[R-sig-ME] Method to transform fixed effect parameter estimates back on to the response scale [after glmer() with family=Gamma(link = "log")] ??

Paul Johnson pauljohn32 at gmail.com
Wed Aug 12 10:18:39 CEST 2015


pj
Paul Johnson
http://pj.freefaculty.org
On Jul 16, 2015 12:43 AM, "Daniel Newman" <dan.newman86 at gmail.com> wrote:
>
> Subject: Method to transform fixed effect parameter estimates back on to
> the response scale [after glmer() with family=Gamma(link = "log")] ??
>
> Dear lme4 experts,
>
> I am using lme4 to model human reaction-time (RT; in milliseconds)
> responses. My model includes both nested and fully crossed random
> intercepts, and fixed effect “predictor” factors.
>
> lmer() seems to work quite well for this, and is nice since I can use the
> fixed effect parameter estimates (beta and Std.Errors) for interpretation
> to say that for every unit of the “predictor” that changes, we expect a
> change of ~beta units in RT on the response scale (milliseconds). Pretty
> happy with the results….BUT…
>
> glmer() may be the better option since the response distribution has a
> positive skew with no zero values (typical RT distribution), and glmer()
> allows the same model specification as my lmer() model, except using
> family=Gamma(link = "log") to account for the skewed response
distribution.
>
> This seems to work well and gives very similar results to the equivalent
> lmer() model, but with somewhat improved residual plots, so I guess the
> glmer() with family=Gamma(link = "log") is a more valid approach since it
> explicitly accounts for the shape of response distribution.

Similar predicted values for inputs? That only sense in which you should
compare.
>
> PROBLEM: Is there a way to transform the fixed effect parameter estimates
> and Std.Errors from the glmer() with family=Gamma(link = "log"), back to
> the response scale (i.e. back to RT in milliseconds). It would be nice/aid
> interpretation to say that for every unit of the “predictor” that changes,
> we expect a change of ~beta units on the response scale.

No, don't back transform params. Yes do run predict() and use that to
explore input _> output mapping. Specify newdata carefully to see what you
want. Run plotSlopes in my package "rockchalk" to see what I mean. That
works on lm and glm, did not consider extend to glmer, but ought to. All we
need is draw one line per group.

>
> Thank you so much for your time!!
>
> Cheers
> Dan
>
>
> --
>
>         [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models

	[[alternative HTML version deleted]]



More information about the R-sig-mixed-models mailing list