Question 1

Each dimension determined in MDS represents only one attribute.

Accepted Answer

Each dimension determined in MDS represents a combination of attributes, not just one attribute.

Question 2

Non-metric MDS procedures assume that the input data are ordinal,and they result in ordinal output.

Accepted Answer

False

Question 3

The objective in MDS is to obtain a spatial map that best fits the input data in the smallest number of dimensions.

Accepted Answer

This is the objective of MDS (Multi-Dimensional Scaling), to obtain a spatial map that best represents the input data in a reduced number of dimensions.

Question 4

MDS solutions are subject to substantial random variability.

Accepted Answer

MDS solutions are affected by random variation in the data, leading to different solutions for the same dataset. This makes it important to assess the stability and robustness of the solution through various techniques.

Question 5

The metric and non-metric MDS methods often produce vastly different results.

Accepted Answer

Metric and non-metric MDS methods aim to represent data in lower-dimensional spaces while preserving the pairwise distances or dissimilarities between points as accurately as possible. The main difference lies in how they treat these distances: metric MDS assumes a linear relationship, while non-metric MDS assumes a monotonic relationship. Despite this difference, both methods strive for a similar goal of preserving the original data structure, and while their results can differ, they do not typically produce "vastly different" results when applied appropriately to the same dataset. Differences in outcomes are often more nuanced and related to the specific nature of the data and the assumptions each method makes about the underlying distance or dissimilarity measures.

Question 6

The conjoint analysis procedure is based on trade-offs respondents make when evaluating alternatives.

Accepted Answer

That is correct, conjoint analysis involves presenting respondents with different combinations of attributes and levels, and asking them to choose their preferred option. By analyzing the trade-offs respondents make, researchers can determine the relative importance of different attributes and levels in driving product or service preference.

Question 7

The number of brands or stimuli selected for use in MDS analysis and the specific brands included determines the nature of the resulting dimensions and configurations.

Accepted Answer

The number and selection of stimuli can strongly influence the resulting MDS dimensions and configuration. Different brands/stimuli may lead to different interpretations and insights about consumer perceptions and preferences.

Question 8

Preference data order the brands or stimuli in terms of respondents' preference for some property.

Accepted Answer

Preference data rank brands or stimuli based on how respondents prefer them, based on certain properties.

Question 9

Derived approaches to collecting perception data require respondents to rate the brands or stimuli on the identified attributes using semantic differential scales or Likert scales.

Accepted Answer

This statement is true. Derived approaches involve identifying specific attributes and having respondents rate the brands or stimuli on these attributes using scales such as semantic differential scales or Likert scales.

Question 10

The direct approaches to collecting perception data are used more frequently than the attribute-based approaches.

Accepted Answer

Direct approaches, such as asking individuals for their opinions or ratings on a specific product or service, are easier and quicker to implement, and therefore are more commonly used than attribute-based approaches, which require more time and resources to develop and administer.

Question 11

The metric MDS procedures assume that input data are metric and the output is also metric.

Accepted Answer

Metric MDS requires metric input data and produces metric output, which preserves the pairwise distances between data points in the input and output spaces.

Question 12

Suppose a researcher is interested in obtaining consumer perceptions of automobiles,the choice of the number and specific brands or stimuli to be included in the MDS analysis should be based on the statement of the marketing research problem and theory only.The researcher should not bias the research by also using his judgment to determine what should be included in the analysis.

Accepted Answer

While it is important to base the choice of stimuli on the research problem and theory, the researcher's judgment and expertise can also be valuable in determining the specific brands or attributes to be included in the analysis. However, the researcher should strive to minimize any personal biases and ensure that the chosen stimuli are relevant and representative of the target population.

Question 13

The fit of an MDS solution is commonly assessed by the stress measure.Stress is a goodness-of-fit measure;higher values of stress indicate better fits.

Accepted Answer

Higher values of stress indicate poorer fits in MDS solutions.

Question 14

The configuration derived from preference data is very similar to that obtained from similarity data.

Accepted Answer

Preference data and similarity data are distinct types of information; preference data reflects individual choices or rankings, while similarity data measures how alike two items are, leading to potentially different configurations.

Question 15

Stress values indicate the proportion of variance of the optimally scaled data that is not accounted for by the MDS model.

Accepted Answer

This is the correct definition of stress values in MDS.

Question 16

Spatial maps are computed in such a way that the fit increases as the number of dimensions decreases.

Accepted Answer

This is true because spatial maps are created by taking high-dimensional data and reducing it to a lower-dimensional space where each point represents a unique location in the data. By reducing the number of dimensions, the fit between the data and the spatial map can actually increase because it allows for more separation and differentiation between different data points.

Question 17

Perception data may be direct or derived.

Accepted Answer

Perception data can be direct, obtained through our senses, or derived, obtained through interpretation, inference, or processing of the direct data.

Question 18

Direct approaches to collecting perception data are attribute-based approaches.

Accepted Answer

Direct approaches to collecting perception data are typically not attribute-based; they involve gathering data directly from individuals' perceptions or opinions, often through surveys or interviews, rather than focusing on specific attributes.

Question 19

In direct approaches to gathering perception data,respondents are asked to make similarity judgments on pairs of various brands or stimuli.

Accepted Answer

In direct approaches to gathering perception data, respondents are asked to make similarity judgments on pairs of various brands or stimuli.

Question 20

Gaps in the spatial map may indicate potential opportunities for introducing new products.

Accepted Answer

Gaps in the spatial map indicate areas where a particular product or service may not be available or may not be meeting the needs of the customers. This can present an opportunity for businesses to introduce new products or services to fill the gap and capture a new market segment.

Quiz 21: Multidimensional Scaling and Conjoint Analysis