a thoughtful web.
Share good ideas and conversation.   Login or Take a Tour!
MisterMentat's profile
MisterMentat


stats
following: 3
followed tags: 37
followed domains: 0
badges given: 0 of 0
hubskier for: 1640 days

recent comments, posts, and shares:
MisterMentat  ·  1327 days ago  ·  link  ·    ·  parent  ·  post: Best way to brew in aeropress

This may be dumb, but are you using fresh grounds for each cup? I feel like if I'm going to make more than a single for me in the morning I pull out the French press.

MisterMentat  ·  1577 days ago  ·  link  ·    ·  parent  ·  post: Hearthstone? Anybody?

I haven't played in a while, but I'm fairly good at card games. What kind of pointers were you looking for?

MisterMentat  ·  1593 days ago  ·  link  ·    ·  parent  ·  post: What are you working on today?

Some more details would satisfy my interest.

MisterMentat  ·  1597 days ago  ·  link  ·    ·  parent  ·  post: An experimental UI for teaching programming

This looks like it could be emulated well by a two shell windows (or tmux) with a script that runs a unit testing script when files in a folder change on the right and just your standard editor on the left.

Cool idea though, and it'd be great for this to be automatically setup for new programmers!

I honestly try to stay out of witchcraft, but how? Can you tell me anything specific?

In a world filled with tough people and tough questions, one man (and his wife), make the toughest decision of all: What flavor of ice cream should we eat today?

Queue Law & Order Bum Bum Sound

Will they get peach, peanut butter, or cookie dough? Will it be in a cone or a cup? TWO SCOOPS OR ONE! Will it melt before they can make it back to the couch? Watch the story of a young statistician and a speech pathologist unfold as they just sort of live their lives. This summer blockbuster is filled with lots of SNL type comedy, laughing till you cry, and just general goofing around.

Opening 2015, make sure you go see Team Scream: Ice Cream Rules, FroYo Drools

MisterMentat  ·  1614 days ago  ·  link  ·    ·  parent  ·  post: Scientists of hubski, what science do you science?

I'm not quite sure what bioinformatics is exactly, but I did do a bit of work on genetics data during an internship at the CDC. From my point of view, biostatistics is not bioinformatics. Biostatisticians and statistics as a whole are a large field, but there are definitely some people that intersect with the informatics realm. It's definitely not an area everyone works in though. If you're interested in genetics, and looking at biostatistics programs. I highly recommend Columbia's biostatistics PhD program. I interviewed there, and they had a very large focus on developing methodology for analyzing genetic data. I ended up choosing another program because I wasn't particularly interested in that area and I wanted to do a pure statistics PhD. However, it seems like you'd like it quite a bit.

MisterMentat  ·  1615 days ago  ·  link  ·    ·  parent  ·  post: Scientists of hubski, what science do you science?

    It never fails to astound me how many scientists are just completely statistically illiterate.

I know. Sadly, introductory statistics courses are taught without really telling anyone why it's cool or how useful it is. I myself hated the statistics courses I took in high school and in my undergraduate studies. In my opinion I think people should be much more exposed to how statistics can be applied. I don't really think the best approach is teaching people how to look up t and z statistics on a table. You leave with the ability to say, "do a t-test because there are two groups and that's what we did that one time in class." Then they see a p-value that is "significant." I fucking hate that word.

    It's so cool that you're interested in this! What do you think is the best way to improve statistical literacy?

The best way, IMO, is to think of things probabilistically. Understanding probability and probabilistic statements is key to understanding statistics. From a young age we are taught the laws of cause and effect. Especially in science classes, we are taught that if we do A, then B happens always. Otherwise it's not a causal relationship. However, in practice, we deal with much more complicated networks of causal relationships. We use randomness as an abstraction to model these complex relationship because it would be impossible to measure every factor in a causal relationship without infinite time, money, and infinitely precise instruments. This is why we see different magnitudes of effects. We don't, and can't, possibly measure everything that would affect the outcome. We use statistics to (hopefully) determine the most likely and most influential causal factors.

