I have a dataset which consists of fish density/biomass from two sampling periods (1 and 2) in two locations (A and B). In sampling period 1 locations A and B are both clear, while in sampling period 2 A is clear but B is experiencing very high turbidity. I want to assess whether the increased turbidity has caused a change in how the fish are using the habitat-- i.e. if they are preferentially choosing the clear "A" location at sampling period 2, compared to sampling period 1.
I was thinking I could assess this with a chi-square test, but my measures of biomass and density are continuous, not discrete. Any suggestions on how to analyze this?
You can use ANOVA with two factors (period and location) to search their effect on density/biomass.
You can also use one of the data mining tools like PCA!
We keep in touch for help.
Regards.
Mohamed Ben-Haddad
Hi Mohamed, I don't think I can use an ANOVA actually because I technically only have one sample per time period/location combination. An ANOVA would require multiple samples (otherwise you only have 1 df); and I don't think PCA would work for this either-- PCA is used to generate a value that encapsulates a variety of correlated factors, like in behavioral observations where one records a variety of measures of aggressive behaviour and then uses PCA to generate a single value for "Aggressiveness" which combines all of the component measures.
I opted to use a spatial ANOVA through the program spANOVA in R. This let me enter the lat longs and correct for spatial autocorrelation in the data while testing the significance of my independent factor.
A chi square test wouldn't be appropriate here because one of the assumptions of a chi square test is that individuals can only appear in one of the boxes of the chi square (e.g. healthy treated, healthy untreated, unhealthy treated, unhealthy untreated). This doesn't apply to the fish which can move between the turbid and clear sections and may appear in the other areas on the alternate sampling day.
- Badges
- Science topic