This a final project for SI544 - Introduction to Statistics and Data Analysis at UMich. The project aims to analyze hospital patient data to explore how financial class (Medicare, Private Insurance, etc.) influences patient waiting times and revenue generation. The analysis employs multiple regression models and hypothesis testing using R.
- Source: Kaggle - Hospital Patient Data
- Data Description:
- Contains information such as financial class, waiting times, and revenue generation.
- Granularity: daily data and patient-level data.
- Key Columns:
- Financial Class
- Entry Time, Completion Time
- Medication Revenue, Lab Cost
- Patient ID
- Investigate how financial class impacts revenue generation and waiting times.
- Compare patient waiting times and medication revenue between Medicare and Private Insurance.
-
Data Wrangling:
- Processed the data by adding
Waiting Time
(difference between consultation times) andInsurance Type
(Federal or Non-Federal).
- Processed the data by adding
-
Analysis:
- Conducted multiple regression to model the relationship between
Lab Cost
andMedication Revenue
with respect to different financial classes. - Performed hypothesis testing to compare waiting times between Medicare and Private Insurance patients.
- Conducted multiple regression to model the relationship between
- Regression Analysis: Found varying relationships between
Lab Cost
andMedication Revenue
for different financial classes, indicating that revenue generation patterns differ by insurance type. - Hypothesis Testing: Discovered significant differences in waiting times between Medicare and Private Insurance patients, with Medicare patients having longer average wait times.
This analysis reveals that financial class affects both the revenue generated and waiting times for patients, with noticeable differences between Medicare and Private Insurance.
- R and RStudio
- Libraries:
readxl
dplyr
ggplot2
moderndive
skimr
infer
For further questions or collaboration, feel free to contact me at [email protected].
Clone the repository:
git clone https://github.com/your-username/hospital-patient-data-analysis.git