Hello
I run a factorial analysis on 20 variables describing the behaviour of
insects on 9 different resistant plants. I then biologically interpreted
each of the 5 factors obtained, with respect to the variables with the
highest loading value for each factor. And I run a GLM on each factor with
plant as independent variable. Eventually, I inferred the resistance
mechanism by comparing (through post-hoc Dunnett's test) the factor score
between each resistant plant and a susceptible standard.
This analysis gave me good results.
However, I am worried that the factors I obtained may vary with the
variability of the variables. For instance, if most of the plants exhibit
the same type of resistance, resulting in a skewness of my dataset, do the
factors reflect all the resistance mechanisms, even the ones in minority?
Additionally, I would appreciate your opinion on conducting GLM on factors.
thank you very much in advance.
Julien.
--
View this message in context:
http://n4.nabble.com/factorial-analysis-influenced-by-data-skewness-tp991087p991087.html
Sent from the R help mailing list archive at Nabble.com.
