[2/2] How to Make the World Add Up (Lies, brazen lies and statistics) (Category Math)
Continue. story Tim Harford's book How to Make the World Add Up ends with a list of the remaining rules:
4. To see the whole picture, step back. It is important to be able to see the information in context, then statements such as “another terrible incident happened” can obscure the trend that “in general, the number of incidents decreased”:) That is, we need comparisons and context to understand how theses fit together. 5. Find out the background. When we see intriguing research results, it’s often due to the publication effect. (publication bias). More broadly, we need to identify the source of the statistics and examine whether all the data have been taken into account. 6. Ask who's missing. One should always ask oneself whether all groups of people were included in the studies and, if not all, how the study would have changed. In most of the older classical psychological studies, participants were college students rather than a representative sample of the entire population. At the same time, it lacked even female students who could be recruited relatively easily for research, but had not been thought of before. You can read more about this in the post about “Poll that changed the polls” 7. Demand transparency from the computer. This point is especially relevant in our time when we have a lot of big data and complex algorithms. It’s important not to be afraid to ask uncomfortable questions about what the data is and how the algorithm works. Interestingly, the conditional perplexity.ai, together with the generated response, provides links to the sources from which it obtained the information. It doesn’t always save you from hallucinations, but at least you can do fact-checking. 8. Appreciate the cornerstone of statistics. The author suggests focusing on official statistics, especially in those countries where it is not customary to manipulate it in favor of a political course. 9. Keep in mind that disinformation can also be attractive. If you are shown a beautiful visualization, graph or dashboard, then you should not be shy and ask questions about what is behind such beauty:) 10. Don't be afraid to change your mind. The author says that it is necessary to be able to change your opinion when new experience or available information appears. That is, we need to reflect on whether we are mistaken in insisting on the old point of view. 11. The golden rule. Keep your curiosity. In general, the author suggests digging deeper and asking more questions. He suggests that curiosity can be pumped ...
I don’t know if it is possible to pump curiosity, but I had it from childhood somewhere on a level. 10 from 10. I remember harassing parents, educators, coaches and teachers with questions like, “Why does everything work like this?”) Curiosity does seem to yield good results. Develop curiosity in yourself and your children and explore the world around you with interest!
P.S. In his book, the author mentions other books about statistics.
- How to Lie with Statistics (How to Lie with Statistics) A book that tells you how to lie with statistics. In fact, the author of the book earned a living by shuffling data, convincing, among other things, that smoking does not lead to cancer. n
- Dark data (Dark Data. Why What We Don’t Know Is Even More Important Than What We Do) A book about how data can be screwed up and what can be done about it
- The Tyranny of Metrics (Tyranny of indicators) This is an interesting book, the title of which goes against the standard approach to measuring everything and everything.) It resembles the structure of a scientific article and famously describes the problems that are largely born of Goodhart's law "When a measure becomes a goal, it ceases to be a good measure."
#Math #Management #Statistics