NURS 8201 Levels of Measurement
NURS 8201 Levels of Measurement
My research question which has been adjusted is “Does the level of prenatal care in African American women ages 18-40 influence the maternal mortality rate?” The variables involved which are the independent variable and dependent variable play an essential part in the prospective research study. These study variables can take on different values and vary which makes it a part of an empirical phenomenon. The purpose of independent and dependent variables is to be used as tools to formulate and design the research study (Flannelly, Flannelly, Jankwoski, 2014). The independent variable from the research question is the level of prenatal care. The dependent variable from the research question is the maternal mortality rate. The independent variable is the variable that will have the presumed effect on the dependent variable.
The independent variable will be displayed as a nominal measurement which implies numbers that aim to categorize reactions into discreet, jointly, and selected categories. The basis for these categories will serve to identify and separate information using numbers (Prion,2013). In this case, African American women would be the known nominal variable in this research study. The dependent variable is demonstrated as the ordinal measurement which is known as rankings that are prioritized based on the criterion. The maternal mortality rate will be evaluated based on a chart, score, or survey data system.
Factors to consider when analyzing each variable based on the level of measurement includes the purpose of the study, hypotheses, questions, or objectives, research design, level of measurement, previous experience in statistical analysis, statistical knowledge level, availability of statistical consultation, financial resources; and access to statistical software (Gray, Grove, & Sutherland, 2017). Out of these factors, I would say the hypothesis is one of the most important elements because it clearly determines what statistics are needed to test the variables. A decision tree is also imperative to put together when analyzing data based on the variables because it can guide your decisions by narrowing alternatives presented. A challenge in making a decision tree, however, is that if you make an incorrect or uninformed decision (guess), you can be led down a path where you might select an inappropriate statistical procedure for your study (Gray, Grove, & Sutherland, 2017).
Flannelly, L.T., Flannelly, K.J., & Jankwoski, K.R. (2014). Independent, Dependent, and Other Variables in Healthcare and Chaplaincy Research, Journal of Health Care Chaplaincy, 20(4), 161-170.
Gray, J.R., Grove, S.K., & Sutherland, S. (2017). Burn’s and Grove’s the practice of nursing research: Appraisal, synthesis, and generation of evidence (8th ed.), St. Louis, MO: Saunders Elsevier
Prion, S. (2013). Making Sense of Methods and Measurement: Levels of Measurement for Quantitative Research. Clinical Simulation in Nursing, 9(1), 35-36.
Click here to ORDER an A++ paper from our Verified MASTERS and DOCTORATE WRITERS NURS 8201 Levels of Measurement:
Your discussion post on levels of measurement is outstanding, informative, and well done. Essentially, selecting a suitable statistical method is essential in the analysis of research questions and data. Inappropriate selection of statistical methods leads to serious challenges during the interpretation of findings and compromises the study conclusion. In statistics, every situation is associated with an existing statistical method to analyze and interpret the data (Daniel & Cross, 2018). Therefore, researchers must acknowledge the assumptions and state of the statistical methods to identify an appropriate statistical method to facilitate data analysis. Apart from understanding the statistical methods, it is also important to consider the aspects of type and nature of the collected data and the aims of the study because, based on the objective of the study, the resultant statistical methods are identified which are appropriate on given data (Mishra et al., 2019). Understanding and applying appropriate statistical methods is essential in ensuring accurate data analysis and helping in avoiding the practice of inappropriate statistical methods, which is prevalent in published research articles (Grove & Gray, 2018).
Daniel, W. W., & Cross, C. L. (2018). Biostatistics: a foundation for analysis in the health sciences. Wiley.
Grove, S. K., & Gray, J. R. (2018). Understanding Nursing Research E-Book: Building an Evidence-Based Practice. Elsevier Health Sciences.
Mishra, P., Pandey, C. M., Singh, U., Keshri, A., & Sabaretnam, M. (2019). Selection of appropriate statistical methods for data analysis. Annals of cardiac anaesthesia, 22(3), 297. doi: 10.4103/aca.ACA_248_18
Research problem: How will the implementation of a sepsis protocol be beneficial among the treatment for the critically ill patient population (i.e. Covid-19)?
