Technical Appendix: The Model for Health Insurance Coverage

Dependent variable: Uninsured Adults 19-64 without Dependents
                    2009-2010 data for 49 states except MA

All variables are proportions and measured as "logits."
                coefficient   std. error   t-ratio   p-value 
  -----------------------------------------------------------
  const           1.22691     0.347772      3.528    0.0010   ***
  lgt_U3          0.728698    0.0918831     7.931    5.94e-10 ***
  lgt_Extr+Cons   0.280012    0.0747943     3.744    0.0005   ***
  lgt_UnPriv     −0.164442    0.0460793    −3.569    0.0009   ***
  lgt_NotEng      0.119194    0.0296539     4.020    0.0002   ***
  lgt_McCain      0.217339    0.0810080     2.683    0.0103   **

S.E. of regression   0.141875   Adjusted R-squared   0.726246

The predictors include:

U(3) – the state’s U(3) unemployment rate;
Extr+Cons – the proportion of the state’s workforce in mining, logging, and construction;
UnPriv – the proportion of the state’s private workforce that is unionized;
NotEng – the proportion of the state’s citizens who have no English language skills;
McCain – the proportion of the state’s 2008 Presidential vote won by Republican John McCain

Sources:
U(3) – Bureau of Labor Statistics, Alternative Measures of Labor Underutilization for States, 2010;
Extr+Cons – Bureau of the Census, Table 631. Employees in Nonfarm Establishments–States: 2010
UnPriv – Barry Hirsch and David Macpherson, Union Membership and Coverage Database from the CPS
NotEng – Census Bureau, Table 4A.  Population 5 Years and Over Speaking a Language Other Than English at Home by English-Speaking Ability by State: 2007; percent responding “not at all” to speaking ability;
McCain – David Leap, Atlas of U.S. Presidential Elections, Results for 2008

Health Insurance Coverage in the American States – I

With this post I begin a new series of reports based on my analysis of state-level data on health insurance coverage.  I began this research in the summer after reading this article on a blog over at the The Atlantic but put it aside during the furore of the election campaign. In that article Richard Florida examines a map of data on insurance coverage from Gallup and finds an “uninsured belt” running through “much of the deep south and the Sunbelt.” In contrast, states in the Northeast and the industrial Midwest have larger proportions of their populations who are covered by health insurance.

Mr. Florida then goes on to report positive correlations between the proportion of a state’s population without health insurance and political attitudes like the proportion of a state’s residents that identify themselves as conservatives in polling or that voted for McCain in the 2008 election. Patterns like these make it tempting to infer that health insurance coverage reflects a pattern of Republican “stinginess” and Democratic “generosity.” The truth, as it turns out, is much more complicated.

What is left out of these “big picture” analyses of ties between Republican opinion and healthcare coverage is any explanation of the mechanisms by which popular opinions are converted into actual policy outcomes like rates of insurance coverage. The most obvious hypothesis is that states with strong Republican leanings elect Republican legislatures and governors that implement policies leading to lower rates of coverage in the states they govern. While that might be the most obvious mechanism, it is simply untrue. There is no evidence that states where the Republicans controlled the levers of government have systematically lower levels of insurance coverage.

For this research I relied on the extensive set of state-level figures on insurance coverage based on Census data as maintained by the Kaiser Family Foundation.  I will start with the coverage rates based on the state’s total population.  Later I will narrow the focus to one specific group, adults 19-64 without dependents, who constitute the most difficult group to insure.

To test this hypothesis, I categorized states based on the number of years between 1990 and 2010 one party or the other controlled both houses of the state legislature and the governor’s office.  A state was scored +1 for each year both houses and the governorship were held by the Republicans; years where the Democrats were in control were scored as -1.  Any years of split control were coded zero.  I then averaged these figures over the two decades to construct an index of partisan control and computed the average percent of the population without insurance for five categories.  Here are the results:

As we might expect, states with consistent Republican control also had higher rates of support for John McCain in 2008.  However there is simply no relationship between partisan control of state governments and the percent of the population without health insurance.  What does influence health insurance coverage rates will be the subject of the postings to follow.