Exercise

Visualizing samples

You saw that a single sample can give an unreliable point estimate. To investigate this you decide to take 100 samples of 90 consecutive days of BTC trading data. For each of these 100 samples you compute the percent change in BTC over that time period. You then want to plot this data as a histogram to understand the sampling distribution.

Although these visualizations can be created with plt.hist(), for this exercise, you'll practice using the .plot() argument on a DataFrame, with the arguments bins and density.

The 100 samples of percent change has already been loaded for you in btc_pct_change_list. This is a list of length 100 with each entry being the percent change in BTC for one of the 100 samples chosen. Matplotlib has also been imported as plt.

Instructions

100 XP
  • Plot a histogram of BTC percent change with 15 bins with the y-values displaying the density, rather than the count.
  • Set the x-axis label to "BTC 90-day percent change".
  • Set the y-axis label to "Percent of samples".
  • Set the title to "Sampling distribution of BTC 90-day change".