the use of Cronbach’s Alpha was discussed specifically in this interview, but indeed: the techniques you mention are commonly used. Specific patterns emerge in fake data, while these patterns are highly unlikely in ‘real’ data.

Even more: in the case of the study on ‘meat-eating bastards’ (the data of which were ‘obtained’ by the same fraudulent social-psychologist) was uncovered to be fake with a very similar technique. Much more simple, though: a statistician noticed in the presented table that the marginal distribution of observations was logically impossible given the small number of observations.

http://economicsintelligence.com/2011/07/28/how-an-arcane-statistical-law-could-have-prevented-the-greek-disaster/

You can find some R manuals here: http://cran.r-project.org/manuals.html, including one on “R Installation and Administration”. Hope that helps.

Groet,
Kroos

What is a BlogPassport ?

Credibility, Copyright, Professionalism

A BlogPassport is like a real Passport for bloggers. It will verify your identity, so you will get credibility. It will register all your blogs no matter the platform used, so you have your secure badge placed on all of them. It will copyright-protect all of you posts, so you can feel free to share. It will unify your blogger’s presence, so you look like a pro.

Check it out and maybe update your post!

Thank you in advance!
Nick

As I’ve already told you, thanks a lot for your R sessions. Really nice!

Here is my proposition of the same function but for lmer.
(note that it assumes that the “coefficient variable” is always in second position in the formula, i.e. after the tilde ~ , and the group variable in last position… cf. objects a and b in function code!)

I hope it helps.

Enjoy,

Julie

library(mlmRev)
data(Exam)
library(lme4)

visualize.lmer <- function (model, coefficient, group,…)
{
r <- ranef(model)
f <- fixef(model)
attributes(r)[[1]] <- "r1"
r1 <- ((r)$r1)[,1]
attributes(r)[[1]] <- "r2"
r2 <- ((r)$r2)[,2]
effects <- data.frame(r1+f[1], r2+f[2])
number.lines <- nrow(effects)
a<- unlist((attributes(model)$frame[2]))
n <- ncol(attributes(model)$frame)
b<- unlist((attributes(model)$frame[n]))
predictor.min <- tapply(a,b,min)
predictor.max <- tapply(a,b,max)
outcome.min <- min(attributes(model)$eta)
outcome.max <- max(attributes(model)$eta)
plot (c(min(predictor.min),max(predictor.max)),c(outcome.min,outcome.max),
type="n",…)
for (i in 1:number.lines)
{
expression <- function(x) {effects[i,1] + (effects[i,2] * x) }
curve(expression, from=predictor.min[i], to=predictor.max[i], add=TRUE)
}
}

par(mar=c(2.3, 2.0, 2.5, 0.3), bg="white", las=2)
layout(matrix(c(1,2), nrow=1, ncol=2, byrow=T), heights=c(3,3), widths=c(3,3))

model.b <- lmer (normexam ~ standLRT + schavg + (1 + standLRT|school), data=Exam)
summary(model.b)

visualize.lmer(model.b, "standLRT", "school",xlab="Student test at school-entry", ylab="Result on Exam", main="Exam results for 65 schools")

model.01 <-lme(fixed=normexam ~standLRT + schavg, data = Exam, random=~standLRT|school)
summary(model.01)

visualize.lme(model.01, "standLRT", "school", xlab="Student test at school-entry", ylab="Result on Exam", main="Exam results for 65 schools")

**Iteration 1
LME step: Loglik: -1606.834 , nlm iterations: 32
reStruct parameters:
ID1 ID2 ID3 ID4
10.055430 2.372683 0.238945 10.159490
Error in nlme.formula((weight) ~ Reed1model(age_months, a, b, c, d), data = wei02yfemale_gr, :
Step halving factor reduced below minimum in PNLS step
>