Reading Challenges and Nobel Prizes

This year, I decided to double last year's reading challenge goal on Goodreads. I've challenged myself to read 48 books this year. I'm doing really well!

This morning, I started Never Let Me Go by Kazuo Ishiguro, which was highly recommended by a friend. Yesterday, that same friend let me know that Kazuo Ishiguro is being awarded the Nobel Prize in Literature:

Mr. Ishiguro, 62, is best known for his novels “The Remains of the Day,” about a butler serving an English lord in the years leading up to World War II, and “Never Let Me Go,” a melancholy dystopian love story set in a British boarding school. He has obsessively returned to the same themes in his work, including the fallibility of memory, mortality and the porous nature of time. His body of work stands out for his inventive subversion of literary genres, his acute sense of place and his masterly parsing of the British class system.

“If you mix Jane Austen and Franz Kafka then you have Kazuo Ishiguro in a nutshell, but you have to add a little bit of Marcel Proust into the mix,” said Sara Danius, the permanent secretary of the Swedish Academy.

At a news conference at his London publisher’s office on Thursday, Mr. Ishiguro was characteristically self-effacing, saying that the award was a genuine shock. “If I had even a suspicion, I would have washed my hair this morning,” he said.

He added that when he thinks of “all the great writers living at this time who haven’t won this prize, I feel slightly like an impostor.”

BTW, I just added a Goodreads widget to my blog to show what I'm currently reading.

This is Pretty Grool

In the movie Mean Girls, Aaron (the love interest) asks Cady (the heroine) what day it is, and she responds October 3rd. Hence, October 3rd was dubbed "Mean Girls Day," and people celebrate by posting Mean Girls memes, watching the movie, and probably wearing pink.

This year, 4 members of the cast released this video, asking fans to help victims of the Las Vegas shooting. Here it is:

“On #October3rd, he asked me to help.” #MeanGirls

Please help the victims of the tragedy in Las Vegas at https://t.co/YMwEV1SDsL pic.twitter.com/OhXNSMvCYC

— Jonathan Bennett (@JonathanBennett) October 3, 2017

Statistical Sins: Stepwise Regression

This evening, I started wondering: what do other statisticians think are statistical sins? So I'm perusing message boards on a sleepless Tuesday night/Wednesday morning, and I've found one thing that pops up again and again: stepwise regression.

No stairway. Denied.

Why? Stepwise regression is an analysis process in which one adds or subtracts predictors in a regression equation based on whether they are significant or not. There are, then, two types of stepwise regression: forwards and backwards.

In either analysis, you would generally choose your predictors ahead of time. But then, there's nothing that says you can't include far more predictors than you should (that is, more than the data can support), or predictors that have no business being in a particular regression equation.

In forward stepwise regression, the program would select the variable among your identified predictors that is most highly related to the outcome variable. Then it adds the next most highly correlated predictor. It keeps doing this until additional predictors result in no significant improvement of the model (significant improvement being determine by change in R²).

In backward stepwise regression, the program includes all of your predictor variables, then begins removing variables with the smallest effect on the outcome variable. It stops when removing a variable results in a significant decrease in explained variance.

As you can probably guess, this analysis approach is rife with the potential of false positives and chance relationships. Many of the messages boards said, rightly, there is basically no situation where this approach is justified. It isn't even good exploratory data analysis; it's just lazy.

But is there a way this analysis technique could be salvaged? Possibly, if one took a page from the exploratory data analysis playbook and first plotted data, examined potential confounds and alternative explanations for relationships between variables, then made an informed choice about the variables to include in the analysis.

And, most importantly, the analyst should have a way of testing a stepwise regression procedure in another sample, to verify the findings. Let's be honest; to use a technique like this one, where you can add in any number of predictors, you should have a reasonably large sample size or else you should find a better statistic. Therefore, you could randomly split your sample into a development sample, where you determine best models, and a testing sample, where you confirm the models created through the development sample. This approach is often used in data science.

