+ Reply to Thread
Results 1 to 4 of 4

Thread: Need help on deciding the analysis tests

  1. #1
    Points: 4,720, Level: 43
    Level completed: 85%, Points required for next Level: 30

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Question Need help on deciding the analysis tests




    Hello every one,

    I am doing research in social science. i have following issue for which I need advise:

    1. My sample is a snowball sample and thus non probability sample.
    2. Sample size is 10
    3. There are three major variables in my research; out of which 2 are independent and one is dependent on the other two.
    4. Each independent variable comprises of 15-30 measurement items
    5. Dependent variable is composed of measurement items.

    Which statistical analysis technique (s) shall I apply to get the following:

    a. To see how each independent variable relate to dependent variable?
    b. How independent variables interact to relate with dependent variable?
    c. Which one of the two independent variable is more important in relationship with dependent variable?

    Any advise is gratefully welcome.

    AJ

  2. #2
    TS Contributor
    Points: 17,636, Level: 84
    Level completed: 58%, Points required for next Level: 214
    JohnM's Avatar
    Posts
    1,948
    Thanks
    0
    Thanked 6 Times in 5 Posts
    Multiple linear regression will answer all of your research questions.

    Here's a link that goes into more detail:

    http://www2.chass.ncsu.edu/garson/pa765/regress.htm

  3. #3
    Points: 4,720, Level: 43
    Level completed: 85%, Points required for next Level: 30

    Posts
    2
    Thanks
    0
    Thanked 0 Times in 0 Posts

    i looked at the site but it says

    Hello,

    Thanks for reply. I looked at the site you mentioned but it says that for multiple regression atleast 40 is sample size required. My sample size is only 10 so what to do now?

    look for your reply
    AJ

  4. #4
    TS Contributor
    Points: 17,636, Level: 84
    Level completed: 58%, Points required for next Level: 214
    JohnM's Avatar
    Posts
    1,948
    Thanks
    0
    Thanked 6 Times in 5 Posts

    You can still do multiple regression, but you may not have enough samples to detect any significant effects.....you may simply need to collect more data so that you can draw some valid conclusions.

+ Reply to Thread

           




Similar Threads

  1. Statistical analysis tests
    By nursepattyb in forum Statistics
    Replies: 4
    Last Post: 11-21-2010, 07:21 PM
  2. urgent - Help deciding on statistics
    By ckyphil in forum Psychology Statistics
    Replies: 3
    Last Post: 01-14-2009, 11:02 PM
  3. Help needed on deciding which stats to use.
    By miss60sg in forum Psychology Statistics
    Replies: 2
    Last Post: 01-09-2009, 10:54 AM
  4. Survey analysis help: what tests to run?
    By Noraft in forum Statistical Research
    Replies: 2
    Last Post: 11-19-2008, 05:28 AM
  5. Deciding which distribution to choose?
    By pst in forum Statistics
    Replies: 0
    Last Post: 12-05-2007, 09:03 AM

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts






Advertise on Talk Stats