Grand Canyon University Reliability and Validity Discussion

Grand Canyon University Reliability and Validity Discussion

250 words and 1-2 scholarly resources for each response to each classmate for full credit.

1) John Gallegos

Topic 3 DQ 1 (Obj. 3.3 and 3.4)

Hello Everyone,

When a counselor used a reliable or valid assessment tool they are making an informed or descriptive decision with consistency. The tool used measures the variable and/or phenomena it is supposed to, and it does it with the least amount of bias (Sheperis, Young & Daniels, 2017, p.83). Reliability can mean the theirs is error freedom and consistency in making an assessment (Sheperis, Young & Daniels, 2017, p.80). There are a lot of confounding variable that are present in the natural environment that could change or effect the research from being reliable.

When the researcher can not control the extraneous variables there is a threat to experiential validity (Sheperis, Young & Daniels, 2017, p.113). When a researcher chooses their participants from an environment, it makes a difference in how the group of participants completed the experiment. Next there is maturation in which the participants, emotional, intellectual, and physical functioning changes over time (Sheperis, Young & Daniels, 2017, p.113). To reduce the threats to the study making sure the sample size is chosen ahead of time and at random. Random assignment would protect against bias and the influence of biases (Sheperis, Young & Daniels, 2017, p.113). Another way to control for threat to the study by using counter balancing. Counter balancing reduces threats by finding all the treatment orders and using random assignment equally through participants (Kooken, Welsh, McCoach, Miller, Chafouleas, Riley-Tillman & Fabiano, 2017, p.100).


Kooken, J., Welsh, M. E., McCoach, D. B., Miller, F. G., Chafouleas, S. M., Riley-Tillman, T.

C., & Fabiano, G. (2017). Test order in teacher-rated behavior assessments: Is

counterbalancing necessary? Psychological Assessment, 29(1), 98–109. https://doi- (Supplemental)

Sheperis, C., Young, J., & Daniels, M. H. (2017). Counseling research: Quantitative, qualitative,

and mixed methods (2nd ed.). Upper Saddle River, NJ. Pearson. Retrieved from

2) Courtney Glicken

Topic 3 DQ 1 (Obj. 3.3 and 3.4)

Reliability and validity are two ways for a counselor to know if the assessment they are using for research is accurate and measures what it was intended for, and to ensure that the assessments are free of biases and inconsistencies that could affect the results (Sheperis, Young, & Daniels, 2017). Validity is when the test measures what it is supposed to measure (Cohen & Swerdlik, 2018), and reliability is when the results are consistent and can be replicated and used within an outside population. Validity and reliability are important in conducting research because a counselor needs to make sure that their research question, and the way they collect the data, are going to align and create no errors in their research. Some threats to experimental validity include: treating data as a way to validate personal beliefs and thoughts, not having the method and methodology match (Hugh-Jones & Gibson, 2012), using assessment tools that will not measure the research question (Sheperis, Young, & Daniels, 2017) and one last threat to validity is vague questions on an assessment, because the client might answer differently because they did not fully understand what was being asked and this could compromise results. Some ways to reduce any potential threats to reliability and validity is to test and retest to correlate results (Sheperis, Young, & Daniels, 2017), ensure that the assessments being used align with the research question, finding a valid approach for the research (Hugh-Jones & Gibson, 2012), having a large and diverse sample size, and doing the proper research before beginning the project to ensure that any potential errors are reduced and eliminated.


Cohen, R. J. & Swerdlik, M. E. (2018). Psychology and testing: an introduction to tests and measurements (9thed). New York, NY: McGraw-Hill Education.

Hugh-Jones, S. & Gibson, S. (2017). Collecting your data. In Sullivan, C., Gibson, S., & Riley, S. Editor (Eds.), Doing your qualitative psychology project (101-122). Retrieved from…

Hugh-Jones, S. & Gibson, S. (2017). Analyzing your data. In Sullivan, C., Gibson, S., & Riley, S. Editor (Eds.), Doing your qualitative psychology project (127-153). Retrieved from…

Sheperis, C. J., Young, J. S., & Daniels, M. H. (2017). Counseling research: quantitative, qualitative, and mixed methods (2nd ed.). Boston, MA: Pearson.

3) Paul Hoffman

Topic 3 DQ 2 (Obj. 3.2)

The three purposes of good experimental design are; causation, control, and variability. An example of a research project utilizing a quantitative method design is the parent surveys that are conducted through phones or online. In the polls, parents to the target group of children answer a question concerning their children. An analysis of these surveys reveals quantitative facts that are based on numerical data on how the parents responded to the survey question. You can determine the validity and reliability of the design and methods of research by considering if the design and methods meet the different types of validity. These validity types that should be considered are; Construct validity, Convergent validity, Content validity, Face validity, Representation validity, Criterion validity, Concurrent validity, Predictive validity, Statistical conclusion validity, internal validity, External validity and Ecological validity (“,” 2018). If the research design and methods meet the above tests, then their validity and reliability will be confirmed, otherwise not.


Csikszentmihalyi, M., & Larson, R. (2014). Validity and reliability of the experience-sampling method. In Flow and the foundations of positive psychology (pp. 35-54). Springer Netherlands.

Validity of Your Survey Results | Measure Issues of Importance. (n.d.) 2018.