Market Research Exam 2

Open-ended question

allows for a wide range of answers, encouraging detailed responses and deeper insights, unlike closed-ended questions that can be answered with a simple "yes" or "no". 

Leading question

a question that prompts or encourages the desired answer.

Ambiguous question

unclear, vague, or open to multiple interpretations, potentially leading to confusion or inaccurate responses. 

Structured questions

Questions that pre specify the set of response alternatives and the response format. A structured question could be multiple-choice, dichotomous, or a scale.

Dichotomous question

A structured question with only two response alternatives, such as yes or no.

Double-barreled question

A single question that attempts to cover two issues. Such questions can be confusing to respondents and can result in ambiguous responses.

Why is it important to consider the respondent’s ability to answer a particular question?

When designing surveys or questionnaires, it's crucial to ensure that respondents have the knowledge, experience, or memory needed to answer the questions accurately. If a question is beyond the respondent’s understanding or recall, their answers can lead to misleading or invalid data.

Example:

Suppose you're conducting a survey on consumer behavior and ask:

“How many ounces of milk did you consume last month?”

Most people don’t track their milk consumption in ounces over a whole month. They might guess or leave it blank, which affects data quality. A better question might be:

“How many times per week do you typically drink milk?”
This version is easier to answer and yields more reliable information.

Why is pretesting important?

Pretesting (or pilot testing) is the process of trying out your questionnaire with a small sample before the full rollout. It helps identify:

• Ambiguous or confusing questions

• Technical or wording issues

• Flow problems or fatigue

• Whether respondents interpret questions as intended

Without pretesting, you risk collecting flawed data or discovering issues too late to fix.

Guidelines for Questionnaire Sequencing

• Start with easy and engaging questions to build respondent confidence.

• Group related questions together to create a logical flow and reduce cognitive load.

• Place sensitive or personal questions toward the end so that respondents are more comfortable and invested.

• Use a funnel approach: Start with broad questions, then move to more specific ones.

• Demographic questions are usually placed at the end unless they’re used to route questions earlier on.

Census

A complete enumeration of the elements of a population or study objects.

Sample

A subgroup of the elements of the population selected for participation in the study.

Target Population

The collection of elements or objects that possess the information the researcher seeks and about which the researcher will make inferences.

Probability sampling

A sampling procedure in which each element of the population has a fixed probabilistic chance of being selected for the sample.

Nonprobability sampling

Sampling techniques that do not use chance selection procedures, but that instead rely on the researchers personal judgment and/or convenience. 

Simple random sampling

A probability sampling technique in which each element in the population has a known and equal probability of selection. Every element is selected independently of every other element, and the sample is drawn by a random procedure from a sampling frame. 

Proportionate stratified sampling

a sampling method where the sample size from each stratum (subgroup) is proportional to the size of that stratum in the overall population, ensuring a representative sample. 

Simple one-stage cluster sampling

a probability sampling method used to select a representative sample from a large population that can be naturally or conveniently divided into groups, known as clusters. 

In two-stage cluster sampling

a simple random sample of clusters is selected and then a simple random sample is selected from the units in each sampled cluster

Systematic sampling

A probability sampling technique in which the sample is chosen by selecting a random starting point and then picking every ith element in succession from the sampling frame.

Convenience sampling

A nonprobability sampling technique that attempts to obtain a sample of convenient elements. The selection of sampling units is left primarily to the interviewer. 

Quota sampling

A nonprobability sampling technique that is a two-stage restricted judgmental sampling. The first stage consists of developing control categories or quotas of population elements. In the second stage, sample elements are selected based on convenience or judgment. 

Judgmental sampling

A form of convenience sampling in which the population elements are purposively selected based on the judgment of the researcher. 

Snowball sampling

A nonprobability sampling technique in which an initial group of respondents is selected randomly. Subsequent respondents are selected based on the referrals or information provided by the initial respondents. This process may be carried out in waves by obtaining referrals from referrals. 

What are the advantages of a sampling study?

1. Cost-Effective

   • It’s much cheaper to survey a sample than an entire population. Fewer resources are needed for data collection, processing, and analysis.

