1. Instantiate an array lags-[1,2,3,5,10,15,20,30]. For each lag in lags compute and plot the history of...

  

Transcribed Image Text:

1. Instantiate an array lags-[1,2,3,5,10,15,20,30]. For each lag in lags compute and plot the history of the 60-day rolling autocorrelation of dow. Make your plot(s) legible. 2.For each lag in lags, compute the average of the autocorrelation times series computed in the previous step and use these 8 values to plot the autocorrelation function (autocorrelation against lag). What do you observe? Does this plot suggest that the Dow Jones is a white noise process? If not, can you suggest a better model? 3. Compute and plot the daily returns of the Dow Jones (Return = 100* ((Closet/Closet-1)-1)), repeat the previous two steps and answer the same questions for this time series instead. import pandas_datareader.data as web import matplotlib.pyplot as plt data = web.DataReader ( '^DJI ' 3 data data.reset_index() dates = data["Date"] dow = data["Close"].to_numpy () plt.plot (dates, dow) plt.show() = 1 yahoo > start= 1995-01-01 3 end= 2022-12-05 1 ) 1. Instantiate an array lags-[1,2,3,5,10,15,20,30]. For each lag in lags compute and plot the history of the 60-day rolling autocorrelation of dow. Make your plot(s) legible. 2.For each lag in lags, compute the average of the autocorrelation times series computed in the previous step and use these 8 values to plot the autocorrelation function (autocorrelation against lag). What do you observe? Does this plot suggest that the Dow Jones is a white noise process? If not, can you suggest a better model? 3. Compute and plot the daily returns of the Dow Jones (Return = 100* ((Closet/Closet-1)-1)), repeat the previous two steps and answer the same questions for this time series instead. import pandas_datareader.data as web import matplotlib.pyplot as plt data = web.DataReader ( '^DJI ' 3 data data.reset_index() dates = data["Date"] dow = data["Close"].to_numpy () plt.plot (dates, dow) plt.show() = 1 yahoo > start= 1995-01-01 3 end= 2022-12-05 1 )