Marketing Research: SMQ II, Sampling and Mere Measurement - lec 5

• Marketing Research, Lecture 5 covered SMQ II and Sampling

• Group presentations: March 26 or April 2.

• Groups should email their preferred presentation date by Friday (Feb 7).

• Smaller groups will receive priority for preferred dates.

• Group report guidelines are on quercus.

• =RAND() typed into a cell in MS Excel will generate a random number between 0 and 1.

Morwitz et al. (1993)

• Study regarding likelihood of purchasing a new car.
• Dependent variable: Likelihood of purchasing a new car within 6 months of survey
• Researchers had access to this purchase data.
• Independent variable: Whether or not person took the survey.
• Treatment group: Asked question about purchasing a new car.
• Control group: Not asked the purchase question.

Mere Measurement Effects

• New car purchases in next 6 months nearly 40% higher in treatment group.
• Other mere measurement effects exist.
• Being asked about buying a PC resulted in a 20% higher rate of purchases in the same study.
• Being asked about voting increases propensity to vote
• Repeated online grocery purchases effect results.
• Survey questions have an effect on socially desirable and undesirable behaviours.

Mere Measurement Effects: Repetition

• Morwitz et al. repeatedly asked some of those surveyed about buying a product.
• Results showed a "polarizing" effect.
• Actual purchases in the next 6 months were over 10% higher if repeatedly surveyed vs. surveyed just once among those who said they planned to buy a new car.
• Actual purchases in next 6 months were almost 70% lower if repeatedly surveyed vs. surveyed just once among those who said they never planned to buy a new car.

Mere Measurement Effects: Implications

• Asking questions can create bias by influencing the property trying to me measured, even without "question bias".
• Can undermine representativeness or construct validity.
• Responses should account for the effect of measurement.
• Counteract with decoy alternatives or change product category.

Step 8: Determine Sample Plan and Size

• Population: Who you want to learn about.
• Population does not have to be individual consumers, could be stores for example.
• Sample plan describes how sample elements/units will be drawn from total population.
• Goal: representativeness!
• Sample size is how many population units will be included in the sample
• Goal: accuracy!
• Alternative to sampling: conduct a census of entire population

UTM Example

• UTM considering buying a vending machine that sells magazines for $2 each.
• Collect student info (via a survey) regarding the prospective purchase.
• Survey asked if students would likely use the vending maching if it was installed
• Survey asked where the vending machine should be located
• Survey asked what type of magazines should be made available
• Consider the relevant “population" in this example.
• Decide whether to draw a sample or perform a census.
• If Professor Landry was responsible for the survey, would it make sense to survey entire class?
• Are the students in the class representative of the entire population?
• How would this bias the results?

Basic Concepts in Sampling

• Sample frame is the master list of the population.
• Sample frame error is the degree to which the sample frame fails to match the true population.
• Errors can be incomplete or inaccurate.
• Sampling error is any error that arises because a sample is used.

Types of Sampling Methods

• Probability samples: members of the population have a “known” probability of being selected into the sample
• Non-probability samples: members of the population have an unknown probability of being selected into the sample

Probability Samples: Simple Random

• Simple random sampling: probability of being selected into the sample is known and equal for all members of the population
• Random device method uses an apparatus to ensure every member of the population has the same chance of being selected:
• Old-school devices: coin, dice, deck of cards...

Simple Random (continued)

• Random numbers method: computer generates random numbers
• More practical when sample frame is electronic, for larger populations

Pilot Surveys

• Results of the pilot survey are to be summarized/tabulated in the appendix of the final group project report
• Include copy or screenshot of pilot survey.
• Pilot survey results must be reviewed before designing the final survey.
• Reviewing results helps you design better survey questions
• Final survey should be significantly different than the pilot

Cluster Sampling

• Researcher divides population into "clusters" that could represent population.
• Study based on randomly-selected clusters
• One-stage: perform census of each selected cluster
• Two-stage: draw sample from each selected cluster
• Area sampling: Using geographic areas as clusters.
• Heterogeneous clusters lead to cluster specification error.

Stratified Sampling

• Population separated into distinct strata (subgroups).
• Probability sample drwan from each strata.
• Proportionate stratified sample: Each strata's proportion in the sample is roughly equal to its proportion in the population.
• Otherwise a disproportionate stratified sample results

Stratified Sampling: Why & When to Use?

• Use stratified sampling when there is reason to believe there are substantial differences across easily-identifiable strata
• Graphical indicators: a non-bell-shaped distribution for key properties, e.g. skewed population, multi-peaked population
• Why stratified sampling?:
  • Allows for explicit analysis of each stratum
  • Can improve accuracy & statistical efficiency

Stratified Sampling (cont.)

• Use proportionate stratified sampling if extent of heterogeneity within strata is believed to be roughly the same across strata
  • Improves accuracy by ensuring each strata is adequately represented when using smaller sample size
• Otherwise: disproportionate stratified sampling
  • Sample should draw disproportionately more from highly-heterogeneous strata than from strata that are relatively homogeneous
  • Improves statistical efficiency by allocating more sample size to strata which require more data points to reliably estimate mean response

Types of Non-probability Samples

• Convenience samples: sample is drawn at the researcher's convenience, e.g. from a high-traffic area on a sidewalk or at a mall
• Purposive Sample: Researcher uses judgement/educated guess to decide who should represent population
• Referral Sample: Ask initial respondents for names/contact info of other potential respondents
• Quota Sample: researcher specifies percentages of the total sample for various types of individuals to be surveyed

Lecture 5 discusses SMQ II, Sampling and Group Presentations. Morwitz et al. (1993) study shows that asking consumers about purchasing a new car increased purchases by nearly 40%. This mere-measurement effect also appeared for PC purchases.