2. Time-Saving

   • Sampling allows researchers to obtain results more quickly, which is especially important when decisions need to be made in a short time.

3. More Practical & Feasible

   • In many cases, it’s simply not possible to reach every member of a population (e.g., all consumers in a country). Sampling makes research manageable.

4. High Accuracy (When Done Well)

   • With proper sampling methods (like random or stratified sampling), a sample can accurately reflect the population, providing reliable insights.

5. Less Data to Manage

   • Handling smaller datasets reduces the risk of data entry errors and simplifies analysis, storage, and reporting.

6. Enables In-Depth Analysis

   • Researchers can allocate more resources per respondent, leading to higher-quality data and more detailed insights.

7. Minimizes Respondent Fatigue

   • You avoid over-surveying the population, which can lead to lower participation rates or poor-quality responses in large-scale censuses.

What are the steps in stratified sampling?

1. Divide the population into distinct subgroups (strata)

   • Each element belongs to only one stratum.

   • No elements are left out.

2. Randomly sample from each stratum

   • Ideally using Simple Random Sampling (SRS) or another probability method.

How does proportionate stratified sampling differ from disproportionate stratified sampling?

• Proportionate Stratified Sampling:
  Each stratum is sampled in proportion to its size in the population.
  E.g., if 60% of the population is female, 60% of the sample will be female.

• Disproportionate Stratified Sampling:
  Strata are sampled unequally, often to ensure enough data from smaller groups.
  E.g., oversampling a small demographic group to allow subgroup analysis.

Steps in Cluster Sampling

Divide the population into clusters

• Clusters must be:

  • Mutually exclusive (no overlap)

  • Collectively exhaustive (all elements included)

Randomly select clusters

• Use Simple Random Sampling (SRS) or another probability method to choose clusters.

Select elements from each chosen cluster

• One-stage cluster sampling: Include all elements in each selected cluster.

• Two-stage cluster sampling: Randomly sample some elements within each selected cluster.

How does the precision of cluster sampling compare with simple random and stratified sampling?

• Less precise than simple random and stratified sampling, because individuals within a cluster tend to be more similar to each other (intra-cluster correlation), reducing variability.

• Larger sample sizes are often needed for the same level of precision.

How can the precision of cluster sampling be increased?

• Increase the number of clusters selected.

• Reduce the size of each cluster (more small clusters rather than a few large ones).

• Use stratified cluster sampling to ensure diversity.

• Use two-stage sampling to increase variability and representativeness.

How does single-stage cluster sampling differ from two-stage sampling?

• Single-Stage Sampling:
  All elements in each selected cluster are surveyed.

• Two-Stage Sampling:
  A random sample of elements is selected from within each chosen cluster, rather than surveying everyone.

What are the advantages and disadvantages of cluster sampling?

Advantages:

• Cost-effective and practical for large, dispersed populations.

• Requires fewer resources (especially for geographic sampling).

• Easier to manage logistically.

Disadvantages:

• Lower precision due to similarity within clusters.

• Increased sampling error compared to simple or stratified random sampling.

• Can introduce bias if clusters aren't representative.

Steps in Systematic Sampling

1. Determine the population size (N)

2. Decide the desired sample size (n)

3. Calculate the sampling interval (i):

4. Select a random starting point between 1 and i.

5. Select every ith element starting from the random number.

Under what circumstances are nonprobability samples appropriate?

• Exploratory research

• Limited resources or time

• When specific subgroups or hard-to-reach populations are being studied

• Pilot testing instruments before full-scale probability sampling

Steps in Quota Sampling 

1. Developing Quotas (Control Categories)

• The researcher identifies key characteristics (e.g., age, gender, race) relevant to the study.

• Estimates the proportion of each group in the target population (using past data or secondary sources).

• Sets targets (quotas) to match the population distribution.

📌 Example: In a cosmetics study, white women aged 18–35 might be set as a control category. If they represent 40% of the population, they should also make up 40% of the sample.

2. Selecting Respondents

• Researchers use judgment or convenience sampling to fill each quota.

• The only rule: respondents must fit the control characteristics.

⚠ Selection within each quota is not random, which introduces potential bias.