Intro to Marketing Research: Sampling - Probability Sampling, Simple Random Systematic Stratified ProportionalDisproportional Cluster One-Stage Two-Stage Area Advantages/Disadvantages

What It Is

Probability sampling is a method of selecting a sample from a population in which every member of the population has an equal chance of being selected. A classic example of probability sampling is the 2019 American Community Survey (ACS) conducted by the US Census Bureau, which used a stratified sampling method to estimate the population characteristics of the United States. This matters for marketing decision-making because it allows researchers to make inferences about the population based on a representative sample, enabling informed marketing strategies and resource allocation.

Key Terms & Concepts

• Simple Random Sampling: A method of selecting a sample where every member of the population has an equal chance of being selected, often using a random number generator or a random sampling table. (Example: A researcher selects a random sample of 100 customers from a database of 10,000 customers.)
• Systematic Sampling: A method of selecting a sample where every nth member of the population is selected, often used when the population is too large to sample randomly. (Example: A researcher selects every 10th customer from a database of 10,000 customers.)
• Stratified Sampling: A method of selecting a sample where the population is divided into subgroups (strata) and a random sample is selected from each subgroup. (Example: A researcher divides a population of customers into strata based on age and selects a random sample from each stratum.)
• Proportional Stratified Sampling: A method of stratified sampling where the sample size is proportional to the size of each stratum. (Example: A researcher selects a sample of 100 customers, with 20% of the sample coming from each of the five strata.)
• Disproportional Stratified Sampling: A method of stratified sampling where the sample size is not proportional to the size of each stratum. (Example: A researcher selects a sample of 100 customers, with 30% of the sample coming from the largest stratum and 10% coming from the smallest stratum.)
• Cluster Sampling: A method of selecting a sample where the population is divided into clusters and a random sample of clusters is selected. (Example: A researcher selects a random sample of 10 stores from a population of 100 stores.)
• One-Stage Cluster Sampling: A method of cluster sampling where a random sample of clusters is selected and all members of the selected clusters are included in the sample. (Example: A researcher selects a random sample of 10 stores and includes all customers who shop at those stores.)
• Two-Stage Cluster Sampling: A method of cluster sampling where a random sample of clusters is selected and a random sample of members is selected from each selected cluster. (Example: A researcher selects a random sample of 10 stores and then selects a random sample of 20 customers from each of the selected stores.)
• Area Sampling: A method of cluster sampling where the population is divided into geographic areas and a random sample of areas is selected. (Example: A researcher selects a random sample of 10 cities and includes all customers who live in those cities.)
• Sample Size: The number of units in the sample. (Example: A researcher selects a sample of 100 customers.)
• Cronbach’s Alpha: A measure of the reliability of a scale or instrument. (Example: A researcher calculates Cronbach’s alpha for a scale used to measure customer satisfaction.)
• Regression Equation: A statistical equation that models the relationship between a dependent variable and one or more independent variables. (Example: A researcher uses a regression equation to model the relationship between customer satisfaction and price.)
• Type I Error: The probability of rejecting a true null hypothesis. (Example: A researcher calculates the probability of Type I error for a hypothesis test.)
• Type II Error: The probability of failing to reject a false null hypothesis. (Example: A researcher calculates the probability of Type II error for a hypothesis test.)

Common Misunderstandings

• Misunderstanding: Simple random sampling is always the best method of sampling.
• Correction: Simple random sampling is not always the best method of sampling, as it may not be feasible or efficient for large populations. (Example: A researcher may use systematic sampling or stratified sampling for a large population.)
• Misunderstanding: Stratified sampling always requires equal sample sizes for each stratum.
• Correction: Stratified sampling does not always require equal sample sizes for each stratum, as the sample size can be proportional to the size of each stratum. (Example: A researcher selects a sample of 100 customers, with 20% of the sample coming from each of the five strata.)
• Misunderstanding: Cluster sampling always requires a random sample of clusters.
• Correction: Cluster sampling does not always require a random sample of clusters, as a non-random sample of clusters can be used if it is representative of the population. (Example: A researcher selects a non-random sample of stores that are representative of the population of stores.)

Quick Application / Identification

A marketing researcher wants to select a sample of customers to participate in a focus group. The population of customers is divided into five strata based on age, and the researcher wants to select a sample of 100 customers. Which sampling method is most appropriate?

Answer: Stratified sampling with proportional sample sizes.

Explanation: Stratified sampling is most appropriate because the population is divided into subgroups (strata) and the researcher wants to select a sample that is representative of each stratum. Proportional sample sizes are used to ensure that the sample is representative of the population.

Last-Minute Revision

• A sample size of 30 is generally considered too small for most marketing research studies.
• The formula for calculating sample size is n = (Z^2 * p * (1-p)) / E^2, where n is the sample size, Z is the Z-score, p is the population proportion, and E is the margin of error.
• Stratified sampling is used when the population is heterogeneous and the researcher wants to ensure that the sample is representative of each subgroup.
• Cluster sampling is used when the population is geographically dispersed and the researcher wants to select a sample of clusters.
• The Cronbach’s alpha coefficient ranges from 0 to 1, with higher values indicating higher reliability.
• A regression equation is used to model the relationship between a dependent variable and one or more independent variables.
• Type I error is the probability of rejecting a true null hypothesis, while Type II error is the probability of failing to reject a false null hypothesis.
• The probability of Type I error is typically set at 0.05, while the probability of Type II error is typically set at 0.20.
• A two-stage cluster sampling design is used when the population is large and the researcher wants to select a sample of clusters and then a sample of members from each cluster.
• The area sampling method is used when the population is geographically dispersed and the researcher wants to select a sample of areas.