I am comparing four groups (measurements of bone thickness and other bone parameters). The distributions are normal (Kolmogorov–Smirnov test) and variances equal between groups (Levenes test). I have 7 samples in each group.

As I see from the literature this would call for a parametric test. But the results from Kruskal Wallis make more sense than those from ANOVA - I get significant differences on more comparisons whit KW than with ANOVA and biologicly and from what we have observed during analysis those results from KW would make more sense.

So my question is if it is ok to use a nonparametric test in this case or is that wrong?

Best,

Nina ]]>

I am looking at how many burrows are occupied by a skink species at eight sites across a property. Counts of the number of occupied burrows have been taken over three years and I want to know if the change in the number of occupied burrows at a site is significant over the three years ie. is there a decreasing or increasing trend in occupancy at a particular site.

I am having difficulty working out which test to use. Given the data is categorical it seems a chi-square test would be best but the same burrows are sampled each year so the samples are not independent. I have also looked at a nested ANOVA but it seems that this would tell me if there is significant differences

Any help would be greatly appreciated! ]]>