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

Stuck on a statistics question in SPSS: Help!

Options
  • 03-11-2011 4:11pm
    #1
    parc
    Registered Users Posts: 787 ✭✭✭


    In relation to "Coefficients" table when doing regression analysis

    Question:
    How are the two coefficients (Slope and offset) statistically significant?

    I kind of know what Slope is, but have no clue what offset is? Once again the lecturer makes no mention of offset in the notes and can't find anything online


Comments

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


    parc wrote: »
    In relation to "Coefficients" table when doing regression analysis

    Question:
    How are the two coefficients (Slope and offset) statistically significant?

    I kind of know what Slope is, but have no clue what offset is? Once again the lecturer makes no mention of offset in the notes and can't find anything online

    I think by offset you mean intercept (this is how it is typically referred to in texts). In relation to the line equation (y=a+bx), a (alpha) is the value at which your regression line cuts the y-axis (-3.281). The slope, beta is given in the output (1.288). Your predictor (slope) coefficient is statistically significant (.027) which is basically a t-test against a coefficient value of 0.

    Generally a non-significant intercept (yours is not, sig = .839) isn't too problematic, but it depends on what you are doing with the model / type of data etc.

    Also, the value under beta is quite important. This is the standardised coefficient which tells you the resultant standard deviation increase in the outcome per standard deviation increase in the predictor. This allows you to compare effect sizes across models with different data and should also be reported.


Advertisement