: A Comparative Analysis of Liquidity and Transaction Costs for Selected U.S. ETFs”, Journal of Portfolio Management; London Vol. 39, Iss. 4, pp.118-131.
Buetow, G. W., and Henderson, B. J. (2012), “An Empirical Analysis of Exchange-Traded Funds”, Journal of Portfolio Management; London Vol. 38, Iss. 4, pp.112-127.
Chevallier, J. (2020), “Covid-19 Pandemic and Financial Contagion”, Journal of Risk and Financial Management; Basel Vol. 13, Iss. 12, pp.309.
Dickey, D. A., and Fuller, W. A. (1979), “Distribution of the Estimators for Autoregressive Time Series with a Unit Root,” Journal of the American Statistical Association, 74(366), pp.427-431.
Dickey, D. A., and Fuller, W. A. (1981), “Likelihood Ratio Statistics for Autoregressive Time Series with a Unit Root,” Econometrica: Journal of the Econometric Society, 49(4), pp.1057-1072.
Granger, C. W., and Newbold, P. (1974), “Experience with Forecasting Univariate Time Series and the Combination of Forecasts,” Journal of the Royal Statistical Society, 137(2), pp.131-165.
Granger, C. W., and Teräsvirta, T. (1993), Modelling Non-Linear Economic Relationships. Oxford University Press. Oxford.
Hong, H., Bian, Z., and Lee, C. C. (2021), “COVID-19 and Instability of Stock Market Performance: Evidence from the U.S.”, Financial Innovation; Heidelberg Vol. 7, Iss. 1.
Ivanov, S. I. (2016), “Analysis of ETF Bid-Ask Spread Components”, Quarterly Review of Economics and Finance; Greenwich Vol. 61, pp.249.
Kwiatkowski, D., Phillips, P. C., Schmidt, P., and Shin, Y. (1992), “Testing the Null Hypothesis of Stationarity Against the Alternative of a Unit Root: How Sure Are We that Economic Time Series Have a Unit Root?” Journal of Econometrics, 54(1), pp.159-178.
Olakojo, S. A., Onanuga, A. T., and Onanuga, O. T. (2021), “COVID-19: Putting Stock Markets Back on Recovery among the Crude Oil Producing Economies”, Contemporary Economics; Warsaw Vol. 15, Iss. Special Issue, pp.34-52.
Phillips, P. C., and Perron, P. (1988), “Testing for a Unit Root in Time Series Regression,” Biometrika, 75, pp.335-346.
Scholes, M. S. (1972), “The Market for Securities: Substitution Versus Pricepressure and the Effects of Information on Share Prices,” The Journal of Business 45, pp.179-211.
Sharifzadeh, M., and Hojat, S. (2012), “An Analytical Performance Comparison of Exchange-Traded Funds with Index Funds: 2002-2010”, Journal of Asset Management; London Vol. 13, Iss. 3, pp.196-209.
Shleifer, A. (1986), “Do Demand Curves for Stocks Slope Down?” The Journal of Finance 41, pp.579-590.
Singh, G., and Shaik, M. (2021), “The Short-Term Impact of COVID-19 on Global Stock Market Indices”, Contemporary Economics; Warsaw Vol. 15, Iss. Special Issue, pp.1-18.
Smales, L. A. (2021), “Investor Attention and the Response of US Stock Market Sectors to the COVID-19 Crisis”, Review of Behavioral Finance Vol. 13 No. 1, pp. 20-39.
Teräsvirta, T. (1994), Specification, Estimation, and Evaluation of Smooth Transition Autoregressive Models. Journal of the American Statistical Association, 89(425), pp.208-218.
Tripathi, V., and Garg, S. (2016), “A Cross-Country Analysis of Pricing Efficiency of Exchange Traded Funds”, Journal of Applied Finance; Hyderabad Vol. 22, Iss. 3, pp.41-63.