[Sora] Request for Reference Library Recommendations

[Stewart Valerie T]

Hello Kayla:  Sorry, I did not see whether these are duplicative of your other responses....

In regard to multiple regression, I think it would be useful to read about this technique from a professor who worked with "real world" data in recidivism:

Regression Analysis: A Constructive Critique
Richard A. Berk
SAGE, 2004 - Mathematics - 259 pages
0 Reviews

Regression Analysis: A Constructive Critique identifies a wide variety of problems with regression analysis as it is commonly used and then provides a number of ways in which practice could be improved. Regression is most useful for data reduction, leading to relatively simple but rich and precise descriptions of patterns in a data set. The emphasis on description provides readers with an insightful rethinking from the ground up of what regression analysis can do, so that readers can better match regression analysis with useful empirical questions and improved policy-related research.

In regard to real-world studies and understanding threats to validity of final results from a statistical view:
Experimental and Quasi-experimental Designs for Generalized Causal Inference
William R. Shadish, Thomas D. Cook, Donald Thomas Campbell
Houghton Mifflin, 2002 - Philosophy - 623 pages
1 Review

This long awaited successor of the original Cook/Campbell Quasi-Experimentation: Design and Analysis Issues for Field Settings represents updates in the field over the last two decades. The book covers four major topics in field experimentation:
    Theoretical matters: Experimentation, causation, and validity
    Quasi-experimental design: Regression discontinuity designs, interrupted time series designs, quasi-experimental designs that use both pretests and control groups, and other designs
    Randomized experiments: Logic and design issues, and practical problems involving ethics, recruitment, assignment, treatment implementation, and attrition
    Generalized causal inference: A grounded theory of generalized causal inference, along with methods for implementing that theory in single and multiple studies


Money, Work, and Crime: Experimental Evidence (Quantitative studies in social relations series) , by Peter H. Rossi (Author), Richard A. Berk (Author), Kenneth J. Lenihan (Author)

In PARTICULAR the chapter by Berk and Brewer called "Feet of Clay in Hobnail boots"  page 238 or something like that.  It talks about over fitting regression models to real world data.

Hope these help.
Valerie T Stewart, Ph.D.
Manager, Oregon Enterprise Data Analytics
Oregon Forecasting Research and Analysis
Valerie.t.stewart at dhsoha.state.or.us<mailto:Valerie.t.stewart at dhsoha.state.or.us>
(503) 945-5676 desk line
(503) 449-5096 mobile phone





From: Sora [mailto:sora-bounces at listsmart.osl.state.or.us] On Behalf Of Brookshire Kayla
Sent: Tuesday, January 17, 2017 4:33 PM
To: 'sora at listsmart.osl.state.or.us' <sora at listsmart.osl.state.or.us>
Subject: [Sora] Request for Reference Library Recommendations

Good Afternoon SORA Members,

I am a Research Analyst with the Department of Justice, Division of Child Support. We are in the process of building a research analyst reference library for our team.

Given the expansive body of knowledge of SORA members, we wanted to reach out and ask: what are your recommendations for specific titles to add to our library?

We are particularly interested in obtaining references for the following areas:

?  SQL training materials, and

?  References for quantitative analysis (descriptive and inferential) including multivariate regression

Any recommendation of texts, manuals, handbooks, etc. from introductory to advanced level would be most appreciated.

Thank you all in advance,

Kayla M. Brookshire
Program Performance Analyst | Division of Child Support
Oregon Department of Justice
Child Support Program Administration
503.947.4639
oregonchildsupport.gov<http://www.oregonchildsupport.gov/>

*****CONFIDENTIALITY NOTICE*****

This e-mail may contain information that is privileged, confidential, or otherwise exempt from disclosure under applicable law. If you are not the addressee or it appears from the context or otherwise that you have received this e-mail in error, please advise me immediately by reply e-mail, keep the contents confidential, and immediately delete the message and any attachments from your system.

************************************
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://omls.oregon.gov/pipermail/sora/attachments/20170118/2a4928fb/attachment.html>