Question 1

The statistic used to indicate how much,on average,an individual score differs from the arithmetic mean is known as the:
A) variability.
B) construct reliability.
C) coding.
D) standard deviation.

Accepted Answer

The standard deviation is the most commonly used statistic to measure variability or spread of scores in a set of data. It shows how much scores deviate, on average, from the mean. It is calculated by taking the square root of the sum of the squared differences between each score and the mean, divided by the number of scores minus one.

Question 2

Equivalent-form reliability is another name for:
A) test-retest reliability.
B) alternative-form reliability.
C) internal consistency reliability.
D) Cronbach's alpha.

Accepted Answer

Equivalent-form reliability is also known as alternative-form reliability. This type of reliability involves administering two different forms of the same test to the same group of people and then correlating the scores on the two forms.

Question 3

If the probability of your finding is greater than 10%,you are likely to conclude:
A) the finding is statistically significant.
B) the finding did not occur by chance.
C) the finding has no relationship to a similar study.
D) the finding is not statistically significant.

Accepted Answer

D

Question 4

A hypothesis that makes a specific prediction as to the exact nature of the relationship between two variables is called a:
A) directional hypothesis.
B) nondirectional hypothesis.
C) statistical hypothesis testing.
D) correlational testing.

Accepted Answer

A directional hypothesis predicts the direction of the relationship between two variables. It specifies whether the variables are expected to have a positive or negative correlation. For example, "increased exercise will lead to a decrease in body fat" is a directional hypothesis because it predicts the direction of the relationship between exercise and body fat.

Question 5

If two variables are related and one variable increases as the other variable decreases,they are likely to have:
A) negative correlation.
B) positive correlation.
C) no correlation.
D) no reliability.

Accepted Answer

A negative correlation means that as one variable increases, the other variable decreases. Therefore, if one variable increases as the other variable decreases, they are likely to have a negative correlation.

Question 6

A correlation with a value of 0 means:
A) the variables are strongly positively related.
B) the variables are strongly negatively related.
C) the variables are moderately related.
D) the variables are unrelated.

Accepted Answer

A correlation value of 0 indicates no linear relationship between the variables. They are unrelated.

Question 7

Descriptive statistics almost always include: A) the median and standard deviation. B) R² and standard deviation. C) the mean and standard deviation. D) $\beta$ and standard deviation.

Accepted Answer

Descriptive statistics typically include measures of central tendency, such as the mean or median, and measures of variability, such as the standard deviation. Choice A includes the median and standard deviation, which is a possible combination, but not the most common one. Choice B includes a nonsensical string of letters and numbers, and choice D includes a combination of letters and a symbol that does not make sense in the context of descriptive statistics.

Question 8

Cronbach's alpha refers to:
A) the degree to which individual measurements of a variable differ from one another.
B) a statistic used to indicate how much,on average,an individual scores differs from the arithmetic means of the scores.
C) a statistic used to evaluate the internal consistency reliability of a scale.
D) the conclusion a researcher makes when the probability is that one's hypothesis is unlikely to be incorrect given the data collected.

Accepted Answer

Cronbach's alpha is a statistic used to evaluate the internal consistency reliability of a scale. It measures the degree to which items in a scale are correlated with each other, indicating the scale's homogeneity or the extent to which all items in the scale measure the same construct. A value of Cronbach's alpha of 0.7 or higher is generally considered acceptable for research purposes. Option A refers to variance, option B refers to deviation, and option D refers to hypothesis testing.

Question 9

If you wanted to determine if the scale you are using relates to other measures of the variable then you would be interest in:
A) discriminant validity.
B) convergent validity.
C) concurrent validity.
D) construct validity.

Accepted Answer

The answer of If you wanted to determine if the...

Question 10

A Cronbach's alpha is represented by which symbol?
A) r
B) $\alpha$
C) $\beta$
D)  $\pi$

Accepted Answer

The answer of A Cronbach's alpha is represented by which...

Question 11

Which of the following is an example of a closed-ended question?
A) How did you decide to attend this school?
B) What is your family like?
C) Are you male or female?
D) What makes someone a good friend?

Accepted Answer

The question "Are you male or female?" has a specific answer that is either one option or the other, making it a closed-ended question. The other options could have multiple possible answers and require more explanation, making them open-ended questions.

Question 12

A scoring strategy in which more negative response alternatives are assigned higher numerical values and more positive response alternatives are assigned lower numerical values is called:
A) reverse-coding.
B) response set.
C) directional hypothesis.
D) internal consistency reliability.

Accepted Answer

This strategy is called reverse-coding, as it involves reversing the scoring of certain response alternatives to account for response bias or social desirability. This can help to ensure more accurate measurement of the construct being assessed. The other options are not related to this particular scoring strategy.

Question 13

Reverse-coding minimizes the potential for a(n):
A) forced choice response set.
B) social desirability set.
C) demand response set.
D) acquiescent response set.

