Term
| Population/parameter/sample/statistic |
|
Definition
- Population and parameter
- parameter: summary statistic for the population
- E.g., mean age of the population
- Sample and statistic
- Sample is used to make parameter estimates
- Sample statistic: an estimate of the population parameter
- E.g., mean age of the sample
|
|
|
Term
|
Definition
- List of units from which sample is drawn
- defines your population
- E.g., list of memebers of organization or community
- Ideally you'd like to list all members of your population as your sampling frame
- Randomly select your sample from the list
- Telephone book as a sampling frame
- Very popular in most telephone surveys
- Misses unlisted numbers
|
|
|
Term
| Literary Digest Survey example |
|
Definition
- In 1936, they sent out 10 million post cards
- names selected from telephone directories and automobile registrations
- survey results: Landon 57%; Roosevelt 43%
- election results: Roosevelt in the largest landslide (61% of the vote and 523-8 in Elect. Coll.)
- Why so inaccurate? Poor sampling frame.
- Leads to selection of wealthy respondents
|
|
|
Term
| Probability vs. Nonprobability Sampling |
|
Definition
- Probability sampling
- Based on random selection: each unit of the population has an equal chance of being selected into the sample
- Representativeness as a goal: sample resembles larger population
- Allows researchers to calculate the amt. of sampling error
- Nonprobability sampling
- Based on convenience
- Sampling frame for randomization does not exist
- Not able to calculate sampling error
|
|
|
Term
Four types of Nonprobability Samples: - Available Sample
- Volunteer Sample
- Purposive Sample
- Quota Sample
|
|
Definition
- Available Sample
- People on the street, easily accessible.
- Notoriously inaccurate -- especially in making inferences about larger population
- Useful in pretesting questionnaires or other preliminary work (pilot study)
- Volunteer Sample
- Sample NOT selected randomly
- Based on people's willingness to express their views
- Many quick polls by the media and online websites
- Purposive Sample
- Dictated by the purpose of the study
- Situational judgments about what individuals should be surveyed to make for a useful sample
- People (or elements) are selected for specific characteristcs or qualities
- E.g., marketing research for users of a new product; research focusing on Internet users
- Quota Sample
- Begins with a table of relevant characteristics of the population
- Proportions of gender, age, education, ethniciity from census data
- Selecting a sample to match those predetermined proportions
- Problems:
- Quota frame must be accurate
- Sample is NOT random
|
|
|
Term
Four types of Probability Sampling: - Simple Random Sample
- Systematic Sample
- Stratified Sample
- Cluster Sample
|
|
Definition
- Simple Random Sample
- A number is assigned to each element
- Numbers are reandomly selected into the same
- Random number sample
- RDD in telephone surveys
- handling invalid numbers: (A) randomly generate a four-digit phone number, and (B) add a predetermined number
- Systematic Sampling
- Select every nth element with random start
- E.g., 1000 on the population list, choosing ever 10th name yields a sample of 100
- Sampling interval: standard distance between units on the sampling frame
- Sampling interval=population size/sample size
- Sampling ratio: proportion of population that are selected
- Sampling ratio=sample size/population size.
- Stratified Sampling
- Modification used to reduce potential for sampling error
- Research ensures that certain groups are represented proportionately in the sample
- Randomly select within groups in proportion to relative group size
- E.g., if the population is 60% female, stratified sample selects 60% females into the sample
- E.g., stratifying by region of the country to make sure that each region is proportionately represented
- Cluster Sampling
- Frequently, there is no convenient way of listing the population for sampling purposes
- E.g., sample of Yolo County or CA: hard to get a list of the population members
- Cluster samples: Samples of lower-level clusters
- A) Sample of census blocks
- B) List of people for selected census blocks
- C) Select sub-sample or people living on each block
|
|
|
Term
Sampling Error/Standard Error (Mng., relationship w/ sample size) |
|
Definition
- Sampling error: The degree of error to be expected in probability sampling
- Every time you draw a sample from the population, the parameter estimate will fluctuate slightly.
- EX:
- Population age: 37.0
- Sample 1: mean age=37.2
- Sample 2: mean age=36.4
- Sample 3: mean age: 38.1
- If you draw lots of samples, you would get a normal curve of values
- Standard error: The average distance of parameter estimates from the population parameter
- As the sample size increases:
- the standard error decreases
- in other words, parameter estimate (from sample statistic) is likely to be closer to the population parameter
- as the sample size increases, we get more confident in our parameter estimate
|
|
|
Term
| Confidence Level/Confidence Interval |
|
Definition
- Confidence levels
- 68% sure estimate is within 1 S.E. of parameter
- 95% sure estimate is within 2 S.E.
- 99% sure estimate is within 3 S.E.
- Confidence interval: interval width at which we are 95% confident contains the population parameter
- Shrinks as:
- Standard error is smaller
- Sample size is larger
|
|
|
