Review

2

Data-Driven Decision Masking

Rolanda Martin

Western Governors University

Mr. Tony Pineda

C207 Data Driven Decision Making

05/15/2024

Data-Driven Decision Masking

Introduction

High nurse turnover rates could increase nursing shortages, which could also result in poor patient outcomes and high health costs. One possible solution to prevent high nurse attrition within a major healthcare system is a nontraditional focus on employee welfare (Dyrbye et al., 2017). A three-year campaign that welcomed voluntary participation and monthly activities aimed at raising nurse morale and relieving work pressure was drawn up. This study examines whether or not this program has any influence on the rate of nurse attrition. It concentrates on a possible link between 36 months' monthly participation rates and attrition in one direction or another. This report studies an existing relationship through linear regression analysis in monitoring the effectiveness of the program. Such relationships can form a solid base from which decisions on measures to encourage nurse retention and improve programs can be made.

Business Question

Is there a strong relationship between the monthly participation rate in the well-being program on an aggregated 36 months for nurses and their nurse attrition rate? The purpose of this question is to assess how the well-being program affects nurse turnover. Investigating the possible relationship between such parameters as each month's proportion of nurse volunteers and a month's attrition statistics for three months in the aggregate, therefore, can help the healthcare system develop reasonable estimates over which program is more effective at helping it achieve its objectives (Morgantini et al., 2020). It might formulate plans regarding nurse retention depending on the effects of different programs on nurses 'resignations or status (Alluhidan et al., 2020).

Data Description

The variables chosen to undergo regression analysis have great meaning for understanding how the healthcare system's well-being program works out. The Monthly Rate of Nurse Participation is an explanatory variable measuring the level at which nursing staff participate in well-being activities. On the other hand, the independent variable, the Nurse Attrition Rate is the ratio of registered nurses who leave their jobs. This is an important leading indicator for workforce stability. With 36 data points covering 36 months, this rich dataset presents the temporal changes in participation and attrition. These help to see how patterns vary over time and follow changing trends.

Linear Regression Analysis

A linear regression graph indicates a negative correlation between nurse participation rate in the well-being program and attrition ratio over 36 months. The regression equation is y = -0.0849x+5.5896, with an R2 of 0.554, indicating that approximately half (or 5 %) of the difference in nurse attrition rate can be explained by participation rates in the wellness program. This graph reflects a recognition that the higher staff Nurse Attrition Rate and lower Wellness Program Participation Rate affect each other negatively. As it is, the formula for the line indicates that an increase in taking part in the wellness program means a decreased rate of nurse attrition. R^2 value indicates that about 55 % of the variation in attrition is accounted for by whether or not they participate in the wellness program. The results of the linear regression analysis indicate that there is a high degree of correlation between the monthly participation rate in the well-being program and nurse attrition over 36 months. The negative relation between the two variables means that when participation in the wellness program is higher, nurse attrition is lower. With an (R^2) value of 0.554, this means that more than half of the variability in nurse attrition can be explained by participation in the wellness program.

Justification for Linear Regression

The use of linear regression as a fitting statistical technique is suitable for this analysis due to its capability of modelling the correlation between two continuous variables. It can be applied to the examination of the association between the monthly rate at which nurses take part in the well-being program and nurse turnover. The goal of the hypothetical healthcare scenario is to explore whether changes in the independent variable (participation rate) can help explain variations in the dependent variable (attrition rate). This relationship is expressed in an equation of a straight line, y = -0.0849x + 5.5896. Furthermore, the negative sign in the table's regression equation reflects an intuitive expectation that a higher level of participation in the well-being program should mean a lower rate of nurse turnover. The R-value of 0.554 adds support to the justification, indicating that more than half of the variance between nurse attrition and participation rates in health programs can be explained by variations in wellness program participation rates. Such a statistical method, which is based on the principles of linear regression analysis, consequently constitutes a good measure for both quantifying and interpreting this apparent correlation in light of nurse well-being and attrition (Breheny & Burchett, 2017).

Null Hypothesis

The null hypothesis states that there is no significant relationship between the monthly rate of nurse participation and the nurses 'attrition rate. From a statistical point of view, it takes the slope of the regression line to be zero so that changes in nurse participation have no impact on nursing turnover.

