Estimates indicate that the 2007 through 2009 three-year average of uninsured children in North Dakota is 7.2 percent (approximately 11,000), which is roughly equivalent to one out of every 14 children. Nationally, 10.3 percent were without health insurance coverage during that period.

This month’s “Economic Brief,” a monthly publication from the North Dakota State Data Center at North Dakota State University, focuses on those children ages 0 to 17 without health insurance in North Dakota. The Current Population Survey’s (CPS) Annual Social and Economic Supplement (ASEC), a joint project between the U.S. Bureau of Labor Statistics and the U.S. Census Bureau, provides annual estimates of the number of people with and without health insurance by selected characteristics.

The CPS ASEC is designed to collect statistically reliable estimates primarily at the national level.

State estimates are less reliable due to the relatively small sample sizes. This can cause state estimates to fluctuate widely from year to year, so the Census Bureau recommends using three-year averages to compare estimates across states and two-year averages to evaluate changes in state estimates through time.

Comparisons of all states using three-year average uninsured rates for 2007 through 2009 show that Texas had the highest proportion of uninsured children in the nation at 18.6 percent, while Massachusetts had the lowest at 3.1 percent.

When examining the two-year averages between 2007 through 2008 and 2008 through 2009 for North Dakota, it appears that the proportion of uninsured children decreased by a percentage point. However, because of the small sample size, this amount of change is not statistically significant. This means that the difference in the two periods may be an artifact of the sample rather than a true representation of change.

“Sampling error can be a difficult concept, and it can be frustrating when you are trying to evaluate change through time,” says Richard Rathge, State Data Center director. “However, it is important to make sure we correctly interpret the data, especially when evaluating issues such as our children’s health and well-being. Thus, we need to pay attention to sampling error to avoid drawing mistaken conclusions.”

Only three states had a statistically significant change in the proportion of uninsured children. Texas showed a decrease of 2.5 percent in the proportion of uninsured youth, while Illinois had an increase of 1.3 percent and Indiana an increase of 1.7 percent.

NDSU Agriculture Communication