Instructions:

 -Each response to another must be at least 175 words in length.

While opinions and reactions are personal and subjective in nature, they need references and citations for support. This approach reflects knowledge acquisition as well as application and synthesis of content. In other words, always support your work with resources. This is also applies to article reviews and/or reflection exercises…you still must have at least two references….one of which will always be your textbook.  

(Cohen, R. J., & Swerdlik, M. E. (2018). Psychological testing and assessment: An introduction

     to tests and measurement (9th ed). New York, NY: McGraw-Hill.)

(Peer Post)

Discuss the impact of each scale of measurement on the ability or inability to be utilized on a test being standardized as a norm-referenced or criterion-referenced assessment. For the purpose of this discussion, you may cluster the ordinal and interval scale together. Subsequently, your post will include the following four elements:

• Ordinal or interval scale of measurement and norm-referenced test.
• Ordinal or interval scale of measurement and criterion-referenced test.
• Ratio scale of measurement and norm-referenced test.
• Ratio scale of measurement and criterion-referenced test.

Provide at least one example that is not in your Psychological Testing and Assessment text for each combination above and describe how the referencing data would be collected. 

• Ordinal or interval scale of measurement and norm-referenced test. 

An example of a nominal scale of measurement is client numbers assigned to each of our clients at work. To avoid violating HIPAA, numbers are assigned to each client during attendance checks in the morning. These numbers are used to “label” each client without having any sort of quantitative value to the numbers, rather just allows the center to keep track of how many students are present in the building (Cohen & Swerdlik, 2017). Nominal scales are mutually exclusive and lack numerical significance therefore in this example, there would not be any norm-referenced testing or assessment conducted (Huitt, 1996). The numbers will be used to count the number of clients present in the building during a certain period of time.

• Ordinal or interval scale of measurement and criterion-referenced test.

Ordinal scale of measurement tells us the order of the numerical values from lowest value to highest value, however, the differences between each value is unknown (Cohen & Swerdlik, 2017). An example of an ordinal scale of measurement is the surveys that I take about my supervisors and their performance. We are asked a series of statements and choose between numbers 1-5; 1 being “do not agree” and 5 being “agree”. When the supervisor gets her results, he/she will be able to identify the truth in each statement from most truthful to least applicable, however she will not be able to necessarily determine the significant difference between each answer. Based on the survey answers, her performance is measured using the ordinal scale and the results are interpreted using criterion-reference assessment (Huitt, 1996). This means depending on what her survey indicates, comparing her performance against a fixed set of standards or criteria, she may or may not get a bonus. For example, if she scores a 4 or higher in more than 75% of the questions, she will get a bonus.

• Ratio scale of measurement and norm-referenced test.

An example of a ratio scale of measurement is grading an organic chemistry exam and whether or not there will be a curve in the class. Using the norm-referenced test, the professor will determine the average test scores of the class and how students scored compared to the other students resulting in a curve on the final grade of the class.

• Ratio scale of measurement and criterion-referenced test.

Ratio scale of measurement provides us with the most information when it comes to measuring data. It indicates the difference between numbers, indicates the direction of the difference, the amount of difference, and has an absolute zero (Cohen & Swerdlik, 2017). An example of ratio scale of measurement is criteria of skill acquisition used with my clients. In collecting data, we use certain percentages as scales to determine whether or not the client has mastered a certain skill or can move on levels in a program. For example, if a client independently answers a specific question with 80% independence, he or she has mastered that certain question and can move on to the next. To assess this measurement of data, criterion-reference assessment is used. A client must obtain certain percentages based on a set of criteria that applies to all clients who have the specific skill acquisition goal (Huitt, 1996).

Provide a statement that evaluates which scale of measurement appears to be the most useful for examining attributes in psychology. Explain.

The ratio scale of measurement appears to be the most useful scale in examining attributes in psychology. I think having the absolute zero attribute is crucial and plays a significant role in measuring attributes in the field of psychology because it accurately depicts measurable data; being that in can’t go in the negatives (Cohen & Swerdlik, 2017). In addition, it meets certain requirements with respect to parameters of the population and numbers can be added, subtracted, multiplied, and divided making scoring more accurate. There are more methods and options to analyze the data in regard to statistics as well with the ratio scale of measurement.

Evaluate which method of referencing (norm or criterion) appears to be the most useful for examining attributes in psychology. Explain your decision based on the area of focus regarding the test results. For example, identify if it is preferable to focus on how one individual performs relative to others who took the same test, or if it is preferable to only focus on what the individual can or cannot do. 

In regards to which method of referencing is best suited, it depends on what data is being measured and tested. I think in examining attributes in psychology such as developmental disabilities and delays, it is best to use norm-referenced testing. Assessing and refencing the scale of measurement for a child who may have a developmental delay requires us to look at a child relative to someone in the same age as him/her. This can help us determine whether or not they are achieving milestones considered to be average in their age range in relation to the rest of children in that age group. Criterion-referenced tests is more applicable in determining whether or not a certain individual has a psychological or mental illness. Because this is something that is not present in all individuals and is not comparable from one person to person, it is more effective to use a set list or predetermined criteria or standards and to use this as reference in assessing the scores (Huitt, 1996).