+ Reply to Thread
Results 1 to 6 of 6

Thread: Standard Regression Analysis / urgent help for stats beginner.

  1. #1
    Points: 11, Level: 1
    Level completed: 21%, Points required for next Level: 39

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Standard Regression Analysis / urgent help for stats beginner.




    Hi Guys!

    I'm fairly new to statistics and am conducting a standard regression analysis with 1 predictor variable ( following from a pearsons correlational analysis in which only 1 of my 3 predictors appeared significant.)

    I have two questions;

    Do I report on both the t-value and f-value to show reliability?

    multiple r = 0.28 and adjusted r2 = 0.74 - would this be considered a weak association as only 7% of the variance can be accounted for?

    Thanks so much in advance for your help

    Alex

  2. #2
    Omega Contributor
    Points: 38,396, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,001
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Standard Regression Analysis / urgent help for stats beginner.

    Is this a typo, "r2 = 0.74", because it would be 74% variance explained?


    If you just ran a simple linear regression, reporting the F and T statistics may be a little redundant. So it depends on your purpose, but the beta coefficient may be the most informative.
    Stop cowardice, ban guns!

  3. #3
    Points: 11, Level: 1
    Level completed: 21%, Points required for next Level: 39

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Standard Regression Analysis / urgent help for stats beginner.

    Quote Originally Posted by hlsmith View Post
    Is this a typo, "r2 = 0.74", because it would be 74% variance explained?


    If you just ran a simple linear regression, reporting the F and T statistics may be a little redundant. So it depends on your purpose, but the beta coefficient may be the most informative.
    Apologies, .074! ive listed the table below..I am trying to asses trait anxiety as a predictor of mindfulness..

    Trait Anxiety regressed onto mindfulness
    B -.331 SE (B ) 0.96 Beta -.285 t -.344 p .001

    a = 65.024
    R = 0.28 , F(1, 134) = 11.85, P=.001)

    As far as I can see the model accounts for 7% variance and is shown to be sig. due to the F value. However, multiple r is only .28 which may suggest the correlation is weak - however, i'm not sure if this is an appropriate application of the multiple r in this case.

    I am citing t-value (.344 with an associated probability of .001) to illustrate that the regression coefficient unlikely to have arisen by sampling error.

    This is the first time i have attempted a regression analysis so I'm slightly worried I'm interpreting the results incorrectly.

    Thanks for your reply, any help is greatly appreciated.

  4. #4
    Omega Contributor
    Points: 38,396, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,001
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Standard Regression Analysis / urgent help for stats beginner.

    Yeah, your interpretations are pretty much right.


    multiple r = R^2, just call it r-squared not multiple r, which is confusing.


    What questions do you have?
    Stop cowardice, ban guns!

  5. #5
    Points: 11, Level: 1
    Level completed: 21%, Points required for next Level: 39

    Posts
    3
    Thanks
    0
    Thanked 0 Times in 0 Posts

    Re: Standard Regression Analysis / urgent help for stats beginner.

    Quote Originally Posted by hlsmith View Post
    Yeah, your interpretations are pretty much right.


    multiple r = R^2, just call it r-squared not multiple r, which is confusing.


    What questions do you have?
    thanks for the reply, my question is about r2 signifying a weak association between trait anxiety and mindfulness. is it correct to look at the R2 value as an indication of the effect size and say TA has a weak association with mindfulness, or does it not matter because the results have shown to be statistically significant and it is irrelevant whether r2 is strong, weak or moderate?

  6. #6
    Omega Contributor
    Points: 38,396, Level: 100
    Level completed: 0%, Points required for next Level: 0
    hlsmith's Avatar
    Location
    Not Ames, IA
    Posts
    7,001
    Thanks
    398
    Thanked 1,186 Times in 1,147 Posts

    Re: Standard Regression Analysis / urgent help for stats beginner.


    The R^2 statistic is contextual, meaning 7% could be huge for someone in social sciences and pitiful for a physicist. We can't interpret it for you. I would slap confidence intervals on it to better convey it's precision. It along with the beta coefficient provide a more robust depiction of the X and Y relationship.
    Stop cowardice, ban guns!

+ Reply to Thread

           




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