1

I run a series of models using gamlss stepGAIC() model selection. The problem that I have is that in gamlss, stepGAIC() uses AIC values to select the variables in the model. Since my sample size is considered small I probably need to use the AICc values to select the best model. I don’t know if I would be able to create models using AIC and select from those models the best based on AICc.

kjetil b halvorsen
  • 63,378
  • 26
  • 142
  • 467
user36467
  • 11
  • 2
  • 3
    Just for reference: stepwise model selection in many cases is a bad idea, see http://stats.stackexchange.com/a/20856/35989 , so you should consider if it is what you really want to do. For alternatives check: http://stats.stackexchange.com/questions/13686/what-are-modern-easily-used-alternatives-to-stepwise-regression – Tim May 08 '15 at 11:04

2 Answers2

3

In general, you can't select "the best" model using stepwise regression. All statistics produced through stepwise model building have a nested chain of invisible/unstated "conditional on excluding X" or "conditional on including X" statements built into them with the result that:

  • p-values are biased
  • variances are biased
  • parameter estimates are biased
  • F statistics are biased
  • false predictors are likely to be included
  • true predictors are likely to be excluded

So, while you could use AIC as a stepwise model building, the consequences of doing so are unreliable and likely invalid model inferences.

Alexis
  • 26,219
  • 5
  • 78
  • 131
0

AICc is given as:

$AICc = AIC + \frac{2k(k + 1)}{n - k + 1}$

where n is the sample size and k is the number of parameters being estimated. You could just create the multiple models you are interested in, then manually calculate the AICc.

dmartin
  • 3,010
  • 3
  • 22
  • 27
  • 1
    Thank you for your response. I already did that but my dilemma is that if I should use AICc for selecting the variables in my models rather than the default AIC used in the stepGAIC function in GAMLSS. – user36467 Dec 23 '13 at 14:07