3.2.1. Conceptual#

After this week you should be able to:

• Define the term sample and population

• Understand the difference between sampling with and without replacement

• Define the sampling distribution of a statistic (such as the sample mean or proportion)

• Explain how the standard error depends on sample size $n$ and the population variability $\sigma$

• Understand that the estimated sampling distribution of the mean for a population can be obtained in several ways including:

  • Calculated empirically from the population - draw many samples of size $n$ from the population and plot their means

  • Modelled using a known distribution (Normal if central limit theorem applies)

This material is covered in the lecture and recapped in the worked examples in Python

3.2.2. Python skills#

This week there is an emphasis on simulating the process of drawing a large number of (re)samples from a sample distribution

The key skill practiced this week is building a for loop to repeat a process many times (such as drawing a random sample and getting its mean)

You might need to change some variable (such as sample size n) on each pass through the loop.

Additional new(ish) Python skills:

• sample from a pandas dataframe using pandas.df.sample()

• Plot an expected distribution such as a curve from the function stats.norm.pdf() over a histogram of simulated data

• Plot a Q-Q plot

This material is covered in the Jupyter Notebooks in this section