Skip to main content
Cross Validated

Return to Question

replaced http://stackoverflow.com/ with https://stackoverflow.com/
Source Link
Community Bot
Community Bot
  • 1

Is there really a difference in result if I use a GLMM with Gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods?

See predict.merMod in R is acting strangely (poorly) when using new levels with glmer modelspredict.merMod in R is acting strangely (poorly) when using new levels with glmer models for an issue with predicting values from a Gamma model that seems to be fixed using a log-transformed model.

Any thoughts?

Is there really a difference in result if I use a GLMM with Gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods?

See predict.merMod in R is acting strangely (poorly) when using new levels with glmer models for an issue with predicting values from a Gamma model that seems to be fixed using a log-transformed model.

Any thoughts?

Is there really a difference in result if I use a GLMM with Gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods?

See predict.merMod in R is acting strangely (poorly) when using new levels with glmer models for an issue with predicting values from a Gamma model that seems to be fixed using a log-transformed model.

Any thoughts?

Slightly improved formatting
Source Link
theforestecologist
theforestecologist
  • 2.3k
  • 7
  • 25
  • 46

Is there really a difference in result if I use a GLMM with Gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods?

See predict.merMod in R is acting strangely (poorly) when using new levels with glmer models for an issue with predicting values from a gammaGamma model that seems to be fixed using a log-transformed model.

Any thoughts?

Is there really a difference in result if I use a GLMM with Gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods?

See predict.merMod in R is acting strangely (poorly) when using new levels with glmer models for an issue with predicting values from a gamma model that seems to be fixed using a log-transformed model.

Any thoughts?

Is there really a difference in result if I use a GLMM with Gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods?

See predict.merMod in R is acting strangely (poorly) when using new levels with glmer models for an issue with predicting values from a Gamma model that seems to be fixed using a log-transformed model.

Any thoughts?

Slightly improved formatting
Source Link
edit approved Jul 16, 2015 at 17:58
mugen
edit approved Jul 16, 2015 at 17:58
mugen
  • 1.5k
  • 1
  • 16
  • 25

GLMM with gammaGamma distribution vs. gaussianGaussian distribution with log transformation

Is there really a difference in result if I use a GLMM with gammaGamma distribution vs. a model with a Gaussian distribution withwith log transformation? If so, how do I choose between the two methods?

See http://stackoverflow.com/questions/31436806/predict-mermod-in-r-is-acting-strangely-.merMod in R is acting strangely (poorly-when-using-new-levels-with-glme) when using new levels with glmer models for an issue with predicting values from a gamma model that seems to be fixed using a log-transformed model. Thoughts

Any thoughts?

GLMM with gamma distribution vs. gaussian distribution with log transformation

Is there really a difference in result if I use a GLMM with gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods?

See http://stackoverflow.com/questions/31436806/predict-mermod-in-r-is-acting-strangely-poorly-when-using-new-levels-with-glme for an issue with predicting values from a gamma model that seems to be fixed using a log-transformed model. Thoughts?

GLMM with Gamma distribution vs. Gaussian distribution with log transformation

Is there really a difference in result if I use a GLMM with Gamma distribution vs. a model with a Gaussian distribution with log transformation? If so, how do I choose between the two methods?

See predict.merMod in R is acting strangely (poorly) when using new levels with glmer models for an issue with predicting values from a gamma model that seems to be fixed using a log-transformed model.

Any thoughts?

Source Link
theforestecologist
theforestecologist
  • 2.3k
  • 7
  • 25
  • 46