我建立一个模型：model=tslm(training[,1]~trend+season+training[,5])，其中training[,5]是另外一个变量，模型也可以拟合出来。
可是接下来想做向前一步预测，用forecast.lm(model,lgdata[97,5],h=1)出现问题：
Error in model.frame.default(Terms, newdata, na.action = na.action, xlev = object$xlevels) :
  变数的长度不一样('training[, 5]')
In addition: Warning messages:
1: In forecast.lm(model, lgdata[97, 5], h = 1) :
  newdata column names not specified, defaulting to first variable required.
2: 'newdata' had 1 row but variables found have 96 rows

我只想做一步预测啊，那肯定变量只带入一步就行啊，为什么陶根training[,5]长度一致啊。求解。