BTW, I've had some online conversations with people about the term data science and I've had the chance to really think about what it is and what it means. Look for more on that in my next Statistics Sunday post!

What do you think are the biggest statistical sins?

Free Tools for Meta-Analysis

My boss is attending a two-day course on meta-analysis, and shared these tools with me, available through Brown School of Health:

• The Systematic Review Data Repository - as the name suggests, this is a repository of systematic review data, so you pull out data relevant to your own systematic review as well as contribute your own data for others to use. Systematic reviews are a lot of work, so a tool that lets you build off of the work of others can help systematic reviews be performed (and their findings disseminated and used to make data-driven decisions) much more quickly
• Abstrackr - a free, open-source tool for the citation screening process. Conducting a systematic review or meta-analysis involves an exhaustive literature review, and those citations then have to be inspected to see if they qualify to be included in the study. It isn't unusual to review 100s of studies only to include a couple dozen (or fewer). This tool lets you upload abstracts, and invite reviewers to examine abstracts for inclusion. This tool is still in beta, but they're incorporating machine learning to automate some of the screening process in the future. Plus, they use "automagically" in the description, which is one of my favorite portmanteaus.
• Open Meta-Analyst - another free, open-source tool for conducting meta-analysis. You can work with different types of data (binary, continuous, diagnostic), conduct fixed- or random-effects models, and even use different estimation methods, like maximum likelihood or Bayesian. 
• Open MEE - a free, open-source tool based on Open Meta-Analyst, with extra tools for ecological and evolutionary meta-analysis. This might be the tool to use in general, because it has the ability to conduct meta-regression with multiple covariates. 

I think of all of these, I'm looking forward to trying out Abstrackr the most.

And of course, there are many great meta-analysis packages for R. I'm currently working on a methods article describing how to conduct a mini meta-analysis to inform a power analysis using R tools - something I did for my dissertation, but not something everyone knows how to do. (By working, I mean I have an outline and a few paragraphs written. But I'm hoping to have more time to dedicate to it in the near future. I'm toying with the idea of spending NaNoWriMo this year on scholarly pursuits, rather than a novel.)

BTW, if you like free stuff, check out these free data science and statistics resources (and let me know if you know of any not on the list).

Mantis Follow-Up

I did a bit of research on the praying mantis, trying to find out all about the one I saw behind my apartment building yesterday:

First, I found out it's a Chinese mantis.

Second, I'm pretty sure this one is male. He's long and skinny, like many of the males I saw in pictures. Female mantises (mantids?) are generally bigger and wider. As a male mantis, he'll be doing a great job keeping the back porch free of moths and whatnot, and won't be doing some of the terrifying things female mantises do, like eating hummingbirds or, you know, their mate.

I didn't see him when I came home from dinner last night, but he was back in his same spot this morning. If I see him again, I'll have to name him and consider him the unofficial mascot of my building.

In the interest of being prepared, what should his name be?

Cool Sighting Behind My Apartment Building

I've never seen a praying mantis in person - maybe behind glass once, but never out in the wild. This afternoon, I found one hanging around (literally) behind my apartment building. After snapping a quick picture with my phone, I ventured back out with a nicer camera; thankfully, it was still there:

Statistics Sunday: Free Data Science and Statistics Resources

I'm working on building up a list of some free resources for data science and/or statistics. Through the data science conference and a book I recently finished, I've learned about some awesome resources already - I know there's more out there, but I wanted to share what I've found so far. This will remain a living document that I'll continue to update as I discover more resources.

Data Science E-Books 

Many of these books are statistically-oriented, but then a big part of data science involves drawing conclusions from the data. Hence, the line between the list below and the next list on statistics resources may be a bit blurry.

