SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Politics : Politics of Energy

 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext  
To: enginer who wrote (5477)2/28/2009 6:52:06 PM
From: RetiredNow  Read Replies (1) of 86356
 
enginer,

Thx for posting the chart. However, I don't think you are reading that chart right. I do alot of statistics in my line of work. One heuristic we use to tell quickly from an eyeball chart like this if there is a new trend in the making, is to look at the average trendline and count sequential datapoints above and below the line. If you see, 6 sequential points or more either above or below the average, then you have a new trend. If there are 8 or more, the probability is VERY high you have a new trend. The reason this heuristic works is that if there was no new trend in the making, randomness would mean an equal number of points above and below the line, and the probability would be high you would NOT see 6 or more point sequentially above or below the line.

Now let's apply that to the below. take a look at the cluster in the middle of each up/down cycle. It seems to hover around the 20 line until around 1996-7. Then every one of the mid-cycle clusters afterwards, for 12 consecutive years is below the 20 line. 12 years of data being below the previous trendline means there is a very high probability that a systemic change has occurred that has set this process into a new downward trend.
Report TOU ViolationShare This Post
 Public ReplyPrvt ReplyMark as Last ReadFilePrevious 10Next 10PreviousNext