應用統計期末報告子組題 (A)

0.1 介紹 布林通道 Bollinger Bands

• What is Bollinger Bands

  • Bollinger Bands are envelopes plotted at a standard deviation level above and below a simple moving average of the price. Because the distance of the bands is based on standard deviation, they adjust to volatility swings in the underlying price. Bollinger Bands use 2 parameters, Period and Standard Deviations, StdDev. *https://www.fidelity.com/learning-center/trading-investing/technical-analysis/technical-indicator-guide/bollinger-bands

• 可以想成統計的95%信賴區間可以調整SMA預設的n=20和standard deviation=2

• 思路

  • 加上TTR套件 把技術股標算出填到表格內的然後畫圖出來 r ttr quantmod 95％信賴區間 Bollinger Bands (別種技術指標需注意單位)

0.2 程式碼解釋

• 抓資料

rm(list=ls(all=TRUE))
#清除全部

library(quantmod)
library(dygraphs)
library(plotly)
devtools::install_github("joshuaulrich/TTR")
#載入套件

ticker = "2330.TW"
start = "2020-01-01"
end = Sys.Date()
# end = as.character(Sys.Date())

data = quantmod::getSymbols(ticker,
                            from=start,
                            to=end, 
                            src="yahoo",
                            auto.assign=FALSE) 

colnames(data) = c("Open", "High", "Low", "Close", "Volume", "Adjusted")

• OHLC = c(“Open”, “High”, “Low”, “Close”)
  • 變數多於第四個會變成畫線，單位需要和y有強烈關係（一樣）
• df=data[,OHLCA]
  • 第四個測試為 eval=FALSE：不執行此 chunk，但顯示程式碼。

bbands = TTR::BBands(data[,c("Close")])   

• 這個套件只用收盤價做計算
  • ,n=20,sd=2 是預設值，除非想換條件
• bbands <- BBands(data[,c(“High”,“Low”,“Close”)]
  • 信賴區間概念不一樣，算出來的會有問題

data <- cbind(data,bbands) 

-合併bbands至data這個dataframe 裡

OHLCB = c("Open", "High", "Low", "Close" ,"dn","mavg","up")

• OHLCB = c(“Open”,“High”,“Low”,“Close”,“dn”,“mavg”,“up”,“pctB”)
  • 最後一個不用畫出來
  • “dn”,“mavg”,“up”分別是
    • lower band,
    • Simple Moving Average(SMA)簡單移動平均線,
    • upper band
• 畫圖加線 加 range selector

fig1 = dygraph(data[,OHLCB]) %>%
  dyCandlestick() %>%
  dySeries("dn", color="orange") %>%
  dySeries("mavg", color="blue") %>%
  dySeries("up", color="orange") %>%
  dyRangeSelector()
fig1

0.3 成果展示

library(quantmod)
library(dygraphs)
devtools::install_github("joshuaulrich/TTR")
ticker = "2330.TW"
start = "2020-01-01"
end = Sys.Date()

data = quantmod::getSymbols(ticker,
                            from=start,
                            to=end, 
                            src="yahoo",
                            auto.assign=FALSE) 

colnames(data) = c("Open", "High", "Low", "Close", "Volume", "Adjusted")

bbands = TTR::BBands(data[,c("Close")])   

data <- cbind(data,bbands) 

OHLCB = c("Open", "High", "Low", "Close" ,"dn","mavg","up")

fig1 = dygraph(data[,OHLCB]) %>%
  dyCandlestick() %>%
  dySeries("dn", color="orange") %>%
  dySeries("mavg", color="blue") %>%
  dySeries("up", color="orange") %>%
  dyRangeSelector()
fig1

0.4 結碖

• 參考網址:https://www.schwab.com/learn/story/bollinger-bands-what-they-are-and-how-to-use-them
• Bollinger Bands 不是一種去判斷股價的進出場時機的訊號， 是根據他是否超過upper or lower band 來等待並觀察之後是否有出現
• double bottom, classic M top, or three pushes to high formation之後再做進一步的操作，
• 做多和買空也能利用upper or lower band訂定初始停利停損值，
• 長線和短線設定的初始值要相反，長配lower band ，短配upper band