Silicon Investor (SI) -- The First Internet Community

STOCKTALK

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.

Technology Stocks : Dell Technologies Inc. -- Ignore unavailable to you. Want to Upgrade?

To: GVTucker who wrote (156792)	5/5/2000 4:00:00 PM
From: D.J.Smyth	Respond to of 176387

Tucker But the people that didn't buy an IBM computer in the most recent quarter did not exit the market all together. They simply went to another vendor. Thus, IBM's numbers do not skew the overall industry's growth rate, only IBM's I know you're saying that the sales lost by IBM were gained by others skewing the others' numbers higher, and negating IBM's thus showing an overall affect which washes out. However, when one fails to use a proper mean distribution, one never arrives at an accurate picture (utilizing simple averages, improper use of statistical tools, or leaving in the outliers are only a few examples of utilizing statistics improperly). Regardless; the issue remains - developing an accurate model of predicting corporate PC sales for Dell and those other players gaining market share. When you have the "fab five" growing at +20% and the "rest of the world" growing at a -3%, how does one utilize the -3% growth in relation to the +20% growth? Also, to what extent do we include IBM's -41% in the picture to arrive at a predictive model? The model does not need to include ALL parameters to be accurately predictive - in fact including all parameters tends to make a predictive model less predictive for individual companies. On the other hand including the right parameters makes all the difference. When you say corporate PC sales are growing at 10% YOY (including the effects of Y2K and all other negative onetime events) yet excluding enterprise sales (the net), isn't such a model more a tool only for those wanting to make a particular point? It is nearly useless for predicting overall corporate PC sales for the fab 5 or for sales into the future. One of the biggest offenders of the poor use of statistics when calculating returns: mutual funds. but the government lets them and it helps brings money to the market.