。。。希望。

stationarity代表會收斂，就像r(t)=a+br(t-1)，b的絕對值必須小於1，若大於1表示不收斂，就non-stationarity了，而time-varying conditional variance表示variance會隨時間而改變，所以他跟stationarity是不衝突的
arch effect 似乎沒有non-linearity這樣的假設存在arch effect 的2個條件是必須是leptokurtic和volatility clustering
這2個檢定方法都很間單的，希望對你有幫助

ARCH models are not linear in the sense that they have nonzero terms on higher-order moving average coefficients in the Volterra expansion. Generalisation of  ARCH-type models are non-linear in the sense that the models are non-linear combination of model parameteres, such as EGARCH and NGARCH.