var1 var2 var3

0.25 141.421 1

0 200 0

0 141.421 0

0.1 223.607 0

0 173.205 0

0.5 100 1

0.083 346.41 2

0.154 360.555 2

0.214 264.575 0

0 200 0

0.143 264.575 0

0.062 282.843 1

Thanks in advance for your help.

- Thread starter Newbe
- Start date

var1 var2 var3

0.25 141.421 1

0 200 0

0 141.421 0

0.1 223.607 0

0 173.205 0

0.5 100 1

0.083 346.41 2

0.154 360.555 2

0.214 264.575 0

0 200 0

0.143 264.575 0

0.062 282.843 1

Thanks in advance for your help.

Thank you for your question. What I am trying to show is that var3 (count of relatives) increases with the increase of occurrences of specific types of coordination words var1 or var2 (independently from each other). I tried Pearson test of correlation and the results were positive but I am not sure this is the right test.

Your help is appreciated.

Your help is appreciated.

Last edited:

You have to build a generalized linear model (GLM) of the form:

Var3 ~ Var1 + Var2

GLM types to consider: Poisson regression, negative binomial regression, Poisson regression + zero-inflated component, negative binomial regression + zero-inflated component. You can choose the "optimal" GLM type using an objective model selection criterion.

Var3 ~ Var1 + Var2

GLM types to consider: Poisson regression, negative binomial regression, Poisson regression + zero-inflated component, negative binomial regression + zero-inflated component. You can choose the "optimal" GLM type using an objective model selection criterion.

Last edited:

Just a followup question. What effect size measure should I use with the Poisson Regression? I would like to compare (or rank) my independent variables. So, I am wondering if Exp(b) can help determine which significant independent variable has a bigger effect on the change of my dependent variable. Other effect size candidates I've seen online are Cohen d, but I am not sure if it is a good choice for my data described above.

Thanks in advance for your help.

Thanks in advance for your help.

Last edited: