Statistical Techniques for Data Science. Week 2

1.

Statistical Techniques for Data Science.
Week 2

2.

Objectives (for today)
data and sampling distributions
statistic
Markov, Chebyshev inequalities
CLT, LLN

3.

Theory (recap)

4.

data and sampling distributions
data distribution – distribution of the original dataset
sampling distribution – distribution of a statistic calculated on many samples
drawn
from the original dataset
sampling distribution != sample distribution (do not mix!!!)

5.

statistic
statistic – any function of the random variables constituting a random
sample (Walpole
R. E. et al. Probability and statistics for engineers and scientists)
Examples: mean, median, standard deviation.

6.

Markov and Chebyshev inequalities
Explain these two formulas?
What is E(X)?