MHA FPX 5017 Assessment 4 Executive Summary Presenting Statistical Results for Decision Making
Context
Assessment 4: Presenting Statistical Results for Decision Making
Student Name
MHA-FPX5017: Data Only Health Care Decisions
Capella University
Prof Name
Month Date, Year
Presenting Statistical Results for Decision Making
Hi my name is [Your Name] and today I will present the statistical results for Villa Health scenario of HACs (Hospital Acquired Conditions). CMS, on yearly basis, analyzes total HACs score to evaluate the overall productivity and performance of hospitals throughout the US (CMS.gov, 2021). Hospitals that have a score greater than the 75th percentile of total HACs score receives payment deduction of one percent on total Medicare payments paid to that hospital (Moehring et al., 2019). I will be summarizing the different statistical results that include descriptive analysis, histograms, linear and multiple linear regression as well as I will be giving recommendations based on those analysis. The given scenario is of St. Anthony Medical Center which is a big hospital in Minneapolis.
Objectives of the Presentation
The objective of the presentation is to look at the statistical variables and data which could impact the overall HACs score of St. Anthony Medical Center. The variables/ predictors that are given in the Villa Health Scenario are as follows
- Nursing staff levels
- RN Staffing percentage as compared to LPN and CAN
- Average LOS (Length of Stay)
Types of Data Analysis
Descriptive Statistics or Statistical analysis are used to data summarization. It includes mean, mode, median, variance, standard deviation and min & max variables (Frey, 2018). The correlation analysis is being used to identify and analyse the predicted pattern of given datasets. The corelation can be both negative and positive and is denoted by r which is a real number and has a value in between 1 and -1. Value of r shows the strength of the corelation based on a formula. Multilinear regression assessment allows for the adjustment (properly accounted for) of conceivably confounding factors in the analysis (Hayes, 2019). For the purpose of analyzing the regression statistics, we have to know the value of R square. The value can range from 0 to 1. This value shows the goodness of fit of the given data.
Analysis of Descriptive Statistics
In the given scenario, the dataset has a mean of 117.17, 3.94, 59.94 and 6.68 for HACs rate, nursing HPPD, mean skills mix percentage and average LOS respectively. The lower ranges are 0.98 for both HPPDs and staffing levels while average LOS has a greater variance of 1.83. HACs rate has an overall variance of 23.95. These statistical results are providing a clear picture of data attribution but further statistical techniques are needed to fully understand that how the above-mentioned factors are interlinked with each other and effecting HACs rate.
Analysis of Correlation and Regression
In the given dataset, there are both positive and negative correlations but in low strength among HACs rate, average LOS and nurses’ skill mix percentages. There is a high negative correlation between HACs rate and HPPD. There is a strong correlation which predicts that nursing staff rates in impacting negatively on HACs rate. One point to keep in mind is that just because datasets correlate it doesn’t necessarily mean that one thing is actually impacting other. There can be false positives and false negatives.
Analysis of Regression
In our data set, in 1st regression, the R value is 0.65 that means there is a 65% variance in the measured factors predictability. HPPD has a p value of 2.1 and skill mix has a p value of 0.25. Both values are measured by α value of 0.05. The HACs rate equation is as follows:
Y= 10.8.8 + 4.17 * (HPPD) + 0.42* (Skill mix percentage)
In 2nd regression, average LOS is measured against HACs rate. The R value is 0.18 which means that the measured factors have a predictability of 18%. Individual coefficient of HACs rate has p value of 2.6 which is greater than α value of 0.05 which means it is insignificant. Average LOS rate will increase by 11.5% as the HACs rate is increased by 1.
Recommendation
It is recommended that HACs reduced medical centre efficacy, heading up existing medical clinic costs of $2,600 for every inpatient per day, despite not withstanding and making insight risks. Assuming that Capacity Balance wasn’t a significant component influencing HAC rates, improving RN as well as LPN staff could be a successful method for lowering HAC levels. Since the average price of an RN is $85,000 and the price of an LPN is $52,000 per year, rising LPN job vacancies will elevate HAC rates at a lower cost. Increasing staff numbers at LPN is also critical recommendation to the Board. However, not all types of problems are as amenable to advancements in staff nurses. Follow up research on how to remove various types of HACs, overall, those with a critical threat is yet to be understand.
References
Frey, B. (2018). The SAGE Encyclopedia of educational research, measurement, and evaluation (Vols. 1-4). Thousand Oaks, CA: SAGE Publications, Inc. doi: 10.4135/9781506326139
Hayes, A. (2022). Descriptive Statistics. Investopedia. http://www.investopedia.com/terms/d/descriptive_statistics.asp
Moehring, R. W., Staheli, R., Miller, B. A., Chen, L. F., Sexton, D. J., & Anderson, D. J. (2019). Central linear associated infections as defined by the Centers for Medicare and Medicaid Services’ Hospital-acquired condition versus standard infection control surveillance: why hospital compare seems conflicted. Infection Control and Hospital Epidemiology, 34 (3), 238–244. http://doi.org/10.1086/669527