Current statistics and some predictions


"Anyone can get a Model T in their favorite color, as long as their favorite color is black." -Henry Ford

However, in the first years of production from 1908 to 1913, the Model T was not available in black[28] but rather only grey, green, blue, and red. Green was available for the touring cars, town cars, coupes, and Landaulets. Grey was only available for the town cars, and red only for the touring cars. By 1912, all cars were being painted midnight blue with black fenders. It was only in 1914 that the "any color so long as it is black" policy was finally implemented.

neelix is correct... so 6 years of any colour OTHER than black ....
 
I see a red pyra and i want too paint it black..
Guys, this threadth is going too derail since lot of miles, it dosnt matter which collor the Pyra will have, as long is get produzed finaly..
Also this long off topics arend a magnet for new customers..
Mybe they say: "look how long this cuminity discus about collors, i dotnt want to be a part of then so i rather will by a GPD Win.."

I got a dream tonight, i got a White Pyra Prototyph and it workd pretty well, as its even playd my PNDs from Pandora..
 
I see a red pyra and i want too paint it black..
Guys, this threadth is going too derail since lot of miles, it dosnt matter which collor the Pyra will have, as long is get produzed finaly..
Also this long off topics arend a magnet for new customers..
Mybe they say: "look how long this cuminity discus about collors, i dotnt want to be a part of then so i rather will by a GPD Win.."

I got a dream tonight, i got a White Pyra Prototyph and it workd pretty well, as its even playd my PNDs from Pandora..
Maybe a product for which all aspects get decided by the manufacturer behind closed doors would be better for those people. Or just not looking into this forum and see what's coming later.
 
The transparent pyra looks very nice in my opinion. All colours i`ve seen so far look very nice! :)
 
Guys, this threadth is going too derail since lot of miles, it dosnt matter which collor the Pyra will have, as long is get produzed finaly..
Maybe we should bump the official news thread about color. Since it doesn't matter what color it is, those of us that have a preference will probably continue to discuss it.
 
Yes, it can be any color... but... in metallic? (like the cars are now-a-days)

(just trolling).

As for predictions: I want the Pyra to be white at delivery, but when turned around, it would flame up and become dark blue...

http://www.bestgifever.com/?yes=b65553ce9a6e50667500edcc432303e3


if x is days sinds pre-order, then y is the amount of Pyra's pre-ordered:

y = 110.7577856 ln(x) + 350.2383681

Now the interesting part: 350/110 -> aproximately the 1:3 ratio of US:EU+restoftheworld


The poly regression is:

y = -1.784154958·10-2 x4 + 7.965785504·10-1 x3 - 12.82672462 x2 + 99.22386282 x + 269.0067873

Thanks to: http://www.xuru.org/rt/TOC.asp and @vcoleiro1
 
Last edited:
y = 110.7577856 ln(x) + 350.2383681

solving for y = 900 preorders:

900 = 110.7577856 * ln(x) + 350.2383681

900 - 350.2383681 = 110.7577856 * ln(x)

ln(x) = 549.7616319 / 110.7577856

x = e^4.963638709 =~ 143 days

so the logarithmic equation can't be right? I'd expect something more like x = 40 days, which is around 10th June (I'm assuming ~10 orders a day, maybe that's over-optimistic).

I'm leaving the polynomial equation as an exercise for the reader, naturally.
 
Log actually models when the people-that-can-preorder pool is limited and fixed. However, through word of mouth this pool keeps growing. So, you are correct, the logarithmic regression is not that good up until yesterday. Also, note that 350 (the constant factor) is actually the preorders of day one. So that day was kind of a singularity, which can not be modelled, and should be factored in as a constant.

