Posted on Monday, 2nd April 2012

Please read Chapter14-APR2.pdf and post a comment.

Posted in Class | Comments (12)

  1. Eric VanEpps Says:
    April 2nd, 2012 at 10:10 am

    On page 446, you refer to results being given in terms of “deviance”, but never really explain the interpretation of deviance as a term. What exactly are “null deviance” and “residual deviance”?

  2. Amanda Markey Says:
    April 2nd, 2012 at 6:10 pm

    Despite 14.1.1, I’m still unclear on the interpretation of log odds coefficients (“we must pick a particular probability p and conclude
    that a unit increase in x is associated with an increase from p to expit…”)

  3. Sharlene Flesher Says:
    April 2nd, 2012 at 10:07 pm

    In 14.2.2 you mention how it is helpful to have good starting values and reparameterize in solving nonlinear least squares problems- can this always be done or are there often cases that don’t have intuitive starting points and can’t easily be reparameterized?

  4. David Zhou Says:
    April 2nd, 2012 at 10:20 pm

    Can you give some very broad guidelines for choosing starting values for nonlinear least-squares problems?

  5. Shubham Debnath Says:
    April 2nd, 2012 at 10:50 pm

    As I was reading I was wondering about reparameterization, so I’m glad that was the last section. How much does the initial value of the parameters affect the iterative procedure? How often will it not converge to a desired answer?

  6. Matt Panico Says:
    April 3rd, 2012 at 1:37 am

    Is there any situation in which the GLM link function would not be in the exponential family?

  7. Ben Dichter Says:
    April 3rd, 2012 at 1:51 am

    Why is the condition of independence between variables so important for regression?

  8. Yijuan Du Says:
    April 3rd, 2012 at 6:46 am

    I think it may be better to give an example showing in the picture if the data follow other distribution, using the ordinary linear model may result in a big departure.

  9. Rob Rasmussen Says:
    April 3rd, 2012 at 8:07 am

    Could you go over more in class the method for calculating the Poisson regression?
    Also, why is the typical link function for Poisson regression the log function?

  10. Noah Says:
    April 3rd, 2012 at 8:09 am

    What is it about the link functions that make them typically concave which makes loglikelihood maximization easy?

  11. Rich Truncellito Says:
    April 3rd, 2012 at 8:22 am

    In modern regression models, the representation of noise or the error term isn’t explicitly stated as it is in linear regression models. To be clear, is this implied status of the error term in modern regression models so that the noise may take on other, nonlinear relationships to the deterministic parts of the models?

  12. Rex Tien Says:
    April 3rd, 2012 at 8:24 am

    Could you explain a bit more about the concept of deviance and null deviance to get a more intuitive understanding of these measures?

Leave a Reply

You must be logged in to post a comment.