The Affordable Care Act (ACA) of 2010 (aka "Obamacare") seeks to provide health-insurance coverage to an estimated 30 million Americans who were uninsured prior to the law's enactment. The two primary methods for doing so, both of which went into effect on October 1 of this year, are expanding eligibility for Medicaid, a long-existing government program for low-income individuals, and creating online marketplaces (or "exchanges") for people above the Medicaid income threshold to purchase private insurance (with federal subsidies available according to income level).
As I wrote on one of my other blogs back in August:
Starting next January [of 2014], individuals with income up to 133 percent of the poverty level will be eligible for Medicaid. The pre-ACA thresholds for Medicaid differ by state and by participant category (e.g., pregnant women, children, parents), but are sometimes as low as 50% of the poverty line.
As readers who have been following the Obamacare saga are no doubt aware, the U.S. Supreme Court ruled in 2012 that states could more readily opt out of the Medicaid expansion than had been intended by the ACA. Many states have indeed opted out, with governors' and legislatures' decisions heavily following party lines (here and here). Democrats have accepted the funding to expand their states' Medicaid eligibility and Republicans (largely) have not.
What struck me in reading about states' decisions on whether or not to accept the Medicaid expansion was the set of reasons cited by opponents for declining participation. Conservative arguments pertaining to an expanded federal-government role in health care and distaste in many states for increased spending on social programs (even though the federal government would largely cover the costs to states of expanding Medicaid) did not surprise me. What did surprise me was the claim that Medicaid is actually harmful to its participants and that people would be better off uninsured than with Medicaid.
Indeed, there are several published studies (many of which are compiled here) appearing to show Medicaid patients faring worse than their uninsured counterparts on health outcomes such as mortality, heart attacks, and timely diagnoses of serious illnesses. Perhaps the most widely publicized and discussed is a 2010 investigation (often referred to as the "University of Virginia study") by LaPar and colleagues entitled "Primary Payer Status Affects Mortality for Major Surgical Operations" (full-text).
In that article, which is based on a very large national data set containing statistics on surgical procedures such as hip replacement and coronary bypass, one finds that whereas uninsured patients had 74% greater odds of suffering in-hospital mortality than their privately insured counterparts, Medicaid patients had 97% greater odds of dying in the hospital than the private-insurance group (Table 6). This is, of course, a correlational or observational research design, linking the type of insurance a patient happened to have with his or her quality of surgical recovery. And with such a research design, patients will differ in many other ways than just their type of insurance coverage. Short of randomly assigning people to type of insurance (more on that later), we are always left with some degree of ambiguity in determining cause and effect.
In the Virginia surgical study, for example, the uninsured appeared actually to be quite wealthy, with roughly 60% in the two highest income categories (based on median incomes within the ZIP codes in which people live): 31.1% in the $45,000-or-greater category and 27.8% within $35,000-44,999 (Table 2). In contrast, only a combined 31% of Medicaid patients lived in the two highest-income sets of ZIP codes, with Medicaid patients clustered mainly (41.3%) in the lowest quartile (less than $25,000). The statistical analysis controlled for patient income, but to the extent the income measure did not capture all facets of patients' personal socioeconomic statuses, income may not have been as potent a control variable as possible (the authors noted that education and nutrition were among variables not included).
Interestingly, Avik Roy, a prominent Medicaid critic, acknowledges that unmeasured aspects associated with income may have played a role in the outcome of the Virginia study:
Another key element to consider is that many of the uninsured are not poor... These individuals are wealthy and/or healthy enough that they have decided to forego insurance. Though the Virginia study corrects for income status and other social factors, the fact that these patients are more capable of paying directly for their own care, at the prevailing rate, means that physicians are more willing to see them.
Another reason to be cautious about making a causal conclusion from the Virginia study that Medicaid is actively harmful to its subscribers is the lack of a well-established mechanism leading from Medicaid to poor health. As another Obamacare critic, Glenn Harlan Reynolds, acknowledges in a USA Today column, "Why Medicaid recipients do worse isn't entirely clear..." (Reynolds does suggest a few possible mechanisms, such as, "Uninsured patients probably go straight to the Emergency Room or to a free clinic, while Medicaid recipients may waste precious days, weeks, or months trying to navigate the bureaucracy." This particular conjecture turns out not to be supported, as Medicaid patients are especially likely to use the ER.)