Independent variable- sepsis protocol- Interval level
Dependent variable- critically ill population- Ordinal level
In the expansive world of research, it is important to understand the level of measurement of variables in research, because the level of measurement determines the type of statistical analysis that can be conducted and therefore the type of conclusions that can be drawn from research. In my research problem, my independent variable would be the sepsis protocol and is classified as an interval level of measurement, because it is considered a common and constant unit of measurement. According to Statistic Solutions (2020), the interval level not only classifies observations into categories that are mutually exclusive but also have some relationship among them. It is also called a continuous level variable and a successful implementation of sepsis protocols should include demographical data (age, race, income, and co-morbidity), distribution (frequency and pattern), and population (school, neighbor, city, state or country). Numerical values can be assigned to arbitrary measurements that may or may not have differences.
In a data collection performed by Sakr et.al (2018), as sepsis remains a major health problem in ICU patients worldwide and is associated with high mortality rates; there is a wide variability and range in the sepsis rate and outcomes in the ICU patients globally. This interval measurement’s advantages include data is crucially important to increase awareness of the global impact of sepsis, highlight the need for continued research into potential preventive and therapeutic interventions, and help guide resource allocations. Furthermore, information on patterns of sepsis around the globe is also of interest, including causative microorganisms, primary source of infection, associated outcomes, and international differences in occurrence rates. The interval scale of measurement provides equal intervals among different categories or variables associated within a sepsis protocol and can take negative or positive values among statistical analysis.
The main challenge of interval levels of measurements is that there is no absolute zero with no fixed beginning. This in part that sepsis provides large multiple data collection in the ICU would not provide precise information on subtypes of microorganisms needed for appropriate antimicrobial coverage, cannot be monitored for errors, and no exact measurement of appropriate sepsis definition. As a result, there is no true definition of sepsis measurement as there can be a variety of measurements which do not have exact or relative values. Interval level of measurements does not always generate more useful data if its uses are highly arbitrary. Therefore, research selection about what should constitute a proper sepsis protocol requires a selection of right statistical technique and data analysis that depends heavily on the variables to be studied and the measurement scales used in the research (Sahifa, 2017)
My dependent variable of the critically ill population can be categorized as in the ordinal level of measurement. This type of measurement depicts some ordered relationship among the variable’s observation and measurements can be in ranked order but without a degree of difference between categories (Goff, 2021) . The critically ill population of the ICU can be categorized into six diagnostic groups based on their severity: traumatic brain injury, multiple trauma, respiratory, neurological, surgery, and medical. These groups are then statistically analyzed and compared to draw inferences and conclusions about the surveyed population with regards to the specific variable and have ordered relationships among them. The critically ill population groups can be assigned numbers for ranking (i.e. the highest number being the worse and the least number represents the least critically ill in the ICU patient population). Ordinal measurements make it easy for the collection, comparison, and categorizing for statistic conversion. The values are indicated in a relative manner and become more informative. It maintains the description qualities within intrinsic order but does not void the origins of scale. The ordinal measurements disadvantages include responses in research that can be too narrow and create or magnify biases. The numerical ranking of each critically ill diagnostic group has no standardized scale of differences of how each score is measured or how each group is different from each other (Allen, 2017).
Allen, M. (2017). Measurements level ordinals. SAGE Journal of Communication research
Methods. Retrieved from https://methods.sagepub.com/reference/the-sage-encyclopedia-of-communication-research-methods/i8473.xml
Goff, S. (2021). What are the advantages and disadvantages of ordinal measurement? Sciencing
Probability and Statistics. Retrieved from https://sciencing.com/advantages-disadvantages-using-ordinal-measurement-12043783.html
Sahifa (2017). Interval scale in research methodology. Reading Craze Article. Retrieved from Http://readingcraze.com/index.php/interval-scale-in-research-methodology/#:~:text=Disadvantages,not%20have%20an%20absolute%20zero.
Sakr, Y., Jaschinski, U., Wittebole, X., Szakmany, T., Lipman, J., Namendys-Silva, S…Vincent,
J.L. (2018). Sepsis in intensive care unit patients: Worldwide data from the intensive care over nations audit. Open Forum Infectious Disease. 5(12). Retrieved from https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6289022/
Statistic Solutions (2020). Data levels and measurements. Complete Dissertation Consulting.
