CALENDAR EFFECTS IN MONTHLY TIME SERIES MODELS

It is not unusual for the level of a monthly economic time series, such as industrial production, retail and wholesale sales, monetary aggregates, telephone calls or road accidents, to be influenced by calendar effects. Such effects arise when changes occur in the level of activity resulting from differences in the composition of calendar between years. The two main sources of calendar effects are trading day variations and moving festivals. Ignoring such calendar effects will lead to substantial distortions in the identification stage of time series modeling. Therefore, it is mandatory to introduce calendar effects, when they are present in a time series, as the component of the model which one wants to estimate.

Stock Liquidity Risk Pricing Model Driven by Systematic and Unsystematic Risk

In the stock pricing, liquidity risk has become one of the important factors that affect the stock realizable value. Systematic and unsystematic risk decided a stock＇s liquidity risk. The author uses the stock price index growth rate and net outer disk ratio to describe a systematic and unsystematic risk faced by investors. With the help of correlation and regression analysis in SPSS software, the paper tries to establish the systematic and unsystematic risk-driven stock liquidity risk pricing model. Empirical study shows that systematic and unsystematic risk has significant influence on stock liquidity risk. The bigger circulation stock, the greater the systemic risk influence; the less the circulation stock, the larger the non-system risk influence. Calendar factor on stock returns ratio has no significant effect. Trading volume on the stock returns ratio of small companies had no significant effect. The model has important reference value for the measure of stock liquidity risk value loss.

Augmented Winter’s method for forecasting under asynchronous seasonalities

The method of Winters(1960)is one of the most well-known forecasting methodologies in practice.The main reason behind its popularity is that it is easy to implement and can give quite effective and efficient results for practice purposes.However,this method is not capable of capturing a pattern being emerged due to the simultaneous effects of two different asynchronous calendars,such as Gregorian and Hijri.We adapt this method in a way that it can deal with such patterns,and study its performance using a real dataset collected from a brewery factory in Turkey.With the same data set,we also provide a comparative performance analysis between our model and several forecasting models such as Winter’s(Winters 1960),TBAT(De Livera et al.2011),ETS(Hyndman et al.2002),and ARIMA(Hyndman and Khandakar 2008).The results we obtained reveal that better forecasts can be achieved using the new method when two asynchronous calendars exert their effects on the time-series.

Empirical Analysis of Seasonality Anomalies in Chinese Stock Market Based on Rolling Sample Tests

The paper uses rolling sample tests to investigate calendar effect in Chinese stock market, the method is very suitable for emerging market. We utilize GARCH （1,1）- GED model to identify the time varying nature of calendar effect. Friday effect existed with low volatility at the early stage, but it seems to disappear since 1997, and positive Tuesday effect began to appear then. There is small firm January effect with high volatility.