Take the 2-minute tour ×
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It's 100% free, no registration required.

I just got my Bachelors Degree in mathematics and I've begun working with a company that is requiring some extensive data analysis and statistical inquiry.

I took several statistics courses in college as well as two grad courses but I found that my education was very theory driven.

I was wondering if any of you had a text in Applied Statistics (at the graduate level) that you recommend or have had good experience with.

Thanks in advance,

James

share|improve this question
    
Graduate-level textbooks are usually rather specialized, with titles like Negative Binomial Regression, or Time Series Analysis by State-Space Methods. Can you be more specific about the area you're interested in, or are you looking for some kind of overview? –  Scortchi Jun 18 at 14:15
1  
It would help if you told us some more about your applications! –  kjetil b halvorsen Jun 18 at 14:15
    
I'm mostly interested in regression methods and some modeling. I encounter a lot of binomial RVs as well as random variables rough or unclear distributions. The applications are are rather wide so an overview would be 'ideal' but clearly isn't the most feasible of a request haha. –  jameselmore Jun 18 at 14:19
add comment

5 Answers 5

up vote 9 down vote accepted

Some very good books: "Statistics for Experimenters: Design, Innovation, and Discovery , 2nd Edition" by Box, Hunter & Hunter. This is formally an introductory text (more for chemistry & engineering people) but extremely good on the applied side.

"Data Analysis Using Regression and Multilevel/Hierarchical Models" by Andrew Gelman & Jennifer Hill. Very good on application of regression modelling.

"The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition" (Springer Series in Statistics) 2nd (second) 2009. Corr Edition by Hastie, Trevor, Tibshirani, Robert, Friedman, Jerome More theoretical than the two first in my list, but also extremely good on the whys and ifs of applications.

Working your way through these three books should give a very good basis for applications.

share|improve this answer
    
Wow! Great, thank you. –  jameselmore Jun 18 at 14:23
    
Box, Hunter, & Hunter is worth reading for anyone at any level who hasn't already read it. –  Scortchi Jun 18 at 15:01
    
1  
I'm a big fan of the Gelman/Hill book. –  John Jun 18 at 17:09
add comment

Harrell (2001), Regression Modelling Strategies is distinguished by

  • covering modelling from start to finish—so data reduction, imputation of missing values, & model validation are among the topics included
  • an emphasis on explaining how to employ different methods at different stages
  • thoroughly worked-out examples (& S-Plus/R code) taking up much of the book
share|improve this answer
add comment

In addition to those, Introductory Econometrics: A Modern Approach by Wooldrige has pretty much everything you could ever want to know about regression, at an advanced undergraduate level.

edit: if you're dealing with categorical outcomes, Hastie et al is indispensable. Also, Categorical Data Analysis by Agresti is a good classical approach, as opposed to Hastie et al's machine learning approach.

share|improve this answer
    
I do not think Wooldridge is particularly advanced. In my opinion a better reference would be Hayashi's Econometrics or even Wooldridge's second text, " Econometric Analysis of Cross Section and Panel Data". –  JohnK Jun 18 at 14:59
1  
Using Hayashi for "applied statistics" is like using a flamethrower to light a candle. He asked for less theory, not more. Also, I think Wooldridge is conceptually sophisticated for an undergrad book even if it's not so technical. It's not like I recommended Stock & Watson. –  ssdecontrol Jun 18 at 15:01
1  
I do not agree but I do like the metaphore ;) –  JohnK Jun 18 at 15:03
add comment

I've gotten a lot of use out of Sheskin's Handbook of Parametric and Nonparametric Statistical Procedures. It's a broad survey of hypothesis testing methods, with good introductions to the theory and tons of notes about the subtleties of each. You can see the TOC at the publisher's site (linked above).

share|improve this answer
add comment

I used "Engineering Statistics" by Montgomery and Runger. It's pretty good (especially if you have a strong math background). I'd also highly recommend checking out CalTech's online Machine Learning course. It's great for an introduction to ML Concepts (if that's part of your data analysis). https://work.caltech.edu/telecourse.html.

share|improve this answer
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.