- According to Leedy, D. and Ormrod, J. E, (2015), , “a ratio scale has two characteristics, (p.94) : (a) equal measurement units and (b) an absolute zero point, such that 0 on the scale reflects a total absence of the entity being measured”. In the question, the scientist collects water samples from streams and rivers and saves exactly 1 liter of water from each sample, which means the equal measurement unit has been used. In Addition, the sample could have no bacteria at all (an absolute zero point). As such, the measurement scale of bacteria content reflects a ratio scale.
- An interval scale has two characteristics: “(a) equal units of measurement, and (b) its zero point has been established arbitrarily”. “The intervals between any two successive numbers of degrees reflect equal changes in temperature, but the zero point doesn’t indicate a total absence of heat” (Leedy and Ormrod, 2015, p.93). Therefore, (a) a country’s average annual temperature is an interval scale because if an average of the temperature is 0, that doesn’t indicate there is no heat, still there is heat since 0 degree is wormer than -10 degree, and it doesn’t matter also whether the temperature reported in Fahrenheit or Celsius. (b) Regarding the amount of tourist dollars that the country brings in every year is a ratio scale because the amount in certain year could be many times higher or less than another year. In addition, since a tourism researcher is studying the relationship between the country’s average annual temperature and the amount of tourist dollars that the country brings in every year, and the country’s average annual temperature is an interval scale, therefore, the amount of tourist dollars that the country brings in every year is ratio scale because of the commonality of the characteristics between the interval and ratio scale.
- Nominal scale is “assigning a specific name to anything, and restricting that thing to the meaning of its name” (Leedy and Ormrod, 2015, p.92). Thus, from the previous explanation of the nominal scale, (a) the political party membership is a nominal scale because the number of each category, e.g. 1= registered as Democrat, means the name of category, and doesn’t mean quantity or order. For more illustration, the category 3 = registered as a member of another party doesn’t mean triple as much Democrat party membership with the category 1. Regarding (b) voting frequency, it’s a ratio scale because it has: (1) equal measurement unit in each vote, which is counted as once, and (2) an absolute zero point, which means a membership has not voted at all in the past 5 years.
- From the definition of the nominal scale in the answer of question 3, the measurement scale that the researcher’s coding scheme for the regions represents a nominal scale because the zip code that above 10000, for example, indicates the category name.
- According to Leedy, D. and Ormrod, J. E, (2015), “With an ordinal scale, we can think in terms of the symbols > (greater than) and < (less than). We can compare various pieces of data in terms of one being greater or higher than another” (p.93). In the question, the economist categories people based on their earning, e.g. group A includes those earning up to $20,000 per year, and group B includes those earning between $20,001 and $50,000 per year and so on. Thus, it’s obvious that people earning in group B higher than those in group A. Therefore, the measurement scale that the economist used is an ordinal scale. On the other hand, the measurement scale here is not a ratio scale because the two characteristics of the ratio scale don’t apply on this study. The absolute zero point means that there is no income at all. Moreover, the measurement units it’s unequal because the ambiguity of the income of poor person or rich person, for example.
- The type of road in this study reflects an ordinal scale measurement because the varying levels of quality. From the definition of the ordinal scale in the answer of question 5, and from the given information in question 6, it’s clear that the traffic pattern in one type of road, e.g. highways, could be higher or lesser than other. On the other hand, the measurement scale here is not a ratio scale because the absolute zero point means that there is no road at all, which is not represented by the categorization scheme.
- The score represents an ordinal scale because the score could be higher or much less if we compared between the students. The measurement scale here in this study is not a ratio scale because obviously all students have anxiety about test. Even though if we suppose that a student chooses never for all the 25 questions, the scale here does not reflect the value of something. On the other hand, the measurement scale here in this study is not interval scale because, for example, might a student thinks that a broad range of frequencies of test-anxiety occurrence for the word sometimes, but thinks of often as being a more limited range, therefore, this is unequal unit of
Conceptual Analysis Exercise;
Identifying Problems with Validity and Reliability in Measurement
- According to Leedy, D. and Ormrod, J. E, (2015), “Content validity is the extent to which a measurement instrument is a representative sample of the content area (domain) being measured” (p.97). The test has a content validity issue since the test doesn’t include or measure the tennis skills; the test administrated just the rules of the game.
- “Equivalent forms reliability is the extent to which two different version of the same instrument (e.g., “Form A” and “Form B” of the scholastic aptitude test) yield similar results” (Leedy and Ormrod, 2015, p.99). From the definition, it’s clear that the problem in the study is equivalent forms reliability because the tests yield different results.
- Because the two researchers often disagree about whether certain behaviors constitute “aggression “or, instead, reflect more benevolent of the gorillas in the Virunga Mountains of the northwestern Rwanda as they watch a particular gorilla family and take notes about family members behaviors, the issue in this study is interrater reliability. “Interrater reliability is the extent to which two or more individuals evaluating the same product performance give identical judgments (Leedy and Ormrod, 2015, p.99).
- The problem in this study is criterion validity. “Criterion validity is the extent to which the results of an assessment correlate with another, presumably related measure” (Leedy and Ormrod, 2015, p.97). In this case, the results of the two research assistants don’t seem to have any correlation with the blood-test results.
- “Test-retest reliability is the extent to which a single instrument yield the same results for the same people on two different occasion” (Leedy and Ormrod, 2015, p.99). In this case, the researcher found that a few students were in two classes of the classes surveyed and thus completed the survey twice. However, these students sometimes gave different responses to particular statements on the two different occasions, and hence their overall scores were also different. As such, the problem is test-retest reliability because the different responses to particular statements on the two different occasions.
- According to Leedy, D. and Ormrod, J. E, (2015), the definition of internal consistency reliability “is the extent to which all of the items within a single instrument yield similar results” (p.97). However, in this case, the problem is the questionnaire lacks of internal consistency reliability because different items in the instrument yield different results.
- “Construct validity is the extent to which an instrument measures a characteristic that cannot be directly observed but is assumed to exist based on patterns in people’s behavior”. “Motivation, creativity, racial prejudice, happiness all of these are constructs, in that none of them can be directly observed and measured (Leedy and Ormrod, 2015, p.97). The problem in the questionnaire is that tolerance belief for people of a particular religion cannot be directly observed and measured but is assumed to exist based on patterns in people’s behavior.
- Reaction-time task could be a valid measure, but in this case doesn’t appear to be right. Even though the face validity is not true, a lack of it can sometimes negatively impact the participants’ cooperation in a research project.
Leedy, P. D.; Ormrod , J. E. (2015). Practical Research: Planning and Design, (13 ed.). Pearson