I am teaching econometrics this semester and using a new book, James Stock and Mark Watson’s Introduction to Econometrics. It’s a very good textbook.
Stock and Watson use a “robust” estimator of standard errors right from the beginning. This means that they can dump an entire chapter on hetereoskedasticity and methods of “correcting” for hetereoskedasticity (these rarely worked in any case.)
They do not waste time discussing the difference between the t-distribution and the normal-distribution. Instead, they assume reasonably large datasets from the get-go and base their theorems on large-sample theory.
The book is not cluttered with examples. Stock and Watson use a handful of applications that they return to again and again as they introduce new problems and new techniques – thus simple regression is introduced with the goal of estimating the affect of the student-to-teacher ratio on test scores. The problem of omitted variable bias is then introduced and the solution of multiple regression then discussed. Later the same example is used to discuss fixed effects and so forth.
Finally, they have a good chapter on evaluating research designs for internal and external validity. In other words, they discuss how to tell the difference between a good study and garbage – really the most important asset for any reader of statistical work.
Two regrets. I would have liked an early chapter on exploratory data analysis. I would have loved a chapter on regression discontinuity design.