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.

温特斯（1960）的方法是实践中最著名的预测方法之一。它受欢迎的主要原因是它易于实施，并且可以为实践目的提供非常有效的结果。但是，由于两个不同的异步日历（例如格里高利历法和回历法）的同时影响，该方法无法捕获出现的模式。我们对这种方法进行了调整，使其可以处理此类模式，并使用从土耳其啤酒厂收集的真实数据集来研究其性能。用同样的数据集，我们还提供我们的模型和一些预测模型之间的比较优势分析，如冬季的（温特斯1960年），TBAT（德Livera等2011），ETS（海德门等。2002年）和ARIMA（Hyndman和Khandakar，2008年）。我们获得的结果表明，当两个异步日历对时间序列施加影响时，使用新方法可以实现更好的预测。