Sampling Techniques

1
Topic 7
Marketing Analysis Research (MAR3613) By
Kanghyun Yoon

• Sampling Techniques

2
Introduction

• Why is the determination of an appropriate sample
  size important?
• A rule of thumb minimum size of 100 or more per
  group.
• However, there is a tradeoff between budget
  availability and the degree of prediction.
• To formally identify the proper sample size,
  understanding statistical theory is necessary.
• Introduction to statistical theory
• Descriptive statistics vs. inferential
  statistics.
• Basics of sampling.
• Population dist., sample dist., and sampling
  distribution.
• Point estimate vs. interval estimate.
• Develop a sampling plan
• Selection of sampling method.
• Discussion of calculating the appropriate sample
  size.
• Introduction to the formula of determining the
  appropriate sample size.

3
Developing a Sampling Plan
Step 1 Define the target population
Step 2 Identify a sampling frame
Step 3 Select a sampling method
Step 4 Determine sample size
Step 5 Select actual sampling units
Step 6 Conduct fieldwork
4
Define Target Population

• Define the target population properly!
• Toy storeAll households with children living in
  Orlando
• Sampling element - which children?
• Sampling units - who in the household?
• Area of coverage - what area?
• Guidelines of identification of target population
• Well thought out research objectives.
• Know your market.
• Consider the appropriate sampling unit.
• Specify clearly what is excluded.
• Should be reproducible - not so restrictive.
• Consider the convenience, depending on the
  research purpose.
• Prepare a sampling frame
• Sampling frame is a list of all elements in the
  population.

5
Select Sampling Method

• Nonprobability Sampling
• Convenience samples
• Judgment samples
• Quota samples
• Snowball samples
• Probability Sampling
• Simple random sampling
• Systematic sampling
• Stratified sampling
• Cluster sampling
• Multistage area sampling

6
Determine Sample Size

• Determining factors
• No. of subgroups to be analyzed
• Budget available
• Ad Hoc methods
• Based on either experience or some constraints
  like budget.
• Rule of thumb gt minimum size of 100 or more per
  group.
• Statistical methods
• Determine the size of the sampling error
• Determine the confidence level (e.g., 95
  confidence level)
• n (z2 s2) / E2, where E acceptance amount
  of sampling error.
• How to estimate s?

7
Basics of Statistical Methods
8
Formula for Sample Size (Means)
9
Three Factors in the Formula

• The magnitude of error (E)
• It indicates how precise the estimate must be
  (e.g., a certain precision level).
• The confidence level (ZCL)
• It indicates how much confident getting the true
  value is.
• We typically use the 95 percent confidence level
  (Z-score 1.96).
• The variance or heterogeneity (S)
• It indicates how all the elements in the
  population are different in terms of key feature.
• We typically use the (unknown) standard deviation
  of the population.
• A rule of thumb for estimating one-sixth of the
  range between max and min.

10
Formula for Sample Size (Proportions)
11
Practice I

• Calculating sample size for means
• Example 1) Suppose a survey researcher, studying
  annual expenditures on lipstick, wishes to have a
  95 percent confident level (Z) and a range of
  error (E) of less than 2.00. The estimate of the
  standard deviation is 29.00. (n 808)
• Example 2) Suppose, in the same example as the
  one before, the range of error (E) is acceptable
  at 4.00, sample size is reduced. (n 202)
• Calculating sample size for means
• Example 3) Suppose a researcher believes that a
  simple random sample show that 60 of the
  population recognizes the name of an automobile
  dealership. The researcher wishes to estimate
  with 95 confidence that the allowance for
  sampling error is not greater than 3.5 percentage
  points (E). (n 753)