I really hope someone can help me with this question, I don't know where else to ask.
I'm setting the number of butterfly species found on a square kilometer of grassland out against how old that square kilometer of grassland is. So 'landscape age' is my independent variable and 'number of species' is my dependent variable.
I want to do a linear regression in SPSS (although it can be done in Excell but I want to know the significance of the trendline). Does my grassland age have to have a normal distribution?
I have far more very old kilometers than very young kilometers and according to my supervisor I need to randomly delete some of my old kilometers in order to get a normal distribution.
Does this sound right to any of you? Do I even need to have a normal distribution?
Thanks
I'm setting the number of butterfly species found on a square kilometer of grassland out against how old that square kilometer of grassland is. So 'landscape age' is my independent variable and 'number of species' is my dependent variable.
I want to do a linear regression in SPSS (although it can be done in Excell but I want to know the significance of the trendline). Does my grassland age have to have a normal distribution?
I have far more very old kilometers than very young kilometers and according to my supervisor I need to randomly delete some of my old kilometers in order to get a normal distribution.
Does this sound right to any of you? Do I even need to have a normal distribution?
Thanks
