When faced with lots of variables and likely interaction terms, is linear regression usable? In the comments, I get educated that yes, it can be done. Thanks to Nigel Goodwin. I will still tell my students to try some inherently nonlinear methods, though.
Source: Logistic Regression Vs Decision Trees Vs SVM: Part I
With the new A9 and A9X chips in its iPhones and iPads, Apple has mobile chips that are better than Intel’s. In fact Apple’s chip business is a very impressive technology story. I don’t have time to put together a full analysis, but I have collected some recent articles. 
Many sources are suggesting that Apple’s current chip generation (A9 and A9X) is better than Intel’s in low-power (mobile) performance. I guess it’s not news that Intel is behind Qualcomm in mobile, but I still find it surprising that Apple’s own chips are apparently better than X86 for Macintosh low-end laptops!
Some recent analysis paid for by the Department of Energy claims that the benefits of weatherizing homes are many times larger than the cost. In contrast, a careful Randomized Controlled Trial of a specific program comes to the opposite conclusion.
Recently, we conducted a first-of-its-kind, randomized controlled trial of the nation’s largest residential energy efficiency program, the federal Weatherization Assistance Program (WAP). The trial consisted of a sample of more than 30,000 WAP-eligible households in the state of Michigan. Our research revealed that investments in residential energy efficiency upgrades among weatherized households in our study cost about double what these households will save on their energy bills (efficiency retrofits cost about $4,600 per household and estimated energy savings are only $2,400). You can read more about our results here.
Sadly, my reading is with the Berkeley authors. The DOE studies seem to be grabbing all kinds of hypothetical benefits out of thin air. This does not mean that all such investments are under water, just that the average investment is not worth doing.
There are certainly ways to tighten/redesign any conservation program to make it more cost effective. But this requires an attitude of continuous investigation and improvement – not something that government agencies are good at. Once an agency has gotten money and gone ahead with a project, its incentives are to tout its benefits much more than to improve on the original design. This comes down to Congressional (and press) oversight. Any signal that the past project might have been less than ideal will be leapt on by political opponents. In my view, this set of incentives is one reason that so many government programs are weak, and furthermore do not improve over time.
Art and Science in Technology - Roger Bohn's Blog 