gelman - Bayesian statistics - logistic regression - weak informative priors

video lecture

CrossValidation1_JDS_May2011.pdf tutorial from interesting website (Objekt application/pdf)

CrossValidation1_JDS_May2011.pdf (Objekt application/pdf)

xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx

Statistical Modeling, Causal Inference, and Social Science

Statistical Modeling, Causal Inference, and Social Science

BLOG by andrew gelman et al.

Chapter 3 Logistic Regression Diagnostics

Chapter 3 Logistic Regression Diagnostics: "Logistic Regression Diagnostics"

Multicollinearity in Logistic Regression

Multicollinearity in Logistic Regression: "Multicollinearity in Logistic Regression"

multicollinearity

multicollinearity - ordinary least squares regression
logistic regression

rwilliam

"[R] ROC curve from logistic regression"

"[R] ROC curve from logistic regression"

ROC curve comparison

methods

parametric, nonparametric

deLong, Hanley ... references included in reference.

CENTERING VARIABLES REFS Linear Mixed Models: Statnotes, from North Carolina State University, Public Administration Program

Mean-Centering Does Not Alleviate Collinearity Problems in Moderated Multiple Regression Models


centering variables - collinearity in interaction terms, SAS, animation, demo

Linear Mixed Models: Statnotes, from North Carolina State University, Public Administration Program: "Centering. It is customary to center data prior to running LMM or HLM. Centering means subtracting the mean, so means become zero. Two main types of centering are group mean centering and grand mean centering. For instance, in a study of PerformanceScore, there might be a PerformanceIndividualScore at level 1 and a PerformanceAgencyScore at level 2, where the latter was a mean score for all employees in an agency. The researcher might center PerformanceIndividualScore for individuals by centering on their group (agency) means, where groups were agencies, on the theory that group performance influenced individual performance and differences from the group means should therefore be the variable of interest. Or one could center each PerformanceIndividualScore on the grand mean of all such scores across agencies. Grand mean centering is preferred over group mean centering unless there is theoretical justification for the latter."

Grand mean centering often improves the interpretability of coefficients because "0" now has a meaning (ex., 0 income is mean income, whereas before centering, 0 income might be out of the range of actual observations). Group mean centering, in contrast, changes the meaning of coefficients in complex ways which make coefficients hard to interpret, as different mean values are subtracted from different sets of raw scores. As a result, with group mean centering it is not possible to recalculate output back to raw score interpretations. In essence, one is dealing with a different variable after group mean centering. Grand mean centered income, for instance, will yield different slopes but the same deviance and residual errors as uncentered raw data. Group mean centered income does not. Group mean centered income is no longer simple income but rather measures income deviation from group means. The researcher must examine his or her theoretical model and decide if that is really what was wanted for the "income" variable. As noted by Kreft, de Leeuw, and Aiken (1995), the choice of centering must be made on a theoretical rather than statistical basis, and "centering around the group mean amounts to fitting a different model from that obtained by centering around the grand mean or by using raw scores" (p. 1). Most LMM/HLM software packages support various types of automatic centering. Centering considerations are further discussed in Burton (1993) and Hoffman & Gavin (1998).

logistic regression, linear trend test for OR

cf linear trend test for crosstabulated data - cochran armittage, mantel haenzel, linear-by-linear association

in LOGISTIC REGRESSION

cf to test linear trend (of OR) across quartiles we entered 4-level ordinal term representing medians of 4 quartiles of original continuous

cf Ridker Comparison of CRP and LDL - NEJM

Nieto

Shahar - 2000

find:
*** *** ***
books with worked example how to compute trends in OR logistic regression models

"logistic regression linear trend test Odds ratio how to" Jewell
Nicholas Jewell Statistics for epidemiology. p222
google books

***
statnotes
http://faculty.chass.ncsu.edu/garson/PA765/logistic.htm#contrasts
***
- Maxwell & Delaney "Designing Experiments and Analyzing Data" Lawrence Erlbaum Associates
cf old nabble- SPSS discussion forum

If you want to know more on polynomial contrasts, check specialised books,
like: Maxwell & Delaney "Designing Experiments and Analyzing Data" Lawrence
Erlbaum Associates. If you Google a bit using this search key: "Polynomial
contrasts logistic regression", you will se that it is widely used in
experimental research to test for linear and non linear trends.

*** ***

- selvin , statistical analysis for epidemiologic data, p228 - cf stata-"trend test after logistic regression"

google books

logistic regression, model fit, trend test, boook

Nicholas P. Jewell, "Statistics for Epidemiology" Chapman. xxxxxxxx



Hosmer DW, Jr, Lemeshow S. Applied logistic regression 1989:25-37 John Wiley & Sons New York. .

In all analyses, we modeled Lp(a) concentrations as quartiles to avoid the
assumption of linearity and to reduce the effects of outliers. Furthermore, we
used median Lp(a) concentrations for the categories to test for linear trends
across quartiles. We categorized the data according to the 90th, 95th, and 99th
percentiles and performed threshold analyses. We also used the test of Hosmer
and Lemeshow to evaluate the goodness of fit of the data to the models (20).

Clinical Chemistry. 2008;54:285-291.)

An Introduction to Logistic Regression

An Introduction to Logistic Regression

by whitehead

logistic regression interaction testing how to - Hľadať v Google

logistic regression interaction testing how to - Hľadať v Google: "Testing and Interpreting Mediational and Moderational Models in ... - [ Preložiť túto stránku ]
Formát súboru: Microsoft Powerpoint - HTML verzia
Testing interactions in logistic regression is similar to OLS regression methods, in that one includes an interaction term in the model predicting a binary ..."

King: xxxx
http://faculty.washington.edu/kingkm/Logistic%20Regression/mediation%20in%20logistic.ppt

FAQ: A comparison of different tests for trend

trend test in logistic regression ??? cf Nieto 2000 Sleep apnea health hypertension study

cf cochrane-armittage test for linear trend in genotypes (genetic association testing)

nice explanation - as how some statistical tests are something we now, but have new names. ...... at the same time a bit confusing.


FAQ: A comparison of different tests for trend: "Does Stata provide a test for trend?"

logistic regression resources

1. binary logistic regression - Rodriguez. Available at: http://data.princeton.edu/wws509/notes/c3.pdf [Cit Júl 3, 2010].

general statistical text, but on authors webpage u can find examples how to perform analysis in R statistical software. !!!!!

2. Categorical Data: Part 6: Logistic Regression. Available at: http://www.math.yorku.ca/SCS/Courses/grcat/grc6.html [Cit Júl 3, 2010]. / for SAS , but general concepts very intuitive //

3. log linear model - zrozumiteľné - Rodriguez. Available at: http://data.princeton.edu/wws509/notes/c5.pdf [Cit Júl 3, 2010].

1. linear models - rodriguez - zrozumiteľne! Available at: http://data.princeton.edu/wws509/notes/c2.pdf [Cit Júl 3, 2010].

generalized linear model, R

http://data.princeton.edu/R/glms.html