Question 1

Canonical correlation has as its objective the identification of key descriptors on which various predefined events will vary.

Accepted Answer

Canonical correlation aims to identify and measure the relationships between two sets of variables, not to identify key descriptors for predefined events.

Question 2

Canonical correlation allows for the establishment of a predictive model that can simultaneously forecast or explain several phenomena based on an understanding of their correlates.

Accepted Answer

Canonical correlation is used to establish a predictive model that can simultaneously forecast or explain several phenomena by identifying the underlying relationships between two sets of variables.

Question 3

Factor analysis is one of the most popular multivariate techniques.

Accepted Answer

Factor analysis is indeed one of the most popular multivariate techniques used in data analysis.

Question 4

Multidimensional scaling addresses the problem of identifying the dimensions upon which customers perceive or evaluate phenomena.

Accepted Answer

Multidimensional scaling is a technique used for identifying the underlying dimensions or factors that customers use to evaluate or perceive different phenomena. The technique involves creating maps or visual representations of the similarities and differences between different items or stimuli based on customers' perceptions or evaluations. By identifying these dimensions, researchers can gain insight into the ways in which customers categorize and evaluate different products or services, and use this information to develop more effective marketing strategies.

Question 5

Multidimensional scaling techniques result in perceptional maps that describe the positioning of companies or brands that are compared relative to the position they occupy in the minds of customers according to key attributes.

Accepted Answer

Multidimensional scaling techniques are used to create perceptional maps that depict the relative positions of companies or brands based on key attributes in the minds of consumers.

Question 6

Factor analysis is a method for determining the number and nature of underlying constructs or variables among a larger set of measures.

Accepted Answer

Factor analysis is a statistical technique used to identify underlying constructs or dimensions (factors) among a large set of measures or variables.

Question 7

Cluster analysis allows for the classification or segmentation of a larger group of variables into homogeneous subgroups, based on similarities on a profile of information.

Accepted Answer

The answer of Cluster analysis allows for the classification or...

Question 8

Hypotheses are speculations regarding specific findings of the research, therefore they are not useful.

Accepted Answer

Hypotheses are important because they provide a framework for the research and guide the collection and analysis of data. They are educated guesses about what the researcher expects to find, and can be tested and either supported or rejected by the data collected.

Question 9

The t-test is a type of statistical test.

Accepted Answer

The t-test is a widely used statistical test to determine whether there is a significant difference between the means of two groups.

Question 10

Higher rs indicate higher degrees of association.

Accepted Answer

This statement is true. The correlation coefficient (r) ranges from -1 to +1. When r is close to +1 or -1, it indicates a strong association between the two variables. On the other hand, when r is close to 0, it indicates a weak association between the two variables. Therefore, higher rs indicate higher degrees of association.

Question 11

When any observed difference in findings is considered significant enough to influence management decisions, the difference is
A) statistically significant
B) managerially significant
C) both statistically and managerially significant

Accepted Answer

While statistical significance indicates the likelihood that a finding occurred by chance, managerial significance relates to practical importance and whether the finding has practical implications for managerial decision-making. Therefore, when a finding is significant enough to influence management decisions, it is managerially significant, regardless of whether it meets statistical significance criteria.

Question 12

When any observed difference in findings is large enough that it is unlikely to have occurred due to mere chance, it is
A) statistically significant
B) managerially significant
C) both statistically and managerially significant

Accepted Answer

Statistically significant means that the difference observed is unlikely to have occurred due to chance. Managerially significant, on the other hand, refers to whether the observed difference is meaningful and relevant to the decision-making process. While both types of significance are important, the question specifically asks about statistical significance.

Question 13

Hypothesis testing involves all of the following steps except
A) compare the results to the alternative hypothesis but not to the null hypothesis
B) stating the hypotheses
C) determining the costs related to the two types of errors arising from the decisions
D) selecting the significance level

Accepted Answer

Hypothesis testing involves stating the hypotheses, determining the costs related to the two types of errors arising from the decisions, selecting the significance level, conducting the test, and comparing the results to the null hypothesis (not the alternative hypothesis).

Question 14

Hypotheses are stated in which two forms?
A) null and void hypotheses
B) null and alternative hypotheses
C) alternative and original hypotheses
D) null and altered hypotheses

Accepted Answer

Hypotheses are stated in null and alternative forms. The null hypothesis (H0) states that there is no significant difference between two variables or that there is no relationship between them, while the alternative hypothesis (Ha) states that there is a significant difference or relationship between the variables.