• Analyze Survey Data for Free edited by Anthony Joseph Damico - this edited online resource, which assumes knowledge of R, offers step-by-step instructions for exploring online survey data; entries are contributed by different users and some entries are still awaiting a contributor if you're so inclined!
• Think Python by Allen B. Downey - an introduction to one of the most popular programming languages for data science, Python
• Think Stats: Exploratory Data Analysis in Python by Allen B. Downey - an intro to stats and probability using Python, written by the same author as Think Python above; while this book is meant to introduce statistics to programmers, it could also be a good way for statisticians to get their feet wet in Python
• Deep Learning by Ian Goodfellow, Yoshua Bengio, & Aaron Courville - a free e-book on machine learning, specifically deep learning
• R for Data Science by Garrett Grolemund & Hadley Wickham - this book teaches you how to pull data into R, and clean, model, and visualize; this book was definitely talked up at the data science conference (thanks to a reader for sharing the link to the free e-book version!)
• Ten Signs of Data Science Maturity by Peter Guerra & Kirk Borne - Borne's was one of my favorite presentations from the data science conference I attended; this e-book highlights what indicates an organization is ready to venture into data science 
• The Elements of Statistical Learning Data Mining, Inference, and Prediction by Trevor Hastie, Robert Tibshirani, & Jerome Friedman - predictive modeling and machine learning approaches
• An Introduction to Statistical Learning with Applications in R by Gareth James, Daniela Witten, Trevor Hastie, & Robert Tibshirani - covers many of the same topics as Elements above, but geared more toward beginners in statistical learning; if these are new concepts for you, read this book before Elements of Statistical Learning
• Python Programming WikiBook - another introduction to Python, which also includes extensions into other programming languages and additional resources/links
• R Programming WikiBook - an introduction to programming in R, another popular programming language for data science
• School of Data Handbook - this handbook, which goes along with the courses available through School of Data, offers recipes for scraping, cleaning, and filtering data to get you started on your data science journey

Also, there's a new R package - dslabs, described here - designed to help teach data science.

Statistics E-Books and Resources

• Peter Miksza has created some Shiny apps to visualize statistical concepts, and manipulate different factors (e.g., type of data) to see how it affects the resulting visualization.
• Correlation and Causation: The Trouble with Story Telling by Lee Baker - a sort of follow-up to my previous discussion of spurious correlations, this book discusses the notion of probability and alternative explanations for correlations
• The Probability Cheatsheet by William Chen - technically not an e-book; it's a short PDF document that summarizes key probability concepts, like Simpson's paradox, the Law of Large Numbers, and conditional probability
• OpenIntro Statistics by David M. Diaz, Christopher D. Barr, & Mine Çetinkaya-Rundel - a free introductory statistics textbook and additional statistical resources
• Think Bayes: Bayesian Statistics Made Simple by Allen B. Downey - yet another free e-book from Downey (see Think Python and Think Stats above), introducing Bayes in mathematical notation (if you prefer mathematical notation when learning stats; not everyone does); it also uses Python for computer-aided analysis, so this book also straddles the statistics-data science line
• Research and Statistical Support Services Short Courses by Richard Herrington & Jonathan Starkweather - also not exactly an e-book: this site, part of the R&SS at University of North Texas, contains multiple short documents teaching the basics of statistical software, and a few other computer tools that could aid in research
• How to Share Data with a Statistician by Jeff Leek - this GitHub document describes how to format data to be shared with a statistician, in order to facilitate efficient and timely analysis
• Introduction to Applied Bayesian Statistics and Estimation for Social Scientists by Scott M. Lynch - an introduction to Bayesian analysis and the use of what are called MCMC (Markov chain Monte Carlo) methods; this book starts with a refresher of classical statistics before introducing the Bayesian notion of probability
• Learning Statistics with R by Daniel Navarro - what started off as lecture notes for an introductory statistics class taught with R became an e-book; there's even an R package (lsr) to go along with the book

Do you have any free resources you would recommend?

Like free stuff? Here are some free meta-analysis tools.