Chapter 7: Sampling
Distributions
Read Chapter 8
Learning Objectives
1.
Statistic vs. Parameter
2.
Sampling Distributions
3.
Mean and Standard Deviation of the
Sampling Distribution of a Proportion
4.
Standard Error
5.
Population, Data, and Sampling
Distributions
log(AveCorCopies) ~ Time| Stress2
Conclusions
Working
Hypothesis:
Theoretical Models,
Data Generating
Mechanisms
Descriptive Statistics
Populations and Samples
Population
– total collection of all individuals of interest
Sample
– randomly selected collection of
n
individuals on
which observations are made.
Data
– observations made on a collection of objects
Population
Ù
Sample
Goal: We want a
representative
sample.
The sample population needs to represent the
target population. Such a sample can be used
to make inferences about the population.
Sampling Distributions (Rice University
)
Principles of Sampling
Examine a Part of the Whole
– the sample. Vegetable Soup example –
Instead of eating the whole pot, you taste a spoonful.
Randomize
– stir up the pot before you sample the spoonful. The top may
be salty or not have any potato in it, etc.
How big of a sample size do you need?
That depends on what you are trying to estimate. If you’re interested in the
broth only, then a single sip may do – assuming it has been well
stirred/randomized. If you are interested in all the big chunks of
vegetables in the soup, you need a large enough sample to make it
representative of the whole.
For example, assume that your soup has very large pieces of carrots and
potatoes- so large in fact that you can not expect to sample a piece of
each with a single spoonful. Then you will have to take many samples
in order to taste a carrot and potato.
The more structure – the larger the sample
Larger absolute sample size, not fraction of population.

This ** preview** has intentionally

**sections.**

*blurred***to view the full version.**

*Sign up*