The statements we make are probabilistic though. Each conclusion we make has a chance of being wrong, no matter how careful we are. In fact, we expect about 1 in 20 of the studies performed (with the 0.05 significance level) to make incorrect conclusions. This is why replication is important. If multiple studies come to the same conclusion, we can be reasonably certain that we made the correct decision. A statistical statement in isolation is not always as concrete as it seems.

So I'd recommend above all understanding the probabilistic statements made during hypothesis testing, and the implications that the cutoffs you select have. I'd also recommend being familiar with all of the assumptions that the models you use make. Know why they make them, and know when you've violated the critical ones.

And please, please, please consult with a statistician if you're doing research. Most universities have consulting arms of their departments that are available for collaborative research inside and outside of their university. We would love to work with you! We won't bite. We study this stuff for our whole lives because it's hard. We didn't learn everything about physical chemistry and quantum mechanics in that one class we took in undergrad, and you didn't learn everything about statistics. Let's work together, and hopefully we can avoid some of the pitfalls of our predecessors.

MisterMentat  ·  1615 days ago  ·  link  ·    ·  parent  ·  post: Scientists of hubski, what science do you science?

I just finished my master's in biostatistics and am about to start my PhD in statistics. You may not consider me a scientist, but I'm the guy that makes sure your science is grounded in actually testable hypotheses and that you're drawing the right conclusions based on the observable data that you've decided to collect.

On a pure statistics level, I'm really interested in Bayesian inference, stochastic computer simulations and computational statistics, machine learning (isn't everyone now, this is becoming a bit cliché), and improving the statistical literacy of the general scientific and lay community.

MisterMentat  ·  1615 days ago  ·  link  ·    ·  parent  ·  post: What have you accomplished this week?

Thanks, and thanks for not giving me the usual response! Most people have a reaction somewhere between disgust and pity when I tell them my field. I absolutely love it though. It's creative, mentally taxing, and open-ended like pure mathematics as well as more immediately useful.

MisterMentat  ·  1618 days ago  ·  link  ·    ·  parent  ·  post: How did you learn programming?

I highly suggest Harvard's introductory material. [CS50.tv](www.cs50.tv). It's really very good. I also suggest you try to do the "Hacker edition" of the assignments. Yes, they are much more difficult, but they actually make you think even if you know what you're doing. They also get you a little more in tune with some of the tools and practices that you'll use in your actual projects.

MisterMentat  ·  1618 days ago  ·  link  ·    ·  parent  ·  post: What have you accomplished this week?

How did you get good at this game? I find it pretty hard to land crafts on the Mun without heavy use of the assistance technologies.

MisterMentat  ·  1618 days ago  ·  link  ·    ·  parent  ·  post: What have you accomplished this week?

Statistics. I just finished my master's in biostatistics, but I didn't want to stop before PhD because, unlike most fields, a PhD is very desirable in industry outside of academia.

MisterMentat  ·  1618 days ago  ·  link  ·    ·  parent  ·  post: What have you accomplished this week?

I got promoted in Starcraft 2!

I'm taking a bit of a brain break before I start my PhD in August. I bum around all fucking day. It's glorious.

MisterMentat  ·  1619 days ago  ·  link  ·    ·  parent  ·  post: After ten years, I have a new desktop background

I always knew we were at the center of the universe.

I saw them at the beginning of June. My wife and I bought tickets the day of the show because we didn't think we'd ever get another shot at seeing them. They were still great at 70. I don't know how they are all still alive.

MisterMentat  ·  1621 days ago  ·  link  ·    ·  parent  ·  post: Astronaut Requirements (could you be one?)

Sadly, no. I am a statistician. Actually it's not sad. I absolutely love being a statistician!

I have given some thought into reading up on some astrostatistics topics, like image processing and spatial statistics, though.

MisterMentat  ·  1622 days ago  ·  link  ·    ·  parent  ·  post: Astronaut Requirements (could you be one?)

My only missing qualification would be the 1,000 hours of piloting experience! I don't want to be an astronaut though.

When I was a kid, I'd tell my parent's, "I don't want to be an astronaut like everyone else, I want to be an astronomer. That way I don't get killed in space!"

MisterMentat  ·  1622 days ago  ·  link  ·    ·  parent  ·  post: The Definitive and Final Ranking of All 50 States

I wonder if the person who wrote this is from Michigan. It sure seems like it.