Forgot your password?
typodupeerror
Math

Big Talk About Small Samples 243

Posted by samzenpus
from the read-all-about-it dept.
Bennett Haselton writes: My last article garnered some objections from readers saying that the sample sizes were too small to draw meaningful conclusions. (36 out of 47 survey-takers, or 77%, said that a picture of a black woman breast-feeding was inappropriate; while in a different group, 38 out of 54 survey-takers, or 70%, said that a picture of a white woman breast-feeding was inappropriate in the same context.) My conclusion was that, even on the basis of a relatively small sample, the evidence was strongly against a "huge" gap in the rates at which the surveyed population would consider the two pictures to be inappropriate. I stand by that, but it's worth presenting the math to support that conclusion, because I think the surveys are valuable tools when you understand what you can and cannot demonstrate with a small sample. (Basically, a small sample can present only weak evidence as to what the population average is, but you can confidently demonstrate what it is not.) Keep reading to see what Bennett has to say.

Comment: Re:Wonder if their time hasn't already passed... (Score 3, Interesting) 167

by dmomo (#48213219) Attached to: Ello Formally Promises To Remain Ad-Free, Raises $5.5M

The site just wasn't ready for mass adoption. There's a great idea behind it, but as of last week, it was just so damn unusable. I'm tempted to think that their marketing blitz was premature. But perhaps the goal wasn't to show off the site so much as to get just enough attention to turn the heads of investors. If so, maybe it worked. They've gained some cash flow while also validating the idea that there IS a desire for what they are building.

Now, they can use some of this funding to actually make the UI usable and add in those missing features. Maybe when their next media campaign comes around, there will be a site worth applauding. We can only hope.

Good for them. I'll keep my account active and hope it turns into a site

Comment: I live in Worcester and would welcome competition. (Score 5, Interesting) 232

by dmomo (#48156103) Attached to: Worcester Mass. City Council Votes To Keep Comcast From Entering the Area

I live in Worcester, and have been a Charter customer for five years. When their Internet connection is working it's great. It's fast, and I have no complaint.

This isn't a "bash Charter" thread, so I won't go into the details, but lets just say that the service drops much more than I can sometimes stand. When it does that , there's no telling when it will come back. The reliability of my Internet connection and their poor customer service would have prompted me to drop them by now if I could. I had Comcast before.. they've got their pros and cons too, but I wish I could at least have a choice to leave this monopoly.

Now, this might border on gossip, but I did get chatty with a Charter service tech who visited my home. I was venting to him and cursing the monopoly Charter has in the area. He told me that Charter had a deal with the City where all schools would get free service in exchange for an exclusivity deal. So no Comcast, no FIOS. I cannot verify this, but it is an interesting anecdote given what's going on.

Comment: Re:It's not your phone (Score 2) 610

by dmomo (#47909007) Attached to: Apple Outrages Users By Automatically Installing U2's Album On Their Devices

Come on. You're kidding yourself. Don't tell me that Apple did it this way because it was easier on their developers. iTunes has countless ways of selling, promoting, and giving away music. This company certainly has the resources to make iTunes behave exactly how they want it to. This was a very deliberate move aimed at putting this album on your device.

Comment: Re:Why does this work (Score 1) 194

by dmomo (#47507975) Attached to: A New Form of Online Tracking: Canvas Fingerprinting

"I'm more curious about why "different computer draws the image slightly differently"
Accessibility. This is important. The HTML5 canvas is about more than just images. It's live elements that can contain text content and other display elements. HTML should render in a sensible manner on any device as dictated by the owner of the machine. All owners are not created equal. All renderings should not be equal.

"Browsers are supposed to provide abstraction from the machine" even if that's true, there's also a matter of canvas dimensions, which can vary depending on your resolution and browser's width. Those are not attributes of the machine, but of the display environment for the page. HTML is designed to adapt to different dimensions, font settings.

If the code and the comments disagree, then both are probably wrong. -- Norm Schryer

Working...