Question 15

The _____ hypothesis is stated in terms that indicate you expect to find no difference or no effect.
A) alternative
B) null

Accepted Answer

The null hypothesis is the statement that there is no significant difference between two variables or no significant effect of a treatment or intervention. It is usually the hypothesis that is tested against the alternative hypothesis in statistical analysis.

Question 16

The _____ hypothesis states that you expect to find a difference or effect.
A) alternative
B) null

Accepted Answer

The alternative hypothesis is the hypothesis being tested, which typically states that a difference or effect is expected to exist. The null hypothesis, on the other hand, states that there is no significant difference or effect between the groups being compared.

Question 17

Which statement below is true?
A) only the null hypothesis can be true
B) only the alternative hypothesis can be true
C) both the null and alternative hypotheses can be true at the same time
D) only the null or the alternative hypothesis can be true

Accepted Answer

In hypothesis testing, we assume two hypotheses: null and alternative hypothesis. We test the null hypothesis against the alternative hypothesis. We either reject the null hypothesis or fail to reject it. If we reject the null hypothesis, we accept the alternative hypothesis. The null hypothesis represents the status quo, and the alternative hypothesis is what we are trying to prove.

In hypothesis testing, we cannot prove the alternative hypothesis; we can only fail to reject it. Hence, we can only say that the null hypothesis is false or that we have insufficient evidence to reject it. Therefore, only the null or the alternative hypothesis can be true. Both cannot be true at the same time because the two hypotheses contradict each other.

Question 18

When testing a hypothesis in any particular study, the researcher can make
A) only a type 1 error
B) only a type 2 error
C) both a type 1 and 2 error at the same time
D) only a type 1 or a type 2 error, but not both

Accepted Answer

A researcher can make either a type 1 error (rejecting a true null hypothesis) or a type 2 error (failing to reject a false null hypothesis), but not both simultaneously in the same test.

Question 19

In setting the level of significance if costs associated with type 1 error are
A) high and a type 2 error is not costly set the level of significance very low
B) high and a type 2 error is not costly set the level of significance very high
C) not very high and a type 2 error is costly set the level of significance very low
D) not very high and a type 2 error is not costly set the level of significance much higher

Accepted Answer

When costs associated with type 1 error are high and a type 2 error is not costly, it is important to minimize the probability of making a type 1 error (i.e. reject a true null hypothesis). This can be achieved by setting the level of significance very low, such as 0.01 or 0.001, to increase the stringency of the test and reduce the chance of a false positive result. However, if costs associated with type 1 error are not high and a type 2 error is costly, a higher level of significance may be more appropriate to reduce the probability of a false negative result (i.e. fail to reject a false null hypothesis).

Question 20

The greater the costs associated with Type 1 error, the _____ we should set our maximum risk.
A) higher
B) lower

Accepted Answer

If costs associated with Type 1 error are greater, it means that making an incorrect decision could have serious consequences. Hence, we should set our maximum risk at a lower level to minimize the chance of making a Type 1 error.

Quiz 12: Advanced Data Analysis

Canonical correlation has as its objective the identification of key descriptors on which various predefined events will vary.

Canonical correlation allows for the establishment of a predictive model that can simultaneously forecast or explain several phenomena based on an understanding of their correlates.

Factor analysis is one of the most popular multivariate techniques.

Multidimensional scaling addresses the problem of identifying the dimensions upon which customers perceive or evaluate phenomena.

Multidimensional scaling techniques result in perceptional maps that describe the positioning of companies or brands that are compared relative to the position they occupy in the minds of customers according to key attributes.

Factor analysis is a method for determining the number and nature of underlying constructs or variables among a larger set of measures.

Cluster analysis allows for the classification or segmentation of a larger group of variables into homogeneous subgroups, based on similarities on a profile of information.

Hypotheses are speculations regarding specific findings of the research, therefore they are not useful.

The t-test is a type of statistical test.

Higher rs indicate higher degrees of association.

When any observed difference in findings is considered significant enough to influence management decisions, the difference is

When any observed difference in findings is large enough that it is unlikely to have occurred due to mere chance, it is

Hypothesis testing involves all of the following steps except

Hypotheses are stated in which two forms?

The _____ hypothesis is stated in terms that indicate you expect to find no difference or no effect.

The _____ hypothesis states that you expect to find a difference or effect.

Which statement below is true?

When testing a hypothesis in any particular study, the researcher can make

In setting the level of significance if costs associated with type 1 error are

The greater the costs associated with Type 1 error, the _____ we should set our maximum risk.