Creating standard deviations with complicated data set

Hello,

I am trying to create standard deviations for a dataset of chat, which consists of lines of chat coded with 1 or 0 along a multitude of categories. For example, a chat line that talks about money will be coded 1 in the money column and 0 in the others. Each line has a player name associated with it, and the chat is organized into different 'phases'.

Now here is where it gets tricky. I want to be able to calculate the standard deviation of each player's mention of money, for example, within each phase. SO essentially comparing the average times money was mentioned versus each player's mention of money, but only in that phase. I am really struggling to be able to organize the data in a way that allows me to compare the data this way.

Any tips are greatly appreciated, and clarifying questions are encouraged!

Thank you so much for your time and advice!

Hey MarviP,

Thanks for answering. It is the variance of players' use of each speech act within each phase. So what I am essentially trying to do is compare the total number of mentions of money, for example, in each of the phases of the game to each player's individual mentioning of money within that same phase.

There will be as many measures of variance as there are averages and as many as there are phases, and each average will have a measure of variance that corresponds to it.

What I am really struggling with is how to gather such information efficiently, when I am looking at a long list of data listing seconds since start, player name, chat data, and the categories coded as 1 or 0.

Thanks so much for the help!