import matplotlib.pyplot as plt parameter = houses['SalePrice'].mean() for i in range(101): sample = houses['SalePrice'].sample(n = 5 + (29*i), random_state = i) statistic = sample.mean() sampling_errors = parameter - statistic sample_size = 5 + (29*i) plt.scatter(x = sample_size, y = sampling_errors) plt.axvline(2930) plt.axhline(0) plt.xlabel('Sample size') plt.ylabel('Sampling error') plt.show()
What I expected to happen:
The task here is to find how sample size effects our sampling. In the above code I kept on increasing the sample size and measured the sampling_error(sample mean - mean of series) and the plot this sampling error on scatter plot. This is what I got.
What actually happened:
As per DQ, my plot is not matching the expected result
Your plot didn't matched the expected plot.