「分享興趣，傳播快樂，增長見聞，留下美好！大家好，這裡是小編。歡迎大家繼續訪問學苑內容，我們將竭誠為您帶來更多更好的內容分享。
"Share interests, spread happiness, increase knowledge and leave beauty! Hello everyone, this is Xiaobian. Welcome to continue to visit the content of the academy, and we will bring you more and better content sharing wholeheartedly.
【思維導圖】
【基礎理論】
指數平滑法的思想來源於對移動平均預測法的改進。用當前值和歷史值預測未來值時，移動平均法面臨兩個難題:其一是當前值和歷史值同等權重不合理。一般而言，未來值總是和臨近時點的值關係更密切;其二是無法令人信服的確定窗口寬度。如使用5日移動平均數還是15日平均數難有定論。而且如果使用5日移動平均數，那麼5日之前的觀察值等於賦予權重零，而五日內的觀察值均有相同權重0.2，這也和實際情況相悖。指數平滑法的思想是以無窮大為寬度，各歷史值的權重隨時間的推移呈指數衰減，這樣就解決了移動平均的兩個難題。
The idea of exponential smoothing method comes from the improvement of moving average prediction method. When using current value and historical value to predict future value, moving average method faces two difficult problems: First, it is unreasonable that the current value and historical value have the same weight. Generally speaking, the future value is always more closely related to the value near the time point; Second, it is impossible to convincingly determine the window width. It is difficult to decide whether to use the 5-day moving average or the 15-day average. Moreover, if the 5-day moving average is used, the observed value before 5 days is equal to zero, while the observed value within 5 days is 0.2 for the same people, which is contrary to the actual situation. The idea of exponential smoothing method is to take infinity as the width, and the weight of each historical value decays exponentially with the passage of time, thus solving two difficult problems of moving average.
【SPSS實例分析】
下面我們來看一個指數平滑法的SPSS實例分析：
Let's look at an SPSS example analysis of exponential smoothing method:
第一步，分析並組織數據。
The first step is to analyze and organize the data.
看用指數平滑法處理是否恰當，創建私人汽車擁有量的序列圖，如下圖所示。從此圖可以看出私人汽車擁有量呈逐年增加趨勢，開始增長較慢，然後變快，近似線性趨勢，也可以說呈增長的線性趨勢，或者用指數趨勢描述更準確，所以可選用指數平滑法進行處理。
See if exponential smoothing is appropriate, and create a sequence diagram of private car ownership, as shown in the following figure. From this figure, it can be seen that the number of private cars is increasing year by year, starting from a slow increase, then becoming faster, approximate to a linear trend, or it can be said to be a linear trend of growth, or it is more accurate to describe it with exponential trend, so exponential smoothing method can be selected for processing.
第二步，定義日期變量。將年份定義為日期變量。
The second step is to define the date variable. Defines the year as a date variable.
第三步，指數平滑法設置。按下圖所示，進行指數平滑法的設置。
The third step is to set up exponential smoothing method. As shown in the figure below, set the exponential smoothing method.
第四步，主要結果及分析。
The fourth step, the main results and analysis.
下期預告：本期，我們學習了指數平滑法的理論基礎和實例分析。下一期，我們將會學習ARIMA模型。
Forecast for the next issue: In this issue, we learned the theoretical basis and case analysis of exponential smoothing method. In the next issue, we will study ARIMA model.
如果您對今天的文章有獨特的想法，歡迎給我們留言，讓我們相約明天，祝您今天過得開心快樂！
If you have a unique idea of today's article, welcome to leave us a message, let us meet tomorrow, I wish you a happy today!
參考資料：《SPSS23（中文版）統計分析實用教程》、百度百科
翻譯：訊飛語音
本文由learningyard新學苑原創，部分圖片文字來源於他處。如有侵權，請聯繫刪除。