This is the same sensor used by others who have reported high NO2 levels correlated with their gas stove burning, though, so it's got to be measuring something relevant.

Update: I read a tweet thread by the author of the original post, and they also used an uHoo.

So if you find the "uHoo doesn't measure NO2 anyway" argument compelling, then really we're all just talking about nothing.

False positive and false negative rates can be different. Trusting that when it says bad, it means bad can be consistent with doubting when it says good

Also, this is not a measurement that yields symmetric action, since it’s harmful in only one direction. Your actions based on the same level of accuracy are likely to be different.

If a device can tell you something is maybe poisonous, a positive result is going to lead to very different behaviour than a negative one, even if they’re equally likely to be accurate. This is especially true when your priors (ie research with accurate devices and knowledge of combustion) lead you to expect (prior to measurement) that it will indeed be poisonous.

So how do I measure NO2 in the home and not something that “correlates”?

The AQMD website has tested devices, and any they found accurate is probably a good place to start.

My limited research suggests the most affordable and reliable gaseous measurements like NO2 want a metal oxide sensor, which you don’t see on consumer grade equipment but is available affordably from commercial sources. It’s more hassle though so I gave up on measuring NO2 for now. Particulates seem to be readily measured with suitable accuracy by consumer grade equipment.

Yep.

Sure, but it’s not measuring NO2, just things that sometimes correlate with the presence of NO2 in some environment. So, maybe it’s sometimes rightish in a general ball park sense, but often it won’t even be that as these correlations are necessarily based on lots of assumptions that often don’t hold. And this is all ignoring interdevice variability which is often very high on this consumer equipment if the tests are to be believed.