Chapter 7
Estimator Selection
DOI: 10.1201/9781003158745-7
Which modeling and which estimator shall I use? These are eternal questions of the statistician when facing data.
The first step is to write down a statistical model suited to analyze the data. This step requires some deep discussions with the specialists of the field where the data come from, some basic data mining to detect some possible key features of the data, and some… experience. This process is crucial for the subsequent work, yet it seems hardly amenable to a theorization.
The second step is to choose at best an estimator. Assume, for example, that after some pretreatments of the data, you end up with a linear model (2.2). In some cases, you know from expert knowledge the ...
Get Introduction to High-Dimensional Statistics, 2nd Edition now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