Interpretation of Results

Goodness of Fit

The R^2 value of 0.554 is an important indicator in measuring the goodness of fit. This value means that about 50 % of the variation in nurse turnover can be ascribed to changes in monthly participation rates. As the value of R^2 becomes closer to 1.0, it can be inferred that a model is capturing more and more nurse attrition variance, implying that the solution to the linear regression equation fits relatively well as an approximation to what goes on out there in reality.

Significance of Independent Variable

The negative coefficient in the linear regression equation, y = - 0.0849x + 5.5896, emphasizes that the independent variable (monthly rate of nurse participation) plays an important role. However, the negative slope shows that as nurse participation increases, the attrition of nurses goes down. The statistical significance of this coefficient, as demonstrated by the outcome of the analysis, adds weight to this relationship and reinforces a figure on how participation affects attrition. Therefore, nurse participation is an effective indicator of nursing turnover. As such, the formula y = -0.0849x + 5.5896 can be used to determine the predicted attrition rate for any particular level of nurse participation. Its function is to give a clear and understandable formulation of the connection discovered through regression analysis (Breheny & Burchett, 2017).

Limitation of Research

The basic assumption of this research is the linear relationship between nurse participation and attrition. However, the development of these real-world phenomena may require very complex nonlinear factors, which this linear regression model cannot always capture. Although participation rates are important indicators of potential attrition, external variables like the specificity of individual nurses or systemic changes in policy may have independent effects on nurses (Breheny & Burchett, 2017).

Recommended Course of Action

The recommended first step is to strengthen and promote the welfare plan. This means more targeted marketing to create greater awareness and attract participation, the addition of a wider range of activities, or regulating monitoring of certain elements based on continued analysis. The aim is to create a work atmosphere that puts the needs of employees first, which will help reduce attrition rates among nurses (Buchan et al., 2019). The organization should also look further into qualitative information from the nurses that will complement the quantitative results and refine the well-being program.

References

Alluhidan, M., Tashkandi, N., Alblowi, F., Omer, T., Alghaith, T., Alghodaier, H., ... & Alghamdi, M. G. (2020). Challenges and policy opportunities in nursing in Saudi Arabia.  Human Resources for Health,  18(1), 1-10.

Breheny, P., & Burchett, W. (2017). Visualization of regression models using visreg.  R J.,  9(2), 56.

Buchan, J., Charlesworth, A., Gershlick, B., & Seccombe, I. (2019). A critical moment: NHS staffing trends, retention and attrition.  London: Health Foundation.

Dyrbye, L. N., Shanafelt, T. D., Sinsky, C. A., Cipriano, P. F., Bhatt, J., Ommaya, A., ... & Meyers, D. (2017). Burnout among health care professionals: a call to explore and address this underrecognized threat to safe, high-quality care.  NAM perspectives.

Morgantini, L. A., Naha, U., Wang, H., Francavilla, S., Acar, Ö., Flores, J. M., ... & Weine, S. M. (2020). Factors contributing to healthcare professional burnout during the COVID-19 pandemic: A rapid turnaround global survey.  PloS one,  15(9), e0238217.

Wellness Program Participation and Nurse Attrition

Nurse Attrition Rate (%)

y = -0.0849x + 5.5896 R² = 0.554

10.1 10.5 9 9.6 14.2 16.3 16.899999999999999 16.8 20.2 18.5 19.3 14.2 23.1 22.7 24.1 24 25.3 24.8 28.5 30.3 28.9 30.2 32 29.7 34.1 24.3 36.4 38.5 38.4 38 40.1 39.5 42.1 42.3 44 42.9 5 4 6.5 3.7 4.7 3.7 4.5 3.8 4.5 3.6 4.3 6 4.3 1.2 4.0999999999999996 3 3.9 2.5 3.5 2.6 3.5 2.1 2.9 2.2000000000000002 3.1 3.1 3.2 1.8 3.5 2.8 2.5 1.5 2.2999999999999998 1.2 2.1 2.5

Program Participation Rate

Nurse Attrition Rate