R auto.arima软件包版本3.22solve.default中的错误（res $ hessian * n.used）

Question

I am using auto.arima() like that:

F12.Xreg <- fourier(NEW.JMB,12)
F4.Xreg<- fourier(NEW.JMB,4)
fb<-cbind(F12.Xreg, F4.Xreg)
fit <-auto.arima(NEW.JMB, D=0, max.P=0, max.Q=0, xreg=fb)

I don't know how can I avoid error:

Error in solve.default(res$hessian * n.used) : 
 system is computationally singular: reciprocal condition number = 6.64873e-30
Error in if (diffs == 1 & constant) { : argument is of length zero
In addition: Warning message:
In auto.arima(NEW.JMB, D = 0, max.P = 0, max.Q = 0, xreg = fb) :
  Unable to calculate AIC offset

Thanks

Answer 1

The two fourier matrices have identical columns so the design matrix is not full rank. You can create the fourier terms with a single call to fourier() .