Tag Archives: confidence intervals

The US county with the longest life expectancy – and a big error margin

Posted on by

A recent ranking of US counties by life expectancy at birth now found Aleutians East Borough at the top of the list:

This is one of three counties with a life expectancy of “100+.” Out of these three, it is also the one with the largest error margin. If I am interpreting this correctly, the list compilers are 95% confident that the life expectancy of this county is between 67.9 and 100+.

This is most likely due to the relatively small number of people in the county. This is not uncommon in these rankings: of the top 16 counties in life expectancy, the highest population is over 55,000 and several counties have fewer people than the one ranking #1. When there are fewer cases (residents, for this analysis) to consider, it is harder to be confident in the calculated life expectancy. My guess is that this county had the highest expected life expectancy in the statistical model so even with the large confidence interval it ended up at the top of the list.

With fewer people in a number of these counties, the year-to-year predictions could shift more given conditions. Does this mean the rankings should be disregarded? Not necessarily but the confidence interval does provide insight into how the life spans of a small number of residents can change these rankings.

Chicago traffic bad and, perhaps worse, unpredictable

Posted on by

Having heavy traffic is bad enough but Chicago also has unpredictable traffic, according to a new report.

Residents of the Chicago area are accommodating that increasing uncertainty by setting aside more time each day — just in case — for the commute, new research shows.

For the most important trips, such as going to work, medical appointments, the airport or making a 5:30 p.m. pickup at the child care center to avoid late fees, drivers in northeastern Illinois and northwest Indiana should count on allotting four times as much time as it would take to travel in free-flowing traffic, according to the “Urban Mobility Report” to be released Tuesday by the Texas A&M Transportation Institute. The analysis is based on 2011 data, which are the most recent available.

It is the first time that travel reliability was measured in the 30-year history of the annual report. The researchers created a Planning Time Index geared toward helping commuters reach their destinations on time in more than 95 percent of the trips. A second index, requiring less padding of travel time, would get an employee to work on time four out of five days a week…

The Chicago region ranked No. 7 among very large urban areas and 13th among 498 U.S. cities on a scale of the most unreliable highway travel times. The Washington area was the worst. A driver using the freeway system in the nation’s capital and surrounding suburbs should budget almost three hours to complete a high-priority trip that would take only 30 minutes in light traffic, the study said.

This sounds like an interesting new way to measure traffic. The absolute amount of time spent in traffic is interesting in itself but this study gives us a sort of confidence interval for time spent in traffic. This suggests that traffic is not just an issue of getting stuck but it is the threat of getting stuck that would affect a lot of behavior. Just the threat could lead to a lot more lost time and productivity.

It would also be interesting to look at how often the average driver gives themselves this time cushion. Could traffic be improved if people planned to take more time to get to their destination?