multi-level nested anova

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

W Out
Posts: 1
Joined: Thu Apr 11, 2013 11:18 am

multi-level nested anova

Postby W Out » Thu Apr 25, 2013 3:10 pm

Dear all,

Can you please help me with a multi-nested anova while using the syntax window of spss? Thank you very much in advance.

UNIANOVA RCHull BY Taxon Pop_cat
/RANDOM=Pop_cat
/METHOD=SSTYPE(3)
/INTERCEPT=INCLUDE
/CRITERIA=ALPHA(0.05)
/DESIGN=Taxon Pop_cat (Taxon).


1) There are more nested levels (see below), how can I write this down in the line /DESIGN ?

2) How to interpret the outcomes?

2) On internet I read that the F value of taxon provided in the outcome is not correct: http://userwww.sfsu.edu/efc/classes/bio ... 8-2008.htm
Is that correct?

The study:

Experimental set-up: various measurements of size and shape of :
Taxon 1: 5 populations, 2 plants per population, 2 leaves per plant, 2 samples per leaf, 50 objects (individuals) per sample. N=1600.

Taxon 2: 5 populations, 2 plants per population, 2 leaves per plant, 2 samples per leaf, 50 objects per sample. N= 1500.

Differences in sample size due to missing leaves/plants.

Research question 1): can you differentiate between the measurements of the two taxa> discriminant analysis.

Research question 2) what about the intra-taxon variation, are there differences between samples/plants/populations and how does this relate to the differences between taxa? > nested anova

Model: taxon fixed, remaining factors (population, plant, leaf and sample) random.

For the nested anova: data ranked since the data do not meet the assumptions of parametric tests and since transformations do not change much.

I hope this is clear.

Who is online

Users browsing this forum: No registered users and 1 guest

cron