ggloor / ALDEx_bioc

ALDEx_bioc is the working directory for updating bioconductor
26 stars 13 forks source link

How to interpretate the aldex.glm() output? #44

Closed zhq90 closed 2 years ago

zhq90 commented 2 years ago

I have run:

mmG <- model.matrix(~ Group + Age + Sex, metadata)
df_clrG <- aldex.clr(df, mmG, mc.samples = 128, denom = "all")
glm.mmG.result <- aldex.glm(df_clrG)

output columns:

 [1] "(Intercept) Estimate"        "(Intercept) Std. Error"      "(Intercept) t value"        
 [4] "(Intercept) Pr(>|t|)"        "model.Age Estimate"          "model.Age Std. Error"       
 [7] "model.Age t value"           "model.Age Pr(>|t|)"          "model.Sexfemale Estimate"   
[10] "model.Sexfemale Std. Error"  "model.Sexfemale t value"     "model.Sexfemale Pr(>|t|)"   
[13] "model.Sexmale Estimate"      "model.Sexmale Std. Error"    "model.Sexmale t value"      
[16] "model.Sexmale Pr(>|t|)"      "(Intercept) Pr(>|t|).BH"     "model.Age Pr(>|t|).BH"      
[19] "model.Sexfemale Pr(>|t|).BH" "model.Sexmale Pr(>|t|).BH" 

The output seem odd to me, would you explain these results?

ggloor commented 2 years ago

This is returning the expected value of the coefficients of the model. The last two terms are the expected value of holm-bonferroni FWER corrections. I am updating the vignette to include this information.

Thanks for the comment, sorry it took so long to do this