Term
| Stages in the Selection of a Sample |
|
Definition
1) define target population
2) select sampling frame
3) determine if a probability/non-probability sampling method will be chosen
4) plan procedure for selecting sampling units
5) determine sample size
6) select actual sampling units
7) conduct fieldwork |
|
|
Term
|
Definition
- Budget and time
- Limited access to total population
- Accurate/reliable results
- Destruction of test units |
|
|
Term
| Questions to ask when defining the population |
|
Definition
- Is a list available that matches the population?
- What are the relevant market segment characteristics?
- Where is the population?
- Does the study include multiple populations? |
|
|
Term
|
Definition
- Define target population
- List of elements from which a sample may be drawn
- AKA working population |
|
|
Term
|
Definition
- Occurs when certain sample elements are not listed or are not accurately represented in a sampling frame
- ex) using a telephone directory would skew to an older market segment |
|
|
Term
|
Definition
- Sampling services (list brokers) provide lists or databases
- Reverse directory: listings by city/street address or by phone number
- Online panels
- Opting in
- International research: availability of sampling frames varies dramatically around the world |
|
|
Term
|
Definition
- Primary sampling unit (unit selected in the first stage of sampling)
- Secondary sampling unit
- Tertiary sampling unit |
|
|
Term
|
Definition
- Difference between sample results and results of a census
- Decreases as sample size increases |
|
|
Term
| Systematic (nonsampling) error |
|
Definition
| - Results from nature of a study's design and execution |
|
|
Term
|
Definition
| - Every member of the population has a known, nonzero probability of selection |
|
|
Term
|
Definition
- Probability of any member of the population being chosen is unknown
- Convenience sampling, judgment (purposive) sampling, quota sampling, snowball sampling |
|
|
Term
|
Definition
- Initial respondents: probability sample
- Later respondents chosen based on info from initial |
|
|
Term
|
Definition
- Same objective as stratified sample
- There may be bias because respondents chosen were similar to interviewer, or easily found, or willing to be interviewed
- Advantages of quota sampling over probability: speed of data collection, cheaper, convenience |
|
|
Term
|
Definition
| - Simple random sampling, Systematic sampling, Stratified sampling, cluster sampling |
|
|
Term
|
Definition
| - starting point is selected by random process, then every nth number on the list |
|
|
Term
| Proportional stratified sample |
|
Definition
| - Number of sampling units drawn from each stratum is in proportion to the population size of that stratum |
|
|
Term
| Disproportional stratified sample |
|
Definition
| - Sample size for each stratum is allocated according to analytical considerations |
|
|
Term
|
Definition
- Sampling unit is a large cluster of elements
- Clusters are selected randomly
- Used to save money |
|
|
Term
|
Definition
- Type of cluster sampling
- Uses two or more probability sampling techniques
- Typically, geographic areas are randomly selected in progressively smaller (lower-population) units |
|
|
Term
| Criteria for selecting the right sample design |
|
Definition
- Degree of accuracy
- Resources: cost
- Time
- Advance knowledge of population
- National vs. local products
- ex) widely used consumer good vs. hybrid car |
|
|
