This review is for Nate Silver’s, The Signal and the Noise : Why Most Predictions Fail – but Some Don’t.
4.5/5 Very good
I really enjoyed this book. I felt he had some great example of where prediction works well and where it fails (fitting the subtitle). I thought the research was excellent. I definitely walked away learning a lot about statistics and with a few example that I can apply to my own work.
The main facets I didn’t like were his over use of adding in Bayesian statistics and some of the examples were talked through too much. It’s not that I don’t like Bayesian stats, it’s that I felt like he was adding in weird plugs for it that didn’t always fit in the book nicely. Had there been smoother transitions, this might have worked. For the longer examples, I did get tired of reading the same subject after a while. (That is pretty typical of me though, so that might not be saying much.)
All-in-all, I highly recommend it. I thought his comparisons, for example: predicting weather and earthquakes, did a great job of demonstrating what makes models feasible or not and how to improve ones you’re currently building. His writing style is also very enjoyable, filled with smaller relatable situations and fun facts about Nate, himself, or the history of the book’s subjects. It’s definitely a book for anyone that’s interested in prediction or that works with statistics.
In addition to Coursera Reviews, I’ll be giving reviews of various books I read. They will have a similar 5 point scale and a description for why I gave the review.
- 1/5 I probably didn’t even finish this book
- 2/5 Probably not worth reading, unless there’s a good reason
- 3/5 Borrow this from a friend and read in your spare time
- 4/5 This could be the next book in your list
- 5/5 Drop what you’re reading right now and start on this one
I’ve started the Big Data Specialization by University of California, San Diego. This specialization focuses on Big Data by using Hadoop. There are a couple courses ending with a capstone project. The first course is “Introduction to Big Data.”
3/5 – Basic Intro Course
This was a basic introduction course. The three week-long classes were pretty easy. They were mostly videos and ended with setting up Hadoop. The first course in a lot of specializations are just a simple beginning one and this fit the same model. It did give a nice overview of several concepts, talked about Gartner’s hype curve, and had an easy installation of VMWare and Hadoop. I can’t really complain a lot, but I also don’t have a lot of praise for it either. For the amount of money, it’s not really worth it, but the rest of courses can make up for this one. I do think it’s a good start and sets up the rest of the specialization nicely.
Here are the links for Sunday.
I’ll be doing a series of reviews for any Coursera classes I take. Right now, I’m in the Big Data specialization so those will be the first set. I’m planning on using a five point system to talk about how well the classes went. Here’s the scale:
- 1/5 – Don’t even start it, not worth doing
- 2/5 – Maybe if you really need this information, but there are better resources
- 3/5 – If it was a free class, it would be worth it
- 4/5 – Pretty good, but there’s room for improvement
- 5/5 – Definitely worth the time and money
I’ll write up why I give the rates that I assign. For a lot of Coursera classes, they might not me good for me but could be good for someone else, and vice versa. I’ve had trouble finding good reviews for Coursera courses, so I might as well add mine.