Avik Roy, in his article cited above, also suggests potential mechanisms:
...the answer almost certainly begins with access to care. Medicaid’s extreme underpayment of doctors and hospitals leads fewer and fewer health-care providers to offer their services to Medicaid beneficiaries.
However, the evidence Roy states for this proposition pertains to both Medicaid patients and the uninsured.
Into the debate charges Austin Frakt, part of an ensemble of bloggers at the The Incidental Economist, whose training (collectively) includes medicine, social sciences, and statistics. Frakt advocates the use of a statistical technique called instrumental variables (IV) to deal with the correlational nature of most Medicaid-related studies and the inevitable omission of potentially relevant control variables and, in fact, he wrote a whole series of postings on Medicaid and instrumental variables. In one posting, Frakt writes:
There are observational studies that purport... that Medicaid coverage is worse or no better than being uninsured. One cannot draw such conclusions from such studies if they do not control for the unobservable factors that drive Medicaid enrollment. Causal inference requires appropriate techniques. Even a regression with lots of controls, even propensity score analysis, is insufficient in this area of study.
In another posting, Frakt writes:
Avik [Roy] dismisses IV as a “fudge factor,” casually and erroneously discrediting a vast amount of mainstream work by economists and several entire sub-disciplines. Since IV is a generalization of the concepts that underlie randomized controlled trials (differing in degree, but not in spirit, from purposeful randomization), and can be used to rehabilitate a trial with contaminated groups — a not infrequent occurrence – it is unwise to trivialize IV and what it can do.
According to Will Shadish and Tom Cook, research methodologists who write mainly in the areas of psychology, sociology, and program evaluation, "An instrumental variable is related to the treatment but not to the outcome except through its relationship on the treatment" (2009, p. 613). As suggested in some of Frakt's postings, for example, variation in states' Medicaid eligibility thresholds presumably would affect Medicaid enrollment, but would affect health only through Medicaid subscription. In a particularly useful posting, Frakt walks readers through a study of insurance and HIV treatment by Goldman et al., which used instrumental variables. [Here's another good explanation of instrumental variables, by David Kenny, which I forgot to include in my original posting.]
Frakt summarizes his Medicaid-Instrumental Variable series with this conclusion:
...there is no credible evidence that Medicaid results in worse or equivalent health outcomes as being uninsured. That is Medicaid improves health. It certainly doesn’t improve health as much as private insurance, but the credible evidence to date–that using sound techniques that can control for the self-selection into the program–strongly suggests Medicaid is better for health than no insurance at all.
As hinted above, opportunities for random-assignment experiments of Medicaid effectiveness occasionally do exist. Reference to true experiments would appear to be a good check on the validity of instrumental-variable studies purporting to substitute for randomized studies. Because Oregon's Medicaid program had been over-subscribed, the state used a lottery system to determine which eligible individuals were allowed to enroll in Medicaid and which were not. The random-assignment element replicates a traditional experiment, with the groups who were and were not admitted into Medicaid available for comparison of their health status over the following years. However, even a study that, in principle, is random-assignment can suffer from deficiencies, such as the incomplete participation within conditions in Oregon.
Still, this past May, two-year follow-up results of the Oregon Medicaid experiment were reported. Though the health benefits of being on Medicaid (vs. no insurance) were modest, there were some differences. Being on Medicaid led to: reduced probability of catastrophic health expenses, greater diagnosis of diabetes, and better treatment for depression. Various perspectives on the Oregon study are available here and here, as well as by searching on The Incidental Economist for Oregon Medicaid (the bloggers there wrote a huge number of posts about the study). Also worth noting, briefly and in conclusion, are other quasi-experimental methods that have been used to study the effectiveness of Medicaid: difference-in-difference and regression-discontinuity design.
By now it should be clear that trying to infer causality as to whether Medicaid leaves its holders better off, worse off, or unchanged is complex business. Still, there appears to be some common ground between analysts who, for the most part, interpret the Medicaid studies differently. Ultimately, Roy concludes his above-cited article with the acknowledgement that:
There is, doubtless, a level of poverty at which Medcaid is better than nothing at all. But most people can afford to take on more responsibility for their own care, and indeed would be far better off doing so.
Shadish, W. R., & Cook, T. D. (2009). The renaissance of field experimentation in evaluating interventions. Annual Review of Psychology 60, 607-629.