Hacker News new | past | comments | ask | show | jobs | submit login

I addressed that in my comment. Their numbers are practically identical, but their conclusion is different, because they make a determination on whether a car seat was "seriously misused".

Further, Table 1 says that seat belts had a non-fatal rate of 99.89% and restraint systems had a non-fatal rate of 99.88%.

Hell, they flat-out say that they had to adjust it to get those numbers:

"Table 2 summarizes little difference in the unadjusted risk for death between users of child restraint systems and users of seat belts (RR, 1.03; 95% confidence interval, 0.72-1.46). After adjusting for seating position, vehicle type, model year, driver and passenger ages, and driver survival status, children in child restraint systems had a 21% reduction in risk for death compared with children in seat belts, although this difference was only marginally significant (RR, 0.79; 95% confidence interval, 0.59-1.05). After excluding the cases of serious child restraint system and seat belt misuse from FARS, children in child restraint systems had a 28% reduction in risk for death compared with children in seat belts (RR, 0.72; 95% confidence interval, 0.54-0.97)."

It seems that they are trying to get to that conclusion.




The result still seems compelling to me. If I can reduce the risk of my child being killed in a car accident by 28% (even if the raw numbers are small) I'm going to do it.

I don't want to change the goal posts here, but death isn't the only thing these booster seats protect against. A properly used booster seat reduces the relative risk of non-fatal injury by more than half[1]. That is also extremely compelling to me.

[1]: http://jama.jamanetwork.com/mobile/article.aspx?articleid=19...


I agree. I am not convinced not to use a child seat for children I care about (also it is the law).

However, the parent commenter used that single study (that seems to have an ax to grind with Levitt) as proof against Levitt's claim.

And it does not appear so cut-and-dry to me.


"Further, Table 1 says that seat belts had a non-fatal rate of 99.89% and restraint systems had a non-fatal rate of 99.88%."

Um, no, I'm afraid.

Table 1 describes the characteristics of the data set. 99.89% of the "seat belt" sample were non-fatal accidents and 0.11% were fatal; that and the row immediately above it sum to 100%. A fatal accident is defined as one in which someone died, including a pedestrian.


I am afraid that you are mistaken.

You will note that they say:

"Within FARS, we identified 7813 children aged 2 through 6 years who were vehicle occupants restrained in a child restraint system or a seat belt in a nondrivable passenger car, van, pickup truck, or sport-utility vehicle that was involved in a crash with at least 1 passenger fatality between 1998 and 2003. Of these 7813 children involved in fatal crashes, 1096 children (14%) were killed."

You will then note that in Table 1 for "Overall" the Fatal rate is 1096 (identical to the number of children, the 14% above, that were killed).

You will also note that if you add together the FARS and NASS CDS numbers you will get 9246, which is the total number of children aget 2-6 from both and also the sum of 1096 and 8150 from the "Overall" column on Table 1.

now that I think about it, it doesn't even matter. If the same relative rates are fatal and non-fatal (separately) that still says that they are practically equivalent.

Also, it says so in the paper...




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: