John Green's tumblr: Follow-up to Yesterday's Post about The Fault in Our Stars
…How strong is the correlation between number of readers (as represented by number of ratings) and overall rating? I don’t know. You’ll have to ask Jutze. But there certainly is a correlation (…)**.
Having just sat my AS statistics exam, there was a flurry of excitement in the house as I raced around around trying to find my calculator.
I found that there is a very strong positive linear correlation (r > 0.95) between the number of ratings and the average rating.
But this model falls apart at the edge case: you assume that there’s a linear relation with the number of readers when we know that there’s a cap for the value of the Good Reads rating, which is 5. (…)
The linear relationship is impressive, but also based on only 4 points of data (in addition to the restriction of rating range). But is it really ‘the more, the merrier’? I picked four more authors (in a non-random fashion), had a look at the respective correlations for their novels, and made a couple of graphs to illustrate the results.
(Figure 1 full size)
The relationship is a negative one for Stephanie Meyer’s books. Two books of J.K. Rowling are outliers - her first one in terms of ratings on GoodReads, her most recent one in terms of rating. I therefore took the liberty to plot a quadratic fit (instead of a linear fit). It appears that John Green might be an exception (like the Mongols?) Also, Amazon.com ratings tend to be higher; again, there is no clear relationship between the amount of reviews and the average rating.
And since I recently finished reading “On Chesil Beach”, here’s the data for Ian McEwan’s novels, along with a more appropriately scaled plot for Maureen Johnson’s books:
(Figure 2 full size)
By the way, the correlation between Amazon.com ratings and GoodReads.com ratings for the 40 books I used above is r = .89. The correlation between number of Amazon.com reviews and Goodreads.com ratings is r = .75.
John Green's tumblr: Why Has The Fault in Our Stars Been So Successful?
[…] The same is true on amazon, where the book’s average rating has actually gone up a bit in the past six months (although not in a statistically significant way). […]
Actually, the ratings have decreased in a statistically significant way (alpha < .05). I used the two most recently archived pages from archive.org, which do not cover exactly 6 months. Still, ratings before 2013-02-03 were higher than those after that date.
- Before (2110 ratings): mean = 4.76 (standard deviation = 0.014)
- After (1232 raings): mean = 4.67 (standard deviation = 0.021)
A t-test (two-sided, unequal variances) yields p = 0.0009 (d = -0.12); and for the non-parametric fans, the Wilcoxon rank-sum (Mann-Whitney) test yields p = 0.0001.
Using 2012-10-19 as dividing date, yields similar results:
- Before (1051 ratings): mean = 4.77 (SD = 0.020)
- After (2291 ratings): mean = 4.71 (SD = 0.015)
A t-test (two-sided, unequal variances) yields p = 0.0188 (d = -0.09); the Wilcoxon rank-sum (Mann-Whitney) test yields p = 0.0008. Of course, significance testing might be a questionable procedure in this case - and also in general.
This is actually a census of all Amazon ratings, so there’s no need to test whether ratings differ. The sample is the population. However, the written reviews could be regarded as a subsample of the ratings of all readers.
Is it a random sample? I don’t think so. So can we draw proper conclusions from the significance test results? Nah. I won’t provide a comprehensive discussion of the benefits and problems associated with the null hypothesis significance testing (NHST). I’ll just name one of my favourite objections, which Cohen (1990, p. 1308) phrased nicely: “The null hypothesis, taken literally (and that’s the only way you can take it in formal hypothesis testing), is always false in the real world.” In the present case, the null hypothesis would mean, that average rating of newer readers is exactly the same as the average rating of those who pre-ordered the book etc.
Anyway, the effect size suggests that the drop in ratings is very small, so it should be safe to argue that the book keeps appealing to new readers.
PS: Sorry for nitpicking; this should in no way diminish the article, which I think is highly insightful.
PPS: I spend a good 15 minutes in R trying to beat the data into shape, but I feel much more comfortable in Stata, so I switched and had the analysis in a few minutes. I posted the do-file in my blog in case anyone in curious. (Haha, as if!)
Will Tumblr still be there in 2023? Will my Tumblr still be around? What will it look like? Okay, I’m not prone to changing the appearance of this place. Looking back at Geocities, MySpace, Facebook, AOL, and all this stuff - all that has been created after Jason Newsted joined Metallica. And all this stuff is old by now, and Jason Newsted would still be the “new guy” if he were still in the band. I’d be surprised if I can still come back to this post ten years from now. I mean, all those kids around will have jobs by then! And the TV shows and stuff, it will be old by then. There will be new trends, new stuff, and possibly a new Tumblr.
