- Tags:: 📚Books, 🗣️ A chart from the 40s is all you need
- Author:: Donald J. Wheeler
- Liked:: 6
- Link:: Understanding Variation: The Key to Managing Chaos - The W. Edwards Deming Institute
- Source date:: 2000-01-01
- Finished date:: 2024-02-01
- Cover::
Why did I want to read it?
In preparation for 🗣️ A chart from the 40s is all you need.
What did I get out of it?
This is clearly a problem when your function is to create knowledge, since organizations tend to chaos (Ser data-driven no es de guapas):
The problem with our information age was succinctly stated by Daniel Boorstin when he said: “Information is random and miscellaneous, but knowledge is orderly and cumulative.”
No comparison between two values can be global. A simple comparison between the current figure and some previous value cannot fully capture and convey the behavior of any time series. (p. 1)
The problem of WoW, YoY tables:
Since both the current value and the earlier value are subject to this variation, it will always be difficult to determine just how much of the difference between the values is due to variation in the numbers, and how much, if any, of the difference si due to real changes in the process. (p. 5)
We analyze numbers in order to know when a change has occurred in our processes or systems. We want to know about such changes in a timely manner so that we can respond appropriately. While this sounds rather straightforward, there is a complication —the numbers can change even when our process does not. So, in our analysis of numbers, we need to have a way to distinguish those changes in the numbers that represent changes in our process from those that are essentially noise. (p. 23)
most people begin to scan the percent difference columns to se which numbers have changed the most. The idea si to single out those values which have changed most dramatically and question why they have changed. (…) the practice of comparing lines in a monthly report by comparing the size of the percent differences assumes that al lines should show the same amount of relative variation month to month. Yet, in any collection of time series, each time series will have its own inherent amount of month-to-month variation. Some lines will show large percent differences month to month, and others will show small percent differences from month to month. Therefore, comparing percent differences will guarantee that some lines receive more attention than they deserve while others receive less attention than they deserve. (p. 34)