mariuskempe
mariuskempe on Hacker News
I honestly can't recommend a book for this. The best resource I've found is MathWorld. I've picked up a bunch of very helpful intuitions from it, including:
- Cauchy: the horizontal distance from the origin at which an arrow shot at a random angle from a point below the origin hits the x-axis
- Gamma: how long you have to wait for the nth event in a
Poisson process
I'm sure these must be books that I haven't read.
I'm sorry! I misread your question as 'Would this be a good book for my level?'.
That's a good question and I was asking myself that I after I wrote that comment. I think my objection is more to the 'Bayesian' and less to the 'methods', if that makes sense. That is, I think constructing and updating models using Bayes' theorem can be (as people doing spam-filtering have shown) a good way of making predictions, but that it is the frequentist properties of the models that actually matter (cf. the ubiquity of cross-validation: 'the proof of the pudding is in the eating'), not the fact that they let you maintain a probability distribution over parameters.
Well, no, because I don't know any good reasons for using Bayesian methods (except when prior probability distributions can be found objectively through some previous experiment etc).
http://www.amazon.com/Data-Analysis-Bayesian-Tutorial-Public... is short and reputable on Bayesian statistics. On MCMC specifically, I don't know, but MCMC is really a kind of algorithm that lets you find the answer to a mathematical question (so I think understanding the math is the right thing to start with).
PS. There a second edition of that book, but I've heard that the first edition is better, because the second edition added a different author and expanded the book.
I should like to give a contrarian comment about this, because it is on top of the front page and seems to be being received positively. This book is probably not a good way to learn about statistical inference. It has quite confused explanations of both Bayesian and frequentist approaches. The preface seems to imply that programmers, by virtue of being able to use computers, don't need to take a rigorous mathematical course in Bayesian methods. However the text actually uses mathematical notation throughout, and as far as I could tell it is often not explained. I noticed at least one case where a probability distribution (gamma) was described only through plots i.e. without specifying its pdf or how you could derive the pdf. I think the kind of discourse that this book exemplifies is halfway to cargo cult 'statistics'.
That's an interesting point. In fact, the expectation of the random walk is always the same as its starting value, because, although most of the walks go to 0 like you observed, there are very occasionally walks that drift upward to astronomical values.
As for the usefulness of this kind of walk: the process we're modelling is an evolutionary one, where the rate of change is fixed (in this case within the species) and we'd like to detect 'random' (non-selected) evolutionary paths by comparing simulations to historical data.
Posted by
mariuskempe on Friday March 16, 2012 @07:40PM
from the gist.github.com dept.
Posted by
mariuskempe on Saturday February 25, 2012 @06:30PM
from the google.com dept.
Posted by
mariuskempe on Friday February 24, 2012 @05:05PM
from the yz.mit.edu dept.
I visited the site during the affected time on Mac OS X 10.7, with Safari - I'm worried I might be infected. How can I check?
Does anyone have any examples of Google lobbying against clearer legal documents? I would love to see this.
Yeah, exactly. I've used the mobile apps of both, and Rdio's has 9 confusing icons and requires you to learn a complicated mental model of your music library will work, whereas Spotify just has 'Playlists', 'Search', and 'What's New' - couldn't be simpler.
Could you all send a similar letter for the patent reforms?
Hey. I voted 'use Coffeescript a lot and JS a little'. I like to use the best tools, so to me learning JS was just a step on the way to learning Coffeescript as soon as I had heard about it. It always boggles me when people don't want to use better tools.
In terms of complaints, I'd say the main one is a few things missing from the big page of documentation that's on coffeescript.org - #'s are comments, function calls with multiple arguments need to have the left paren start immediately after the function name, how to pass anonymous functions. Those cost me a few hours taken together starting out.
What info from the census would enable someone to steal an identity? From the looks of it there's only DoB and address in terms of personal info...
That's one of the funniest things I've ever read on HN
Posted by
mariuskempe on Monday May 30, 2011 @12:47PM
from the show-hn dept.
We read HN mostly for the Rate my Startup posts and the announcements of cool new apps. We thought, "wouldn't it be nice if there was one place that announced those, and didn't focus on politics and funding like TechCrunch?" and so we made Apps Only - https://twitter.com/#!/appsonly. Apps Only covers only new apps, with an extreme focus on product.We only tweet something if...
I'm so impressed with that. If I was getting that much criticism (for something so obviously excellent!) I'd be shaking in my boots. :-(
Hahahahahahahahahahahahahahaahahahahahahahahahahahahaha legendary.
Posted by
mariuskempe on Wednesday April 13, 2011 @10:58AM
from the open-science.pen.io dept.
Posted by
mariuskempe on Wednesday March 30, 2011 @07:29PM
from the self-post dept.
Try searching for, say, 'github', and you will find that github's URL is displayed as: "www.https://github.com/" - it happens for any site with https in the URL.It only works sometimes, though - it happens to me when if I search while logged in, but not while logged out. For evidence see this screenshot:...
I look forward. Is there a twitterfeed / alert mailing list?
If you're going to do it anyway, consider using Flattr. I'd pay you.
Edit: and if you do, twitter me at @mariuskempe and I'll start donating.
Very erratic for me. Lovely idea though, very much looking forward to using!
Posted by
mariuskempe on Tuesday March 08, 2011 @12:34PM
from the crunchgear.com dept.