Goto

Collaborating Authors

How do your statistics boss you around?

@machinelearnbot

Other than being fun to play with and fun to illustrate, they serve a lot of important tasks for researchers. They can quickly identify which of 500 comparisons is statistically significant. They can offer data to show whether your brand users comprise 2 distinct groups of people or 7 distinct groups of people. They can offer data to show which price your consumers would refuse to pay. But there are two ways to use statistics.


Immigration Data & Statistics

@machinelearnbot

Since the passage of the Homeland Security Act of 2002, the Office of Immigration Statistics (OIS) has responsibility to carry out two statutory requirements: 1) to collect and disseminate to Congress and the public data and information useful in evaluating the social, economic, environmental, and demographic impact of immigration laws; and 2) to establish standards of reliability and validity for immigration statistics collected by the Department's operational Components.


Wrong traffic statistics reported by Bit.ly

@machinelearnbot

Do you know what causes Bit.ly (a URL shorterner and traffic reporting tool) to report traffic statistics (on a specific URL) that are 3-4 times higher than they really are? This is happening in very specific circumstances. I've noticed the error when we send a newsletter from our Ning platform (using the Ning email submission tool). It does not happen when using other email blasts (for instance LinkedIn or VerticalResponse), and it does not happen with bit.ly links accessible from a web page (as opposed to a link embedded into an email).


Amazon.com: The Book of R: A First Course in Programming and Statistics (9781593276515): Tilman M. Davies: Books

#artificialintelligence

I almost never write Amazon reviews, but feel compelled to in the case of this gem of a textbook. Excel), but NO programming background -took statistics in high school, barely passed calculus in college -was inspired to learn R after seeing a colleague use it for data analysis -have been disappointed by R texts that I've encountered thus far, finding them either too advanced or poorly organized/written Why I am giving this book 5 stars: -it is structured very logically, starting with the basics of the language before moving onto programming, statistics, and more advanced concepts -it is accessible to a wide audience, yet goes into the necessary level of detail -it is well written, in an easy, clear voice -an appropriate balance of text vs code examples and graphics -it has effective exercises at logical points to ensure the reader not only understands, but can execute the concepts learned -it is aesthetically very nice -- the spine doesn't crack, the book doesn't warp over time, the font and text size are very readable As a sidenote, I ordered R for Dummies as well. I didn't give it an especially thorough glance, but quickly flipped through it and decided to return it because I knew on first glance that The Book of R was far superior.


Sketchy summary statistics

#artificialintelligence

Ben Orlin of Math With Bad Drawings explains the pitfalls of using summary statistics -- mean, median, and mode -- to make decisions in life. Aggregates like these are meant as wideout overviews. Learn to visualize your data. So far we've seen when you will die and how other people tend to die. Now let's put the two together to see how and when you will die, given your sex, race, and age.