## Posts tagged ‘sales’

### Results of **Hold On… How Many Copies?** Contest

As predicted, I did not meet my self-imposed deadline of posting the winner of the *Hold On… How Many Copies?* contest on Saturday. But I think you’ll agree I have a good excuse. When I woke at my in-laws on Saturday morning, my wife and kids surprised me with the pronouncement that we’d be spending the day at the Museum of Mathematics in New York City. (A post about that coming soon. It was awesome!) But after a full day of mathematical thinking and a late dinner, I didn’t have the energy to post results last night.

So, sue me.

But without further adieu, I can now announce the winner. Not before some data analysis, though.

The ten responses were:

{21, 137, 301, 333, 392, 429, 453, 595, 1637, 3142}

With a range of **3,121** and an average of **744**, there was quite a spread to the data.

I certainly love the optimism of the respondent who predicted that 3,142 copies were sold! But with Q1 = 390 and Q3 = 559, the responses of 1,637 and 3,142 would both be considered outliers. Indeed, the actual number was lower than either of those guesses, but you won’t hear me complain about selling **634 copies** of *Math Jokes 4 Mathy Folks* from Dec 15 to Dec 21!

**The winner guessed 595 copies.** Well done! He or she will be contacted via email or can contact me directly at patrick@mathjokes4mathyfolks.com.

For what it’s worth, I would not have won my own contest. Knowing that sales vs. rank is generally exponential but also knowing that sales decline during the third week of December, I used a purely linear regression to generate a guess of 473 copies. This would have resulted in a third-place finish. Oh, well. I take solace knowing that a third-place finish is far superior to where I would have placed if I had sponsored a marathon instead.

So, thanks to everyone who bought a copy of the book last week. Wow! Who would’ve thought sales would still be that brisk five years after publication! For that matter, thanks to everyone who’s ever bought a book. This has been an incredible ride!

Thanks, also, to those of you who entered the contest. Sorry if you didn’t win, but I hope you had fun playing.

**Happy holidays!**

### Hold On… *How Many* Copies?

How many copies of *Math Jokes 4 Mathy Folks* do you think sold last week?

Make Your Prediction Here (Google Form) |

Why would you want to make a prediction? Well, lots of reasons…

- Like the author (and readers) of this blog, you’re a math geek.
- You swoon at the sight of data.
- You’ve never met a puzzle you didn’t like.
- You want to show the world how awesome you are.
**You’d like to win a signed copy of***Math Jokes 4 Mathy Folks*, some cool MJ4MF stickers, and a surprise gift, all shipped to you in exclusive MJ4MF packaging!- All of the above.

If you’re reading this blog, then you surely love being alive in the Age of Big Data. I love it, too, and I devour any data that I can get my hands on.

Amazon feeds my desire by providing two valuable pieces of data about * Math Jokes 4 Mathy Folks*. First, they provide the

**sales rank**for the book, which is updated hourly. Second, they provide

**weekly sales data**. The downside to this latter stat is the delay in its release — they provide data for Monday-Sunday, but it isn’t released until the following Friday. The upside is that big dorks like me use the time from Monday through Thursday to make predictions.

The chart below shows the average sales rank and weekly sales for Nov 24 through Dec 14. (The “average sales rank” is the average of the sales ranks for the seven days each week. Although it’s updated hourly, I don’t have the time to check it that frequently, so I rely on Author Central, which reports the sales rank at the end of each day.) It also shows the average sales rank (but not sales) for last week, Dec 15‑21.

Week |
Amazon Sales Rank(Weekly Average) |
WeeklySales |

Nov 24-30 |
4,742 | 114 |

Dec 1-7 |
3,437 | 279 |

Dec 8-14 |
2,390 | 435 |

Dec 15-21 |
2,063 | ? |

**The question: How many copies of MJ4MF were sold last week?**

Oh, sure… I could just wait until Friday to find out — but what fun would that be?

Instead, I constructed several mathematical models, and then I tweaked them to predict how many books were sold. The tweaks were based on some things I’ve learned over the past couple of years:

- Holiday sales are most vigorous in the first two weeks of December. They slow down a bit in the third week. Consequently, a sales rank of 1,655 on Dec 1 does not equal a sales rank of 1,655 on Dec 21.
- The long-term trend is not linear. In fact, this graph from Foner Books shows that it’s logarithmic.

Which brings us to the contest. Go to the Google form and **enter your prediction and email address**. (The email is only so I can contact you if you win.) **Closest guess to the actual number of sales will win the grand prize.** In the event of a tie, a winner will be randomly selected (or if I’m feeling generous, maybe there will be multiple winners… it’s hard to predict my disposition on any given day).