Accepted Answer

Reverse coding is a technique used in surveys and questionnaires to minimize the effect of acquiescence bias, where respondents might agree with statements without considering them carefully. By reversing the scoring of some items, it encourages more thoughtful responses and reduces the tendency to agree with all items regardless of their content.

Question 14

If you wanted to determine if the scale you are using relates to a relevant outcome measured at the same time then you would be interested in:
A) construct validity.
B) discriminate validity.
C) criterion validity.
D) concurrent validity.

Accepted Answer

Concurrent validity is when the results of one assessment are compared to another assessment that measures the same thing at the same time. In this case, the researcher wants to determine if the scale being used relates to a relevant outcome measured at the same time, which is concurrent validity.

Question 15

If the probability of your finding is less than 5%,you are likely to conclude:
A) the finding is statistically significant.
B) the finding is not statistically significant.
C) the finding has no relationship to a similar study.
D) the finding has occurred by chance.

Accepted Answer

The answer of If the probability of your finding is...

Question 16

The degree to which individual measurements of a variable differ from one another is called:
A) consistency.
B) variability.
C) deviation.
D) reliability.

Accepted Answer

Variability refers to the degree of difference or spread in the measurements of a variable. Consistency is the degree to which measurements are the same or stable over time. Deviation refers to how far a measurement is from the mean or expected value. Reliability refers to the consistency and accuracy of measurements over time and across different conditions or observers.

Question 17

A quick method of finding out the degree of customer satisfaction at a local supermarket would be through the use of:
A) an essay.
B) a Likert scale.
C) an experimental study.
D) a quasi-experimental study.

Accepted Answer

A Likert scale is a quick and efficient way to gather data on customer satisfaction levels by asking them to rate their experience on a scale of agreement/disagreement. This method allows for easy quantification and analysis of the responses. Essay, experimental, and quasi-experimental studies would be more time-consuming and less practical for quickly obtaining customer satisfaction data in a supermarket setting.

Question 18

If two variables are related and one variable increases as the other variable increases,it is likely to have:
A) negative correlation.
B) positive correlation.
C) no correlation.
D) no reliability.

Accepted Answer

If one variable increases as the other variable increases, it suggests a positive correlation between the two variables. This means that as one variable increases, the other variable also tends to increase. Negative correlation occurs when one variable decreases as the other variable increases. No correlation means that there is no relationship between the variables. No reliability is not a relevant option in this context.

Question 19

If you wanted to determine if a scale is relevant to an outcome or behavior you would be interested in:
A) construct validity.
B) discriminate validity.
C) criterion validity.
D) predictive validity .

Accepted Answer

Criterion validity measures whether a scale is predictive of a specific outcome or behavior, making it the best choice for determining if a scale is relevant to an outcome or behavior. Construct validity refers to whether a scale measures what it claims to measure, while discriminate validity measures whether a scale can differentiate between different groups. Predictive validity refers to the ability of a scale to predict future behavior or outcomes.

Question 20

A researcher discovered that items on a scale did not measure what they were intended to measure.The scale,therefore,has an issue with:
A) construct validity.
B) content validity.
C) predictive validity.
D) concurrent validity.

Accepted Answer

Construct validity refers to how well a test or scale measures the concept or construct it is intended to measure. If the items on the scale do not measure what they were intended to measure, then the scale has a problem with construct validity. Content validity refers to how well a test or scale covers all aspects of the construct it is intended to measure. Predictive validity refers to how well a test or scale predicts future outcomes. Concurrent validity refers to how well a test or scale correlates with another measure of the same construct at the same time. None of these address the issue with the items not measuring what they were intended to measure.

Quiz 7: Survey Design and Scale Construction: Part 2

The statistic used to indicate how much,on average,an individual score differs from the arithmetic mean is known as the:

Equivalent-form reliability is another name for:

If the probability of your finding is greater than 10%,you are likely to conclude:

A hypothesis that makes a specific prediction as to the exact nature of the relationship between two variables is called a:

If two variables are related and one variable increases as the other variable decreases,they are likely to have:

A correlation with a value of 0 means:

Descriptive statistics almost always include:

Cronbach's alpha refers to:

If you wanted to determine if the scale you are using relates to other measures of the variable then you would be interest in:

A Cronbach's alpha is represented by which symbol?

Which of the following is an example of a closed-ended question?

A scoring strategy in which more negative response alternatives are assigned higher numerical values and more positive response alternatives are assigned lower numerical values is called:

Reverse-coding minimizes the potential for a(n) :

If you wanted to determine if the scale you are using relates to a relevant outcome measured at the same time then you would be interested in:

If the probability of your finding is less than 5%,you are likely to conclude:

The degree to which individual measurements of a variable differ from one another is called:

A quick method of finding out the degree of customer satisfaction at a local supermarket would be through the use of:

If two variables are related and one variable increases as the other variable increases,it is likely to have:

If you wanted to determine if a scale is relevant to an outcome or behavior you would be interested in:

A researcher discovered that items on a scale did not measure what they were intended to measure.The scale,therefore,has an issue with: