My work implies a lot of econometrics, and I had a good formation about it. Nevertheless, I am regularly faced with some semi or non parametric techniques (for instance I had to use quantile regressions, partial estimation, or nonparametric estimation of whole distribution estimations), and I had no courses about it, neither in statistics or econometrics.
So my question is which book would you recommend for someone to have both a good overview and a logical presentation of this domain ? I would like to have a good background for these techniques. I precise that I have a graduate level in econometrics and applied statistics, so some maths are fine, but with some intuition is very good too !
Thanks in advance
Best Answer
I would recommend two books if you are interested in smoothing techniques, especially in density estimation and regression (rather than in tests that don’t require classical normality assumptions, which are often based on ranks rather than the raw data):
The first is much slimmer, a bit more introductory, with lots of examples and illustrations. It covers histograms, nonparametric density estimation, nonparametric regression, semiparametric and generalized regression models, single index models, generalized partial linear models, additive models and their marginal effects and generalized additive models.
The second tome covers nonparametric kernel methods, semiparametric methods, consistent model specification tests, nonparametric nearest neighbor and series methods, and some time series, simultaneous equations, and panel data models at the end. There is not too much about QR in this book. Koenker's QR would make a nice supplement.
It is also worth mentioning some other books. While comprehensive and worth reading later, I found Pagan and Ullah to be a difficult first introductions to this material. I have heard good things about Yatchew's Semiparametric Regression book, but I have not read it myself.