My bachelor thesis is about fatigue, nausea and cognitive decline in patients who have head and neck radiation. For example, the dependent variable is fatigue, looked at the difference score (score of fatigue 6 months after radiation (T1) - the start of radiation (T0) score.

The multivariable analysis included:

* T0, as a separate variable, due to the expectation that the relationship between the variable and the endpoint Δfatigue may be different between patients with a low or high score at T0

* Chemotherapy

* WHO-score, as a confounder

My questions are:

- Should I look at the adjusted R2 when all variables are included in the analysis, or look at the adjusted R2 without the confounder in the analysis?

And if you want to look at the R2 of all variables in the analysis (including the confounder), the adjusted R2 is 26%

- Does this indicate that the difference between the patients, whether or not fatigue (the declared variance), is explained by 26% by chemotherapy alone? Because the WHO-score in the analysis is taken as a confounder?

Thanks for the answers.

Regards,

Lisa ]]>

Code:

`model{`

for(i in 1:n) {

y[i] ~ dbeta(alpha[i], beta[i])

alpha[i] <- mu[i] * phi[i]

beta[i] <- (1-mu[i]) * phi[i]

log(phi[i])<- -inprod(X2[i,],delta[])

cloglog(mu[i]) <- inprod(X1[i,],B[])

}

for (j in 1:p){

B[j] ~ dnorm(0,.001)

}

for(k in 1:s){

delta[k] ~ dnorm(0,.001)

}

}"

Since that deviance is equal to sum of deviance residuals squared, and the deviance of my model is negative, I don't know what to do.

Any help? ]]>