Advertisement
If you have a new account but are having problems posting or verifying your account, please email us on hello@boards.ie for help. Thanks :)
Hello all! Please ensure that you are posting a new thread or question in the appropriate forum. The Feedback forum is overwhelmed with questions that are having to be moved elsewhere. If you need help to verify your account contact hello@boards.ie

Conventional way to report findings

Options
  • 04-08-2010 3:41pm
    #1
    Kurtosis
    Registered Users Posts: 2,881 ✭✭✭


    I've been using SPSS to analyse data from surveys as part of a project and I've come to writing up a report of my findings. I was wondering is there anywhere I could find a guide on the most appropriate way to represent the variables I have or is it a case that I should represent all scale variables the same way, and the same for nominal and ordinal parameters? For example I have an age variable, but apart from a mean value, should I include the median, standard deviation, min and max values or all of the above? Sorry if this is oversimplifying matters, I'm pretty inexperienced with stats!


Comments

  • Options
    #2
    Ostrom
    Registered Users Posts: 3,483 ✭✭✭Ostrom


    Depends on what you are reporting; what kind of questions are you addressing? Whats your subject? Are you just summarizing the variables or doing anything more advanced?


  • Options
    #3
    Time Magazine
    Registered Users Posts: 8,452 ✭✭✭Time Magazine


    penguin88 wrote: »
    For example I have an age variable, but apart from a mean value, should I include the median, standard deviation, min and max values or all of the above? Sorry if this is oversimplifying matters, I'm pretty inexperienced with stats!

    As efla says, it depends on a lot of things. For summaries, I like histograms. For regressions, you should include coefficients, t-stats and p-values.

    Also, you should think about including just about everything in an appendix. That way you can reserve the cool stuff for the main body of the text.


  • Options
    #4
    Kurtosis
    Registered Users Posts: 2,881 ✭✭✭Kurtosis


    efla wrote: »
    Depends on what you are reporting; what kind of questions are you addressing? Whats your subject? Are you just summarizing the variables or doing anything more advanced?
    Time Magazine wrote: »
    As efla says, it depends on a lot of things. For summaries, I like histograms. For regressions, you should include coefficients, t-stats and p-values.

    Also, you should think about including just about everything in an appendix. That way you can reserve the cool stuff for the main body of the text.

    Thanks for the replies! I got to talk to the researcher I'm working with and it is just the basic summary of the variables that they want from me. It's data on a service, so there are customer details, a few lifestyle scale-type questions or yes/no question and then information on how many times they used the service. I may have to compare the customers that completed the full service with those who didn't, but shouldn't have to worry about that for a while.

    And cheers for the tip on the appendix Time Magazine, I just wish I had cool stuff for the main body of the report :pac:


Advertisement