Chapter 4: Designing Studies - Section 4.1: Samples and Surveys
The Practice of Statistics, 4th edition – For AP* STARNES, YATES, MOORE
Chapter 4: Designing Studies
- Sections:
- 4.1 Samples and Surveys
- 4.2 Experiments
- 4.3 Using Studies Wisely
Section 4.1 Samples and Surveys
- Learning Objectives: After this section, students should be able to:
- IDENTIFY the population and sample in a sample survey
- IDENTIFY voluntary response samples and convenience samples
- DESCRIBE how to use a table of random digits to select a simple random sample (SRS)
- DESCRIBE simple random samples, stratified random samples, and cluster samples
- EXPLAIN how undercoverage, nonresponse, and question wording can lead to bias in a sample survey
Population and Sample
- Definition of Population: The population in a statistical study is the entire group of individuals about which we want information.
- Definition of Sample: A sample is the part of the population from which we actually collect information.
- We use information from a sample to draw conclusions about the entire population.
- Process of Sampling:
- Collect data from a representative sample and make an inference about the population.
The Idea of a Sample Survey
- Conclusions about a whole population are often drawn from a sample.
- Steps to Conduct a Sample Survey:
- Step 1: Define the population to describe.
- Step 2: Specify what to measure.
- Step 3: Decide how to choose a sample from the population.
- A sample survey is defined as a study that utilizes an organized plan to choose a sample that represents a specific population.
Sampling Methods
- Methods to select trustworthy samples include:
- Convenience Sampling: Selecting individuals who are easiest to reach.
- Voluntary Response Samples: Individuals decide whether to join the sample in response to an open invitation.
How to Sample Well: Random Sampling
- A sample chosen by chance/rules out:
- Favoritism by the sampler.
- Self-selection by respondents.
- Definition of Simple Random Sample (SRS): An SRS of size n consists of n individuals from the population chosen so that every set of n individuals has an equal chance to be the sample selected.
- In practice, random numbers generated by computers or calculators are often used, but when technology is unavailable—tables of random digits may be utilized.
- TI-84 Random Number Generator:
- MATH → Prob → randInt(low, high, #)
How to Choose an SRS
- Label: Assign a numerical label to each member of the population of the same length.
- Table: Read consecutive groups of digits of the appropriate length from a Table of Random Digits.
- The sample contains individuals corresponding to the labels found.
- Definition of a Table of Random Digits: A long string of digits (0-9) where each entry is equally likely and independent of each other.
Example of Selecting an SRS
- Problem: Use Table D at line 130 to choose an SRS of 4 hotels:
- Digits: 69051, 64817, 87174, 09517,…
- SRS of 4 hotels: 05 Beach Castle, 16 Radisson, 17 Ramada, and 20 Sea Club.
- Sample Hotel List:
- 01 Aloha Kai
- 02 Anchor Down
- 03 Banana Bay
- 04 Banyan Tree
- 05 Beach Castle
- 06 Best Western
- 07 Cabana
- 08 Captiva
- 09 Casa del Mar
- 10 Coconuts
- 11 Diplomat
- 12 Holiday Inn
- 13 Lime Tree
- 14 Outrigger
- 15 Palm Tree
- 16 Radisson
- 17 Ramada
- 18 Sandpiper
- 19 Sea Castle
- 20 Sea Club
- 21 Sea Grape
- 22 Sea Shell
- 23 Silver Beach
- 24 Sunset Beach
- 25 Tradewinds
- 26 Tropical Breeze
- 27 Tropical Shores
- 28 Veranda
Other Sampling Methods: Stratified
- Advantages of Stratified Sampling:
- Provides statistical advantages by sampling important groups (called strata) separately.
- Definition of Stratified Random Sample: First classify the population into strata (groups of similar individuals), then choose a separate SRS in each stratum and combine these to form the full sample.
Example: Sampling Sunflowers
- Instructions: Use Table D or technology to take an SRS of 10 grid squares, using the rows as strata, and then repeat using the columns as strata.
Other Sampling Methods: Cluster
- Cluster Sampling: An alternative when populations are large and spread out.
- Process:
- Divide the population into smaller groups (clusters).
- Randomly select some clusters and include all individuals in those selected clusters in the sample.
Example: Sampling at a School Assembly
- Task: Describe how to select 80 students using different sampling methods:
- (a) Simple Random Sample
- (b) Stratified Random Sample
- (c) Cluster Sample
Inference for Sampling
- Purpose of Sampling: To gain information about a larger population.
- Inference: The process of drawing conclusions about a population based on sample data.
- Reasons to Rely on Random Sampling:
- Eliminates bias in selecting samples from available individuals.
- Laws of probability allow trustworthy inference about the population.
- Results from random samples come with a margin of error that sets bounds on the likely error.
- Larger random samples yield better information about the population.
Sample Surveys: What Can Go Wrong?
- Many sample surveys are affected by errors in addition to sampling variability.
- Good Sampling Techniques: Include strategies for reducing all sources of error.
- Common Errors:
- Undercoverage: Some groups in the population are left out of the sample selection process.
- Nonresponse: Occurs when a selected individual cannot be contacted or refuses to participate.
- Response Bias: A systematic pattern of incorrect responses, significantly influenced by the wording of questions in surveys.
Summary of Section 4.1
- A sample survey selects a sample from the population of individuals we want information on.
- Random sampling employs chance to select samples.
- The basic random sampling method is a simple random sample (SRS).
- Stratified random samples require dividing the population into strata and then selecting a separate SRS from each stratum.
- Cluster sampling involves dividing the population into clusters, from which some are randomly selected.
- Failure to utilize random sampling often results in bias, systematic errors in sample representation.
- Voluntary response and convenience samples are particularly susceptible to significant bias.
- Sampling errors arise from selection processes. Random sampling error and undercoverage are common types of these errors.
- The most serious errors are nonsampling errors, with common types including nonresponse, response bias, and question wording.
Looking Ahead…
- Next Sections:
- The distinction between Observational Studies and Experiments
- The language of experiments
- Randomized Comparative Experiments
- Principles of Experimental Design
- Inference for Experiments
- Blocking techniques
- Matched Pairs Design
- Overview of upcoming concepts in Section 4.2.