Above the Meadows, In Dreams: A Teacher's Idealism
I think I like the idea of what I do much better than what it actually is that I do. I’m not sure if that’s a good thing or a dangerous illusion. But I hope it will last as a source for motivation.
I’m a teacher. My parents once were as well. Some tell me that I was born to be a teacher. I…
That’s a wonderful sentence: “I love the idea of killing stupidity and ignorance and poverty by giving away what I know.”
It also ties in nicely with AnnMaria De Mars’s recent blog post “The importance of teachers”, which argues that teachers are among those who change people’s lives much more than seemingly more illustrious professionals.
Image Proposals for Travis
Your Band Name Here
A career in music requires effort, exposure, and endurance. You might not aim at becoming a true professional rock musician (as in: does nothing but music-related stuff 24/7) - the equations are the same. There’s no safe haven for amateur/indie artists. So why not have a go at something semi-serious. And by that I mean: Start your own band. You live in a city? Great, put up ads in music stores, college, anywhere. You live in the middle of nowhere? Great, people will be happy if you approach them. Plus, there’s less to distract you from rehearsing. In any case, network: Is there a local band you like? Make the musicians join your band. Have a vision. BE ORIGINAL.
Keep in mind that your first songs will suck. Feel free to cover anything you like; this keeps up the morale and improves your skills.
Bonus: Form a band that contains only women (plus you). Women are still lamentably underrepresented in indie rock music.
Costs: Some effort, a dollar for paper, a dollar for printing, a dollar for pins, a few bucks for travelling to record shops, instrument shops, community places, then some more effort and possibly a couple of phone calls. From there on it’s the usual expensive associated with being in a band.
Travis - the two color guy
Pick two colors. They’re your image now. Done.
Bonus: Make your all lyrics about (at least) one of these colors.
Risks: Choose wisely - you might have to deal with this monochrome image for the rest of your career! Also, avoid colors associated with (questionable) causes. Also, don’t choose black and that-gray-that-is-almost-black.
Costs: No initial costs here; eventually, you might have to pay extra to achieve posters, cds and t-shirts in exact the same color (over and over again).
Five Seasons and a Movie
Make your music all about a specific TV series, get a built-in audience for free!
Bonus: Make your music about the Season 1 of Community (optionally about how much the following seasons suck(ed)).
Risks: I have no idea about copyright issues (though the U.S. seem to be fine with fair use etc.), you’ll never become super-duper famous on that route.
Costs: At most a bunch of DVD sets; but seriously, you’ve watched them all on netflix already, haven’t you?
The Thomas Lynley Experience
Same as above, only with a book series - in fact, with crime novels by Elizabeth George. Wrock is so last year - be the trend-setter for once. The audience (middle-aged and older women) has yet to discover YouTube, Bandcamp, Tumblr etc. - so there’s little competition in this market segment.
Bonus: Make each song you write about a particular murder from the books.
Risks: Be prepared that your audience is going to expect detailed accounts of sceneries and wardrobes. It’s going to be 90% females and older than you.
Costs: You should read the books - at least some of them, I guess. Wikipedia summaries are scarce, sorry. Also, say hello to cardigans!
The Cat Reverb Experience
Start playing progressive rock while denying that you play progressive rock with relentless vigor. But instead of copying the 70s stuff, just, well, do you thing, which doesn’t even have to be progressive rock. It did work for Steven Wilson, who seems to be on the cover of every (German) music magazine these days.
Bonus: Get semi-famous prog musicians as guests - they are rather willing to solo here and there.
Risks: You’ll probably end up with an audience that’s 90% males and older than you.
Costs: You might need to get a Mellotron, at least for the photo sessions.
John Green's tumblr: Why I Hate Atlas Shrugged with a White-Hot Passion
(I was asked why I dislike the novel Atlas Shrugged so much; I answered; people asked me to make the answer rebloggable, and so I have. All of this, as always, is offered with the caveat that I might be—and often am—wrong.)
1. Atlas Shrugged is a novel of ideas. The plot exists only…
I’m tempted to ditch any NaNoWriMo plans I’ve made so far and just write “Quentin Shrugged” instead. “Who is Margo Roth Spiegelman?” would be the opening line. Everybody’s missing Margo, who has disappeared. Quentin had seen her last when she had come to his window at night to take him on a trip during which they take from the poor looters and give to the rich prime movers. Now with Margo gone, Quentin is the only one who is happy and content. What should he care about Margo’s fate? Towards the end of the book there will be a hundred-page long monologue by Peter van Houten, in which he rambles endlessly about the eyes on the billboard in “The Great Gatsby”. In the end, Margo returns just to find that Quentin has turned into an asshole. So she hooks up with Lacey instead and they imagine each other complexly ever after.
Saturday, March 24th, 2012