Running head: FINAL PROJECT PART II 1
FINAL PROJECT PART II 7
Final project part II:
Luz Rodriguez
Southern New Hampshire
The statistics shows that over one third of American adults (36%) are obese and more than two thirds (69%) of the remaining population is overweight. The paper tries to relate the relationship between the hospital stay of the patients as associated with the different BMI of the different patients. This tries to depict the time duration that is associated with the hospital stays among the patients. The BMI has a direct impact to the length of hospital stay. Taking the WHAS100 data into consideration, the statistics shows the different factors, which are associated with the different trends and the survival rates with respect to the hospital admission for the acute myocardial infarction. This data was taken from all patients that were admitted for MI in the hospital for the time duration stated (Gerstman et al., 2015).
The collected data was put under a longitudinal model with 9 different variables within 100 different observations. The variables that were put under observation are those that lies between the focus in LOS and the BMI. BMI is the body mass index which be calculated by taking observing the measure and dividing the weights in kilograms and dividing it by the respective heights in meters squared. A longitudinal model was used in generalizing the estimates of the equations and also was used in bringing the analysis and relationship between the BMI and the hospital stay (Hosmer et al. 2016).
Summary statistics for los: Group by: bmi
BMI | n | Mean | Variance | Std. dev. | Std. err. | Median | Range | min | Max | Q1 | Q3 |
10- 15 | 1 | 8 | 8 | 0 | 8 | 8 | 8 | 8 | |||
15- 20 | 6 | 8 | 14 | 3.7416574 | 1.5275252 | 7.5 | 11 | 3 | 14 | 6 | 10 |
20-25 | 29 | 7.1034483 | 10.310345 | 3.2109726 | 0.59626264 | 6 | 13 | 3 | 16 | 5 | 9 |
25-30 | 35 | 7.3428571 | 82.408403 | 9.0779074 | 1.5344464 | 5 | 55 | 1 | 56 | 4 | 7 |
30- 35 | 23 | 5.9565217 | 10.043478 | 3.1691447 | 0.66081235 | 5 | 15 | 3 | 18 | 4 | 7 |
35 to 40 | 6 | 4.6666667 | 3.8666667 | 1.9663842 | 0.80277297 | 4 | 5 | 3 | 8 | 3 | 6 |
On the other hand, the t-test showed two sample T hypothesis test: Hypothesis test results:
Difference | Sample Diff. | Std. Err. | DF | T-Stat | P-value |
μ1 – μ2 | 6.49 | 0.59375453 | 198 | 10.930443 | <0.0001 |
The histogram helps in identifying the gender and the length of stay at the institution. This shows the difference in the groups taking the length of stay and gender as the variables. This shows that women have longer stays in the hospitals. From this analysis, its that the number of women overstaying in the hospitals is more than the number of men who over stay in the hospital (Akinyemiju, 2016, July 18).
References
Gerstman, Burt B. (2015). Basic Biostatistics Statistics for Public Health Practice. Jones & Bartlett Learning. Burlington, MA.
Hosmer, D. W., Lemeshow, S., & May, S. (2016). Applied survival analysis: Regression modeling of time to event data (2nd ed.). New York, NY: John Wiley and Sons Inc.
Akinyemiju, T.-R. N. (2016, July 18). Association between body mass index and in-hospital outcomes. Medicine. Baltimore, Md.: Wolters Kluwer.
IHP 525 Milestone Two Table
Information on data set | |
Which variables are you investigating? | Length of hospital stay based on gender |
What is the type of each variable? | Length of stay is quantitative
Gender is category |
List the descriptive stats you will run on the data. | Distribution, Mean, Medium, Mode, Minimum, Maximum, & Standard Deviation |
What does each calculation tell you about the data? | Distribution describes the shape / how the data trends when graphed
Mean = the average Mode = the value that appears the most Median = The midpoint of the data Minimum = The lowest value observed Maximum = The highest value observed Standard Deviation = the amount of variation present among the data values |
A. Assess the collected data. Use this section to layout the source, parameters, and any limitations of your data. Specifically, you should:
1. Describe the key features of your data set. Be sure to assess how these features affect your analysis.
Summary statistics for los (Length of stay): Group by: gender
gender | n | Mean | Median | Mode | Min | Max | Std. dev. |
0 = Male | 65 | 6.3 | 5 | 5 | 1 | 17 | 3.3406011 |
1 = Female | 35 | 7.8 | 6 | 4 | 3 | 56 | 8.9172668 |
This data set helps in analyzing the observation related from the length of stay in the hospitals and among this patients, the data set shows that 65 are male and the remaining are female. Analyzing the male, their shortest time period was a single day while their longest duration way 17 days. However on the other hand, females took a shorter period of 3 days while the longest time period was 56 days. This shows that females take a longer stay as compared to men with MI.
Analyzing the other parameters, the mean, mode and the median of both male and female that stays in the hospitals and the analysis is as shown in the table above. This would probably give a skewed graph to the right since the mean>median. The standard deviation also shows that the length of stay are closer to the expected average while the case is not the same for the females as in this case it spread out and contains outliers (Lisitsyna et al., 2019).
2. Analyze the limitations of the data set you were provided and how those limitations might affect your findings. Justify your response.
In this case, there are several limitation and this also affects the results differently, this include the fact that the sample size is small, there is no stated reasons why females take longer stays. For this case it’s likely to skew the data. Taking a large sample size may bring up the idea and reasons behind longer stays and if age is a factor in this case. This also does not give a clear picture since the sample size of the male and the female was not the same and the fact that some information regarding the patients is not disclosed which makes it impossible to know if there is any other reason associated with the longer stay and or if environmental condition in the hospital is a factor. All this limitations are likely to impact the results as maybe gender maybe one of the factors that needs to be considered when analyzing hospital stays of MI patients (Sall et al., 2017).
References
Lisitsyna, L. S., & Oreshin, S. A. (2019). Sampling and Analyzing Statistical Data to Predict the Performance of MOOC. In Smart Education and e-Learning 2019 (pp. 77-85). Springer, Singapore.
Sall, J., Stephens, M. L., Lehman, A., & Loring, S. (2017). JMP start statistics: a guide to statistics and data analysis using JMP. Sas Institute.
los 0.0 5.0 10.0 2.0 17.0 33.0 3.0 6.0 1.0
los 0-10 10 to 20 30-40 40-50 50-60 30.0 4.0 0.0 0.0 2.0