To chi square or not to chi square?

Question

I am running a frequency count on the instances of powerless of language in the language of prosecuting attorneys and the same frequency count of the defendants language.

I am asking if the frequency of the powerless language by women makes a favorable verdict and less powerless language by men creates a favorable verdict. I have 400 cases/transcripts.

Below is my hypothesis: Is the use of powerless language used by defense attorneys in arguments independent of the verdict?

a. Is the use of powerless language used by female defense 
    attorneys in closing    arguments independent of the verdict? 
Ha) The use of powerless language by a female defense attorney is 
    not independent of the verdict.
Ho) The use of powerless language by a female defense attorney is               
    independent of the verdict   
b. Is the use of powerless language used by male defense attorneys 
    in closing  arguments independent of the verdict? 
Ha) The use of powerless language by a male defense attorney is 
    not independent of the verdict.
Ho) The use of powerless language by a male defense attorney is                 
    independent of the verdict. 

Would I run two separate chi squares: one on all of the prosecuting attorneys and one on all the defending attorneys with the verdicts?

---

You are all right- thank you! I am not asking the right question for the research. The comment about all of the persuasion that could have taken place is exactly what I want to adrress. I want to see if the court makes the decision outside of chance. So based on the comments I have changed my hypothesis: Is the frequency of powerless language in arguments to the Supreme Court from 2007– 2011 independent of the verdict? a. Is the frequency of powerless language used by female attorneys in closing arguments independent of the verdict? Ha) The frequency of powerless language by a female attorney not independent of the verdict. Ho) The frequency of powerless language by a female attorney is independent of the verdict. b. Is the frequency of powerless language used by male attorneys in closing arguments independent of the verdict? Ha) The frequency of powerless language by a male attorney is not independent of the verdict. Ho) The frequency of powerless language by a male attorney is independent of the verdict.

When the case has two male attorneys the male with the greater frequency of powerless language will be counted as committing an expectancy violation. The male with the lesser frequency will count as powerful language. The more powerless language that is spoken by a male the more of an expectancy violation that occurs and the more the justices will assign a negative valence to the attorney. In these instances, the justices will side with the male attorney who used less powerless language. In the instance of a female attorney and a male attorney the instances of powerless language will be counted. If the female attorney uses less powerless language than the male attorney, then she will be coded as using powerful language and the male attorney will be coded as using powerless language. The negative valence will be assigned to the female attorney. If the male attorney uses more powerless language than the female attorney, then the male attorney will be assigned a negative valence and the female attorney a positive valence. In the instance of two female attorneys, the instances of powerless language will be counted. The female who uses less powerless will be coded as committing an expectancy violation. The female who uses more powerless language will have a positive valence.

So, yes, to chi-square

Answer 1

I think you should use logistic regression with verdict as the dependent variable and sex of attorney and powerless language as independent variables.

First, you need to consider how to operationalize 'powerless language'. You say you have a frequency count, but it might be better to scale this by the amount of language. Trials last very different times, so perhaps your measure should be "powerless statements per hour" or some such. Call this variable PL (you can call it whatever you'd like).

All your hypotheses are about language of the defense attorney, which simplifies things a bit.

The next independent variable is sex of the defense attorney. Code this, e.g., 1 for female and 0 for male.

Suppose your dependent variable is labeled "V" and can be G or NG (guilty or not guilty).

Then your model is

P(G) ~ PL + S + PL*S

where ~ means "is related to"

Then you use logistic regression.

In R

m1 <- glm(V~PL + Sex + PL*Sex, family = 'binomial')
summary(m1)

In SAS

proc logistic data = mydata;
 class sex;
 model V = PL|Sex;
run;