[R-sig-ME] show p_value for the interaction between two main effects

[Ben Bolker]

  To get the p-value of terms with more than one parameter (like
factors) you typically need to use anova(...,test="Chisq") to compare a
full and a reduced model.  drop1(test="Chisq") might work too.



On 18-01-18 12:21 PM, Luca Danieli wrote:
> Hello everybody,
> 
> sorry to disturb you again.
> Is it possible to obtain only the p_value of an interaction for a lmer() model that uses the function factor()?
> 
> Best
> Luca
> ________________________________
> From: Luca Danieli
> Sent: 17 January 2018 18:26
> To: r-sig-mixed-models at r-project.org
> Subject: show p_value for the interaction between two main effects
> 
> Hello all.
> 
> I have the following model,
> 
> me.model = lmer(Score ~ Closure*ExpertiseType + (Closure|Participant) + (1|Item), datasheet.complete)
> 
> in which Closure and ExpertiseType are ordinal data (so I use the function factor()).
> 
> This does not provide me anymore with an output
> 
> Closure (estimate) (error) (t) (p_value)
> ExpertiseTye ... ... ... ...
> Closure*ExpertiseType ... ... ... ...
> 
> I would need to know the p_value of the interaction, I could I do it?
> 
> Best
> Luca
> 
> 	[[alternative HTML version deleted]]
> 
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>