statisticalrethinkin..

PrefaceMasons, when they start upon a building,Are careful to test out the scaffolding;Make sure that planks won’t slip at busy points,Secure all ladders, tighten bolted joints.And yet all this comes down when the job’s doneShowing off walls of sure and solid stone.So if, my dear, there sometimes seem to beOld bridges breaking between you and meNever fear. We may let the scaffolds fallConfident that we have built our wall.(“Scaffolding” by Seamus Heaney, 1939–2013)is book means to help you raise your knowledge of and confidence in statistical modeling.It is meant as a scaffold, one that will allow you to construct the wall that you need,even though you will discard it aerwards. As a result, this book teaches the material in ofteninconvenient fashion, forcing you to perform step-by-step calculations that are usuallyautomated. e reason for all the algorithmic fuss is to ensure that you understand enoughof the details to make reasonable choices and interpretations in your own modeling work.So although you will move on to use more automation, it’s important to take things slow atfirst. Put up your wall, and then let the scaffolding fall.Audiencee principle audience is researchers in the natural and social sciences, whether newPhD students or seasoned professionals, who have had a basic course on regression but neverthelessremain uneasy about statistical modeling. is audience accepts that there is somethingvaguely wrong about typical statistical practice in the early 21st century, dominated asit is by p-values and a confusing menagerie of testing procedures. ey see alternative methodsin journals and books. But these people are not sure where to go to learn about thesemethods.As a consequence, this book doesn’t really argue against p-values and the like. It assumesthe reader is ready to try doing statistical inference without them. is isn’t the ideal7