Tim, RE: "Great. Doesn't change the point that there is no statistical significance to the odd/even year up/down correlation. ...(I would suggest experiments with coin flips,"
------------------
If a high percentage of your growing base (new users not cyclical) consists of upgrade buyers buying every 3 to 4 years (cyclical), you might interpret that this chart suggests a rather large upgrade cycle is pending, with some assumptions.
Remember that this chart does not represent "candlesticks" (your words), but rather the buying pattern of semi, which in turn is related to the buying pattern of chips.
Also, if you think the odds of an upgrade buyer buying is being equated to the outcome odds of flipping a coin (essentially your words), you could be confusing a few things that are basic principles of statistics:
First, the "result" of flipping a coin is independent of historical results. When flipping a coin, there's always a 50% chance you'll get heads.
Second, the "result" of a flipping of a coin is not dependent on time. If you flip a coin today or tomorrow, the odds are still the same 50%. Unlike a PC/mobile, just because a coin gets old doesn't mean it no longer works or can't be flipped.
So, when you analyze the stretches between cycles, you would be in error to equate it to the patterns of a coin where past event (outcome of a coin flip) is independent of future event (outcome of a coin flip), when a certain aspect of the upgrade cycle is related to economic cycles.
The significance is not whether the year is odd or even, but duration, somewhat cyclical nature of the buying semi equip, and the number of upgrade users that have not upgraded as of yet (which the chart alludes to). Using an eyeball glance on the semi chart, you could consider that a large upgrade cycle is pending.
Consider an upgrade cycle of X years, and a variance of V, with a percentage of P of all buyers in X year. If the output of that is a Gaussian distribution that loosely reoccurs say every other year or less, that's loosely the output pattern, regardless of your attempts to incorrectly connect it to the results of a coin.
RE: "Poisson distribution"
You're talking about a distribution pattern within a cycle (which is completely different than discussing economic patterns that stretch between the cycles).
Take another look, the distribution under an individual graph looks more like a Gaussian distribution than a Poisson distribution. Mean > 30 . . .
Regarding the pattern between cyles, if you don't believe in small economic cycles, the following might annoy you even further, but might possibly interest others: there were large economic downturns in 1819, 1937, 1957, 1873, 1893, 1914, and 1930 - or respectively, 18, 20, 16, 20, 21, 16 years.
Our last large economic downturn was (I think) around 1983 (whenever the auto industry went bust and almost took down the rest of the country), and loosely add 18 years to this and you get a very chilling 2001. Some think there are also political cycles too - approximately every 15 years (i.e. 15 years for the next party, which is 30 years for the next cycle) - Robert McElvaine's 80's book contained a prediction that a liberal epoch was due in the 1990s and Arthur Schlesinger made a prediction in 1949 that the next conservative epoch will begin around 1978. We could very well be stuck with Bush until 2008.
Back to my post, I think there's a tendency for a person to simply get to the bottom-line and by pass the explanation (in this case of small economic cycles), which is what I did in my first post, but of course in doing so it obviously invited the most wildest interpretations of where that bottom-line came from.
But equating economic stretches in buying patterns to candlesticks, please? There is now such a field as behavioral economics these days, but that might be too intuitive or grey for black & white thinking . . .
Regards,
Amy J |
