Question

How do I figure out if the respondents in my data set agree or not? The most used measure is standard deviation, but I'm in doubt whether I can do that when my index variables are scale (consist of answers to a number of questions). My question is how do I measure the dispersion in order to figure out whether the population agree when I have a scale variable?

Answer 1

# Question #10258

How do I figure out if the respondents in my data set agree or not? The most used measure is standard deviation, but I'm in doubt whether I can do that when my index variables are scale (consist of answers to a number of questions). My question is how do I measure the dispersion in order to figure out whether the population agree when I have a scale variable?

Solution. Yes, you can use something like ANOVA. Here, if the questions $(q_1^n,\ldots ,q_m^n)_{n = 1,N}$ where $m$ is the number of questions, $N$ is the number of people, in your list can be treated as independent and $a_{i}$, $i = 1,m$ are scale variables, then you are to calculate the variance of the sample $(q_i^n /\sqrt{a_i})_{n = 1,N}$ for each $i = 1,m$ and use a method you want.

Answer provided by AssignmentExpert.com