Evidence Based Practice: Levels of measurement

This is a request for two discussion question reply posts 1 page each:

The reply will be on a post created by Kemline below:

Research question
There is limited understanding of the benefit of antipsychotic drugs for delirium in elderly patients with dementia in a nursing home. Some studies have shown that the unconventional use of antipsychotic drugs for delirium in elderly patients can increase the risk for severe illness and functional decline.

Independent and dependent study Variables
Supportive variables would be long-term nursing home residents with a history of dementia with behavioral changes or patients with a history of delirium. The dependent variable in this study would be the effect of antipsychotic drugs on elderly patients. The independent variable would be the elderly patients in the nursing home with an established diagnosis of delirium or of dementia with behavioral disturbance. I would like to achieve that, eventually, antipsychotic drugs will no longer be used to treat delirium in patients with dementia and other alternative treatments will be used instead.

Level of measurement and challenges
In this study, the most efficient measurement level for the independent variable would be the ordinal level. The data gathered would be directed towards patients with a known diagnosis of delirium and dementia with behavioral disturbance thus these patients would include all patients with behavioral issues. Furthermore, the ordinal scale would allow us to categorize the types of behavioral problems further. The challenge that I can perceive would be the patients with diagnoses of both dementia and other forms of psychosis such as bipolar.

As far as the dependent variable the use of a nominal level of measurement would work best. The drugs can be easily categorized into classes of antipsychotic medications. Of course, the drugs being used off labels for the benefit of delirium would need to be excluded as well as the drugs that can be used for different indications not exclusively for psychosis.

Rudolph, J. L. (2017). Antipsychotic (non)selectivity: A setup for swallowing and side‐effects in seriously ill elderly adults. Journal of the American Geriatrics Society, 65(12), 2564–2565. https://doi.org/10.1111/jgs.15168

Ohsako, N., Hashimoto, T., Shiko, Y., Kawasaki, Y., Nakagawa, M., Okuma, T., Kurata, T., Suzuki, H., Ishige, M., & Kikuchi, S. (2022). Pharmacotherapy for elderly patients with delirium in a general ward setting: A retrospective study. Asian Journal of Psychiatry, 70. https://doi.org/10.1016/j.ajp.2022.103024

The second post to reply to is from Daniel below:

Public stigma is the reaction that the general population has towards people with mental illness. Patients with mental illness are faced with stereotype and prejudice as a result of misconception about their diagnosis. Stigma about mental illness seems to be endorsed by the general public in the Western World. Study has shown that majority of the citizens in the United States and many Western European nations have stigmatizing attitude about mental illness. Furthermore, stigmatization about mental illness are not limited to uninformed members of the general public; even the well trained professionals from mental health disciplines subscribe to stereotype about mental illness, Phelan J., et al. (2000).

What are the Effects of Stigma on people with mental illness in seeking treatment?

Dependent and Independent Variables.
The independent variables for this research will be patient perception about stigma, self- esteem, confidence, and access to social opportunities.
The dependent variable will be the causes of stigma against people with mental health conditions.

Level of measurement

Correlation Analysis will be used to determine the relationship between the dependent and independent variable. Correlation Analysis is used to estimate the change in one variable due to change in the other. If there is shown to be a strong correlation between two variable or metrics, and one of them is being observed acting in a particular way, then you can conclude that the other one is also being affected in a similar manner.


Correlation analysis can reveal meaningful relationship between different metrics or groups of metrics. Information about those connections can provide new insights and reveal independencies, even if the metrics come from different entities.

Correlation analysis can also help to significantly reduce the cost associated with the time spent in investigating meaningless or duplicative alerts. In addition, the time saved can be used on more strategic initiatives that add to the organization

Another important benefit of correlation analysis is anomaly detection. Correlation analysis filter irrelevant anomaly and group correlated anomalies into a single alert.

Limitation of Correlation Analysis

Correlation doesn’t tell us about cause and effect. Correlation also cannot accurately describe curvilinear


Rossler, W. The stigma of mental disorders: A millennia-long history of social exclusion and prejudices. EMBO Reports, 2016. 17(9); 1250-1253.

The Lancet Editorial. The health crisis of mental health stigma. The Lancet, 2016,


Miles S, Price GM, Swift L, Shepstone L, Leinster SJ. Statistics teaching in medical school: opinions of practicing doctors. BMC medical education. 2010;10:75.

Windish DM, Huot SJ, Green ML. Medicine residents’ understanding of the biostatistics and results in the medical literature. JAMA. 2007;298(9):1010–1022