Greetings folks,
I'm fiddling with SPSS (I'm a former SYSTAT user and not confident with R yet) to do some basic analyses for some frequency data for turtle habitat detections.
Basically for simplicity sake we tracked radio-tagged box turtles in 4 different habitat types, Flatwoods (FW), Oak Scrub (OS), Grassy Prairie (GP), and Ephemeral Wetlands (EW).
We had the following amount of observed detections FW( 487), OS( 396), GP (67), and EW (68). I figure the most simplistic way to determine if there is a difference in frequency of detections between habitat type is a simple Chi-Square (feel free to suggest other analyses as well if you'd like!).
When I do run a basic Chi-Square I find there is significance (P=0.0001).....however what is the best way to to determine where the significance rises? IE Which groups are significantly different form the other?
I'm familiar with Tukey-Kramer and Bonferonni tests in the context of ANOVA, and Kruskal-Wallace in Non-parametric analyses... but not sure the best steps to see where the significance lies between these 4 groups in a Chi-Square context.
Any help is greatly appreciated, but especially in the context of SPSS. I've seen some sources on Post-hoc analyses in that program, but most of those deal with additional other grouping variables (IE sex or season) in Chi-square which I will move onto next!
Thoughts and all help/explanations are welcome!
You may find the attached to be of some use. Best wishes David Booth
Hi,
These three videos on youtube will answer your question:
https://www.youtube.com/watch?v=cOu9rv83G-I
https://www.youtube.com/watch?v=krLz0GK3uwg
https://www.youtube.com/watch?v=Rp0qorrPXA0
For a detailed explanation you can refer to this book:
Contingency Table Analysis by Maria Kateri
ISBN 978-0-8176-4810-7 ISBN 978-0-8176-4811-4 (eBook)
DOI 10.1007/978-0-8176-4811-4
Springer New York Heidelberg Dordrecht London
- Badges
- Science method
- Similar topics
- Mathematics
- Statistics
- Statistical Modeling
- Analyses of Variance
- ANOVA