Handout 10a) Chapter 3: Surveys & Samping

What is a sample?

A smaller group of individuals selected from the population

• rely on this sample to draw conclusions about the population

What is bias?

When a sample is misrepresentative of the population

What is randomization?

Purposeful effort to allow chance to determine sample

• best way to avoid bias

• ensure that, on average, sample represents population

What is census & issues with it?

Surveying everyone

• uncommon method

• difficult & costly to complete

• populations are changing

What is a statistics & the notations used?

Statistic - any summary found from the data

• statistics estimate paraments are called sample statistics

What are simple random samples (SRS)?

An approach to choosing samples

SRS implies that every possible sample has an equal chance to be selected

• Representative sample is only possible through randomization

What is a sample frame & sampling variability?

Sampling frame:

• those eligible of being sampled

• random number generator can help select sample

Sampling variability:

• differences between one sample to another

What are some other approaches (other than SRS) to choosing the sample?

All statistical sampling designs leave it up to chance, rather than human choice

• stratified random sampling (most common)

• cluster sampling

• multistage sampling

• systemic sampling

What can go wrong/what makes a bad sample?

• Selection bias

• Volunteer bias → sample of only those who want to (info is useless/taken with grain of salt)

• Convenience sampling → include individuals who are at hand (lacks randomization)

• Incomplete sample frame (unrepresentative)

• Non-response bias (those who don’t respond may provide meaningful insight)