Retrieved from https://www.statisticssolutions.com/free-resources/directory-of-statistical- https://www.statisticssolutions.com/free-resources/directory-of-statistical-analyses/data-levels-and-measurement/analyses/data-levels-and-measurement/
Thank you for that response! In an ideal hospital, there would be a separate ICU for separate systems (i.e. Neuro, cardiovascular, medical and surgical); however, in the hospital that I work in, we only have one intensive care unit. Most of the patients do have multiple co-morbidities while being critically ill affecting multiple organs (sometimes all into failure). Another level of measurement that can be applied to my dependent variable could be the interval level of measurement. Not only can the ICU patients be classified and placed in order, but can also be measured in different levels. One example would be as you mentioned which is a neuro case patient (ICU level of care) but also can have other categories of illnesses such as cardiovascular issues or surgical issues. According to the Corporate Finance Institute (CFI, 2021), interval level of measurements can provide assurance that differences between values are important but are also equal; both share the same intervals, interpretations, and meaning. The interval scale can label and order variables, with a known, and evenly spaced between intervals that there is relationship given between variables (Stevens, 2021). An example would be that most critically ill patients that are admitted in the ICU have either multiple co-morbidities that affect different organs or new medical problems that arise during their stay in the hospital. There is relationship between variables that constitute the critically ill population. It has known and equal distance between each value on the scale.
Corporate Finance Institute (2021). Level of measurement. CFI Education. Retrieved from
Stevens, E. (2021). What are the four levels of measurement? Nominal, ordinal, interval, and
ration explained. Career Foundry Article. Retrieved from https://careerfoundry.com/en/blog/data-analytics/data-levels-of-measurement/
The levels of measurement refer to the relationship between the values assigned to the attributes of a variable. In essence, the measurement level is used to describe information within the values (Berlin et al., 2017). The levels of measurement come in four levels, namely, nominal, ordinal, interval, and ratios (Damasceno, 2020). A researcher can select the level of measurement that is then most appropriate in defining a variable. In my study on the prevalence of obesity among children, the variables that will be assessed include weight and height, the child’s physical activity and nutrition, and family physical activity and nutrition. These variables will be held in the same data file, the survey data.
The height and weight will be based on the BMI calculations from self-reports on the height and weights of the children selected for the study. This implies that height and weight measurement will be a ratio scale. The validity of this measurement will be achieved by comparing the located data with national surveys that had been done on the topic (de Rezende & de Medeiros, 2021). A reliable self-report will have low variation from the national survey. The moderate report would have a significant variation, while unreliable reports would show high variation compared to other national reports. The level of bias found on the self-reports on height and weight would imply that overweight and obesity are underestimates.
The children’s physical activity and nutrition will be measured through an ordinal scale. My study will be measured using the question of whether the sampled participants for the study participated in any form of physical activity with the last month (de Rezende & de Medeiros, 2021). These physical activities will include running, gardening, bike riding, calisthenics, and walking as forms of exercise. The respondents’ responses to this question will be in the form of yes or no questions to record the general physical activities of the selected children for the study.
The family physical activity and nutrition will be measured using an open-ended question that will inquire more on any physical activity that the family has been having in the last month on an ordinal scale. Besides, the family’s nutrition will be measured by the consumption of five or more fruits and vegetables on their daily meals (de Rezende & de Medeiros, 2021). This measure will be compared to the average recommendation on daily fruits and vegetables according to the US Department of Agriculture. The consumption of vegetables and fruits will be combined to reduce confusion on the number of variables considered in the study.
My study will consider height and weight as the independent variable, while physical activity and nutrition on the child will be the first dependent variable. The second independent variable will be family physical activity and nutrition (Berlin et al., 2017). The study will be interested in how the measurement of weight and height is affected by the physical weight and nutrition of the child and the family. The conclusion of the study will be based on the effect that the two independent variables and on the dependent variables considered in this study.
The selected levels of measurement to be included in the study are more effective because they directly approach the data on child obesity. Besides, the results gained from selected levels of measurement would simplify the data analysis process the study’s outcomes (Berlin et al., 2017). However, these measures are prone to biases that might affect the reliability of the study. Precision and assistance of children in answering the questions on the survey would be important in eliminating increased levels of bias.
Berlin, K. S., Kamody, R. C., Thurston, I. B., Banks, G. G., Rybak, T. M., & Ferry Jr, R. J. (2017). Physical activity, sedentary behaviors, and nutritional risk profiles and relations to body mass index, obesity, and overweight in eighth grade. Behavioral Medicine, 43(1), 31-39. https://doi.org/10.1080/08964289.2015.1039956.
Damasceno, B. (2020). Elements of Statistics: Basic Concepts. In Research on Cognition Disorders (pp. 141-147). Springer, Cham.DOI: 10.1007/978-3-030-57267-9_14,
de Rezende, N. A., & de Medeiros, D. D. (2021). How rating scales influence responses’ reliability, extreme points, middle point and respondent’s preferences. Journal of Business Research, 138, 266-274. https://doi.org/10.1016/j.jbusres.2021.09.031