Hello!
to see if a machine will need maintenance next month I am doing a logistic regression model, using panel data (0 = no maintenance, 1 = yes maintenance). Dataset example:
I wrote this code but I have doubts that it is conceptually correct. can anyone tell me if I need to add other arguments to make it work?
mod1<-pglm(Yclass ~ Processo + eventi + precedente, data=res$train, family = binomial(link= logit), model="random", index=c("t", "Matricola"))
summary(mod1)
Maximum Likelihood estimation
Newton-Raphson maximisation, 7 iterations
Return code 8: successive function values within relative tolerance limit (reltol)
Log-Likelihood: -148.3882
10 free parameters
Estimates:
Estimate Std. error t value Pr(> t)
(Intercept) -3.30623 0.47164 -7.010 2.38e-12 ***
ProcessoConciario 6.45689 1518.85928 0.004 0.9966
ProcessoDragaggi 1.39857 0.80160 1.745 0.0810 .
ProcessoEnergetico 1.37626 0.61488 2.238 0.0252 *
ProcessoMetallurgico raffinazione 1.24404 0.79567 1.564 0.1179
ProcessoMinerario estrattivo 1.38342 0.54321 2.547 0.0109 *
ProcessoRiciclaggio inerti 1.33535 0.70564 1.892 0.0584 .
eventi 0.13225 0.05536 2.389 0.0169 *
precedente -0.17969 0.02837 -6.333 2.40e-10 ***
sigma -0.72554 0.30551 -2.375 0.0176 *
Signif. codes: 0 ‘’ 0.001 ‘’ 0.01 ‘’ 0.05 ‘.’ 0.1 ‘ ’ 1
Also how do I interpret the output obtained? Specifically, what is "sigma"?
Thanks to those who will help me.