- Real world problems are often brought to a statistician because the person with the question, for some reason or other, thinks the statistician must be able to help them. The client has often already left out some complicating factors, or made some simplifications, which he thinks that the statistician doesn’t need to know. The first job of the consulting statistician is to find out what the real question is with which the client is struggling, which may often be very different from the imaginary statistical problem that the client thinks he has. The first job of the statistical consultant is to undo the pre-processing of the question which his client has done for him.
- Förra året föreläste jag på en gymnasieskola tillsammans med en hjärnforskare. Naturligvis fick vi frågan om varför vi blivit forskare och som vanligt hade jag inget bra svar. Men hjärnforskaren hade det. Hon berättade att hon drevs av en vilja att bli bäst på något. Detta är en helt rimlig drivkraft för en forskare. Att specialisera sig som forskare innebär att man kan bli den person i världen som är främst inom ett specifikt område. Och ju smalare ett område är desto större är sannolikheten att man blir världsbäst inom det.
Jag har dock insett att min drivkraft inte alls handlar om att bli världsbäst inom ett smalt område. Jag drivs av en vilja att ha hyfsad koll på ganska mycket och det är nog därför epidemiologi passar mig. Som epidemiolog är jag inte expert på ett särskilt organ eller en särskild sjukdom. Däremot är jag expert på kvantitativ metod inom medicin, kunskaper som jag kan applicera inom en mängd områden.
- I am a professor of mathematical statistics, and the reader will notice that, apart from a few sections in Chapters 6 and 7, I treat mostly topics that lie distinctly outside my professional area of expertise. To do so may seem immodest and reckless, but I have two things to say in my defense. First, I have tried very hard to respect the expertise of those who know more than I do about a particular topic.1 Second, the subject of the book is so multifaceted and crossdisciplinary that anyone who takes it on will find themselves to be a nonexpert on most parts of it; yet, this is a book that needs to be written, so someone needs to write it, and it might as well be me.
1) There is an obvious tension between this statement and passages such as [my] treatment [in Sections 3.8 and 4.7] of philosophical arguments by renowned philosopher John Searle. What can I say? One has to strike a balance. When someone is wrong, they're wrong, but I have refrained from delivering such verdicts without first having seriously entertained the possibility that they're right.