Statistical exercise
Linear Regression Model
Exercise 4 offers two versions: EXCEL (base) and RStudio (BONUS). Submit final results in MS Word.
Track 1 RStudio: If you have chosen to work with RStudio (1 % BONUS), please run the following models and complete the following tables. See Track 2 below for EXCEL
RStudio Track
Model 1. Run a linear model to predict the impact of difference in hospital beds (use the total_hospital_beds) and hospital’s ownership on hospital net benefit. Complete table below.
Model 1a
Hospital Characteristics
Coef.
St. Err
Hospital beds
Ownership
For-Profit
Not-for-profit
Other
N
R-Squared
1. Discuss your finding(s). Do you think having higher number of hospital beds has a positive impact on the hospital net benefit? What about the ownership?
Model 2. Now, estimate the impact of system membership on hospital net benefit. Complete table below.
Model 2
Hospital Characteristics
Coef.
St. Err
Hospital beds
Ownership
For-Profit
Not-for-profit
Other
Membership
System Membership
N
R-Squared
2. Discuss your finding(s) (no more than 2 lines). Is the result significant? Explain.
Model 3. Now, include the Medicare-discharge-ratio and Medicaid-discharge-ratio in your model. Complete table below
Model 3
Hospital Characteristics
Coef.
St. Err
Hospital beds
Ownership
For-Profit
Not-for-profit
Other
Membership
System Membership
Socio-Economic Characteristics
Medicare-discharge-ratio
Medicaid-discharge-ratio
N
R-Squared
3. How do you evaluate the impact of having higher Medicare and Medicaid patients on hospital net benefit?
4. Based on your finding(s), please recommend 3 policies to improve hospital performance. Please make sure to use the final model for your recommendation(s).
Excel Track
Model 1. Run a linear model to predict the impact of difference in hospital beds (use the total_hospital_beds) on hospital net benefit in teaching hospitals. Complete table below.
Coefficient
Standard Error
t Stat
P-values
Lower 95%
Upper 95%
Intercept
Total Hospital Beds
R Square
Model 2. Run a linear model to predict the impact of difference in hospital beds (use the total_hospital_beds) on hospital net benefit in non-teaching hospitals. Complete table below.
Coefficient
Standard Error
t Stat
P-values
Lower 95%
Upper 95%
Intercept
Total Hospital Beds
R Square
1. Use the results from model 1 and model 2 and compare the results between teaching and non-teaching hospitals.
Model 3. Now, include the Medicare-discharge-ratio and Medicaid-discharge-ratio in the first model: Teaching Hospitals. Complete table below.
Coefficient
Standard Error
t Stat
P-values
Lower 95%
Upper 95%
Intercept
Total Hospital Beds
Medicare-Discharge-Ratio
Medicaid-Discharge-Ratio
R Square
Model 4. Now, include the Medicare-discharge-ratio and Medicaid-discharge-ratio in the second model: Non-Teaching Hospitals. Complete table below.
Coefficient
Standard Error
t Stat
P-values
Lower 95%
Upper 95%
Intercept
Total Hospital Beds
Medicare-Discharge-Ratio
Medicaid-Discharge-Ratio
R Square
2. How do you evaluate the impact of having higher Medicare and Medicaid patients on hospital net benefit in teaching hospitals?
3. How do you evaluate the impact of having higher Medicare and Medicaid patients on hospital net benefit in non-teaching hospitals?
4. Based on your finding(s), please recommend 3 policies to improve hospital performance. Please make sure to use the final model for your recommendation(s).
The data is the same of Exercise 1, 2 and 3.
Download codes from here:
E4-codes-dplyr
E4-codes-no-dplyr
