Medicaid Expansion Some Numbers and Association

Several states are reluctant to go for Medicaid expansion. I am not sure whether Medicaid expansion will be beneficial for those who decided not to implement it. The resistance to implement the expansion in the first place shows that they don’t believe that everyone should have a chance  to care. Moreover, it shows that they are using this notion that ” if you can’t pay for it, you don’t even think about it”. The same people think that businesses should thrive under their watch, though it affects negatively the health behaviors of their citizens, that businesses are worth implementing as long as they are profitable. The question, why don’t we make those who influence negatively our citizens health and behavior pay the price.

Imaging Robinson Crusoe in his beautiful island hurting himself, evidently his coconut production will decrease thus his injures will be worse than before.

I conducted a simple Bootstrap regression analysis with 1000 replication, and I used data from CMS and America Health Rank to find the type of association between those states that expanded medicaid and their overall health ranking. although this is very simple analysis, it provides an overview for interested audience to investigate more on this matter and see if Expanding or not expanding Medicaid is within their reach.

An Econometric note:

Please note that when I run the regression analysis including the constant, the coefficient corresponding to medexp becomes negative and statistically highly not significant. however, when I run the model without a constant, the coefficient becomes positive and statistically less significant. in case, I include the constant basically I assume that each state have an initial ranking. Meanwhile, the case I exclude the constant term, I am assuming that or forcing all state not to have any ranking.

correlate Rank MedExp

| Rank MedExp
Rank | 1.0000
MedExp | -0.1953 1.0000

. regress ranks MedExp, noconstant vce(bootstrap, reps(1000))

(running regress on estimation sample)

Bootstrap replications (1000)
—-+— 1 —+— 2 —+— 3 —+— 4 —+— 5

Replications = 1000
Wald chi2(1) = 2.01
Prob > chi2 = 0.1564
R-squared = 0.1234
Adj R-squared = 0.0747
Root MSE = 26.4752

| Observed Bootstrap Normal-based
Rank | Coef. Std. Err. z P>|z| [95% Conf. Interval]
MedExp | .0000881 .0000621 1.42 0.156 -.0000337 .0002098