Exercise 5
For this week’s exercise, we need to try a few logit (logistic regression) models (see this link for more information:). Use same dataset from week 1 exercise.
If you have chosen to work with Excel, please run below three models and complete the following tables. Use same dataset from week 1’s exercise.
Medicare and Medicaid Discharge Ratios: Medicare Discharges ÷ Total Hospital Discharges; Medicaid Discharges ÷ Total Hospital Discharges
Model 1: Run a regression model using being a member of a network and find out its impact on hospital cost.
Coef. ST. ERR Wald Stat P-values Lower 95% Upper 95%
Hospital cost
N
R Square
(Limit all results to 2 decimal places max)
Model 2: Run a regression model using being a member of a network and find out its impact on hospital cost and hospital revenue.
Coef. ST. ERR Wald Stat P-values Lower 95% Upper 95%
Hospital cost
Hospital Revenue
N
R Square
(Limit all results to 2 decimal places max)
Model 3: Run a regression model using being a member of a network and find out its impact on Medicare and Medicaid discharge ratios.
Coef. ST. ERR Wald Stat P-values Lower 95% Upper 95%
Hospital cost
Hospital Revenue
Medicare discharge ratio
Medicaid discharge ratio
N
R Square
(Limit all results to 2 decimal places max)
Based on your findings, recommend 3 policies and discuss the impact of being a member of a network on hospital cost, hospital revenue as well as Medicare and Medicaid discharge ratios. Do you recommend keeping membership for a hospital? Why or why not?