For the ones that want to get a better model (for example: poly), take the @vcoleiro data and paste it in the website mentioned earlier:

1 350
2 429
3 478
4 507
5 525
6 551
7 563
8 573
9 590
10 601
11 610
12 621
13 629
14 645
15 653
16 665
17 675
18 682
19 687
20 695

Update to 19 datapoints:
y = 112.3626812 ln(x) + 348.0876387
y = 366.7816819 * x^0.215470155
y = -1.418121857·10-2 x^4 + 6.724571737·10-1 x^3 - 11.46127533 x^2 + 93.84073437 x + 274.5892673


Update for 20 datapoints, used:

y = 8.833726959·10-2 x3 - 3.5881036 x2 + 55.59939578 x + 322.7655315

Predicts 1000 by day 28
 
Last edited:
Yes, it can be any color... but... in metallic? (like the cars are now-a-days)

(just trolling).

As for predictions: I want the Pyra to be white at delivery, but when turned around, it would flame up and become dark blue...
Is coal dark blue? I thought most of the time they wore black.

I didn't think ED was going to add enough metallic stuff for it to look like car paint, I thought he just wanted it not to look flat and plain.
 
It may be that, plus however many prepreorders haven't been converted, but no promises.
 
With 20 datapoints and this polynomial regression formula:

y = 8.833726959·10-2 x^3 - 3.5881036 x^2 + 55.59939578 x + 322.7655315


Predicts 1000 Pyra's preordered by the end of day 28, which is 2016-05-28 23:59 CET

However, visual inspection of the curve, shows tendency to be 750 by day 25 and 800 by day 30
 
Last edited:
@FBnil So you're predicting a trend reversal, while you're prediction is based on the given data? How does that work?
 
I am pretty sure behavior of a tiny subset of the human population can be easily predicted based on such calculations.
 
...and ten sig. fig.s are definitely appropriate when the dependent variable is a three (maybe four) digit integer!

Even y = 110 ln(x) + 350 could be seen as excessively precise.
 
@rygD Just saying the furmula isn't a good fit (unless there's something to know, that I don't).

Take a look at the graph http://p.rdw.se/pyra-preorder.html. Visually estimate the point (28, 1000) and tell me, you see that graph going anywhere near that point.

But maybe there's just something wrong with my eyes.

@Binky Sorry, I don't understand "sig. fig.s". ?
 
i matched something like a y(x) = ln(ln(x+1)*A+1)*B, which seems a bit more realistic than a polynomial, though the mid-region wasn't perfect (could probably mess with a few parameters, though).
 
Well, this stats game is addictive. Here's my analysis.

We are not looking at a single curve. This is the superimposition of at least three different demographics.

Demographic 1: The people who were poised over the keyboard ready to order as soon as they were allowed. This is viewable as a virtually instant spike. Eyeballing it, I model this as 130 people.

Demographic 2: Forum members (who didn't order within the first hour). As far as I can tell, this is about 350 people. I arrived at this by assuming that all of those ordered in the first 5 or 6 days, and treating the curve at that time as linear and finding its y-intercept. I model this as a step response with a time constant of 1.3 (eyeballed): 350*(1-e^(-x/1.3)) . This part could probably stand to be tweaked a little more but it's unimportant.

Demographic 3: Everyone else. The tricky one. Initially, this appeared linear, but in recent days a falloff is becoming apparent; I decided to model this as a step response as well. From day 5 to 15 roughly 12.65 Pyras per day were sold - I will conservatively round this *up* to 13 and treat it as the initial slope for the step response, which makes the equation 13*n*(1-e^(-x/n)), where 13*n is the total number of non-forum goers who end up preordering. I experimented with different values of n to achieve the best fit with the observed falloff - 50 worked well, for a total of 650 "outside" preorders. Rounding the initial slope down to 12 and making n=70 make a slightly more optimistic final prediction of 840 "outside" preorders. These are pretty much the outer limits of the model, so it's not all that sensitive to the exact numbers you pick.

Putting it together: my prediction for now is that Pyra preorders are described by the curve P(t) = 130 + 350*(1-e^(-t/1.3)) + 650*(1-e^(-t/50))

On this basis, I predict that we will hit 800 preorders sometime around day 34, and 900 sometime around day 52, should preorders stay open that long. Total preorders are unlikely to exceed 130+350+840=1320.

Obviously, real life is not math, and I will be quite surprised if this turns out to be accurate. Nevertheless, here's a fun graph showing the fit:

preorder_overlay3.png
 
Back
Top