So, what are you waiting for? Open Excel or SPSS or your stat software of choice, muddle through a few regressions, and submit your entry!

**Winners will be announced on Saturday, December 27, 2014.** The exact time will depend on what time I roll out of bed, what activities my wife and kids propose for the day, and my particular disposition on Saturday. On second thought… safest if you check back on Sunday.

Good luck!

### Amazon Sales Rank, and What Math Geeks Do

Today, I asked my son’s if they would like to buy The Oatmeal’s *Why Grizzly Bears Should Wear Underpants*. They laughed uproariously at the title, and then Eli asked, “Is that the #1 book on Amazon?” In fact, it’s not. At the time of this writing, its ranking was #624. “That’s not #1,” Alex affirmed, then added, “but it’s a lot better than your book.”

Ha-rumph.

“A lot better” is highly subjective. Sure enough, the #3,517 ranking of *Math Jokes 4 Mathy Folks* has an absolute difference of 2,893 compared to *WGBSWU*; or, if you’re into ratios, the rank of my book is five times as much as the rank of *WGBSWU*. But what does that really mean?

In practical terms, it means that the number of copies of *WGBSWU* that will sell on Amazon this week is approximately six times the number of copies of *MJ4MF* that will sell during the same period. If my calculations are correct, that is. No one is really sure how ranking translates to sales, but I estimate that approximately 250 copies of *MJ4MF* and 1,500 copies of *WGBSWU* will sell this week.

This is what math geeks do: We try to understand everything quantitatively.

I took weekly sales data for *MJ4MF* and compared that with the book’s average ranking for the week. I randomly chose 20 weeks in 2012-13 for this analysis, because while pulling weekly sales data is relatively easy — it’s provided at Amazon Author Central — determining weekly average ranking is more difficult, since data has to be pulled day by day. And it’s not as simple as just exporting the data to Excel or a CSV file… the data is provided in a graph, and if you want to manipulate that data in any way, you have to look at each point on the graph, determine its value, and then enter it manually. Ugh.

The graph below shows the relationship between average rank and weekly sales:

The regression equation *S* = 914.77 × *R*^{-0.977} gives a reasonably good fit (*r* = 0.89). What’s interesting is that this formula is less accurate in November and December than during the rest of year. There are two reasons for that. First, sales increase dramatically during the holiday shopping season. Second, such a formula is bound to be less accurate with larger numbers.

The **average rank** for December 9-15 was **#3,592**, and using the formula above, approximately **253 copies** of *MJ4MF* should have sold. (I suspect that estimate is a little low. For the same week last year, the average rank was #4,573 and 277 copies were sold.)

Amazon posts sales data for each week on the following Friday. Sales data for last week won’t post until December 20. I’ll update this post on Friday and let you know how well I did.

[**Update, 12/20/13:** A record-breaking 335 copies of *MJ4MF* sold December 9-15. (Thank you!) But as predicted, the estimate was indeed low. As I gather more data, perhaps I will be able to create a better model.]

### Giving Thanks

The end of the year is a good time to reflect and be thankful for all that we have. I have two fantastic, five-year-old sons who love math and their daddy — what more could a man want?

Eli is thankful, too. This is the note he wrote to his teacher for the Math Enrichment homework she asked him to complete during the holiday break:

When I asked why he was thankful for homework, he said, “Because this was fun!”

Checking sales on Amazon Author Central tonight, I was thankful to the 299 folks who bought a copy of *Math Jokes 4 Mathy Folks* from December 17‑23, making it the best-selling week for my silly joke book yet. In fact, between Thanksgiving and Christmas, an astounding 928 people bought my book; people who, apparently, are unaware that they could have gotten not one but two venti, decaf, sugar-free, non-fat, vanilla soy, extra hot, no foam, mocha cappuccinos with three shots, light whip, extra syrup, cinnamon and sprinkles at Starbucks for the exact same price. Oh, well… their loss.

These numbers represent a sales increase of nearly 40% compared to the 2011 holiday season. My financial planner previously predicted that I’d be able to retire at age 65; but, if this trend continues, I might be able to retire at age 64 9/10.

Allow me to take this opportunity to thank all of you, whether you read my blog posts religiously in 2012, stopped by only once in a blue moon, bought *Math Jokes 4 Mathy Folks* from a local, independent bookstore, or stole a copy from your local library. I appreciate your support, in whatever form it takes.

Wishing you peace, joy, and happiness in 2013, y’all. May you occasionally laugh so hard that milk comes out of your nose.