Textbook Notes (270,000)
CA (160,000)
Ryerson (10,000)
MKT (900)
MKT 500 (40)
Chapter 9

# MKT 500 Chapter Notes - Chapter 9: Simple Random Sample, Sample Size Determination, Sampling Error

Department
Marketing
Course Code
MKT 500
Professor
Helene Moore
Chapter
9

This preview shows half of the first page. to view the full 3 pages of the document.
Wk. 3 Chapter 9 Sampling
Lecture on: September 18, 2012
**explore XL Data Analyst
Basic concepts in samples and sampling
- Population: entire group under study as specified by the research project
- Sample: subset of the population that would represent the entire group
- Census: defined as an accounting of everyone in the population
- Sampling error:
o The method of sample selection
o The size of the sample
- Sample frame: master list of all members of the population
Determining size of a sample
- How to calculate sample size page 296 for formula
o Adjusted sample size = calculated sample size * (1/incidence rate %) * (1/response
rate %)
- Sometimes sample size must be adjusted because of time pressure, cost constraint, study
objectives, and data analysis procedures
How to select a representative sample
- Probability sampling:
o Simple random sampling: random digit dialling, table of random numbers, etc.
Probability of selection = sample size/population size
o Systematic sampling: “skip interval” – every third person for example
Skip interval = population list size/sample size
o Cluster sampling: population is divided in similar groups researcher can select few
clusters or draw samples from each cluster
Area sampling: researcher divides the population to be surveyed into
geographic areas such as census tracts, cities, neighborhoods etc.
One-step area sampling: researcher may believe the various geographic
areas to be sufficiently identical to permit them to concentrate on one area
and then generalize the results to the full population
Two-step area sampling: choose random sample of areas, and then decide on
a probability method to sample individuals within the chosen areas
o Stratified sampling: if the population is believed to have a skewed distribution for
one of more of its distinguishing factors, the researcher identifies subpopulations
called strata. A random sample if taken from each stratum.