Comments on: Thurs Apr 12 http://www.stat.cmu.edu/~kass/smnp/?p=121 Thu, 26 Apr 2012 14:07:02 +0000 hourly 1 http://wordpress.org/?v=3.0.4 By: Thomas Kraynak http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-310 Thomas Kraynak Thu, 12 Apr 2012 13:29:46 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-310 Could you go over how you formulate the sample ACF? Could you go over how you formulate the sample ACF?

]]> By: Matt Bauman http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-309 Matt Bauman Thu, 12 Apr 2012 13:23:13 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-309 I've heard some forms of AR(p) models being referred to as Wiener Cascades or Wiener Filters -- are there any differences between these three terms? Or are they just synonyms? I’ve heard some forms of AR(p) models being referred to as Wiener Cascades or Wiener Filters — are there any differences between these three terms? Or are they just synonyms?

]]> By: Rob Rasmussen http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-308 Rob Rasmussen Thu, 12 Apr 2012 13:01:26 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-308 Could you explain more about the difference between ACF and PACF? Could you explain more about the difference between ACF and PACF?

]]> By: Rich Truncellito http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-307 Rich Truncellito Thu, 12 Apr 2012 12:26:53 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-307 In describing the autocovariance function on p. 512, you define h = t - s. Does this definition of h also apply to the h in the description of "strictly stationary" on the previous page? In other words, does the number of elements in each set of variables {Xt, Xt+1,..., Xt+h} and {Xs, Xs+1,..., Xs+h} have to agree with h = t - s? In describing the autocovariance function on p. 512, you define h = t – s. Does this definition of h also apply to the h in the description of “strictly stationary” on the previous page? In other words, does the number of elements in each set of variables {Xt, Xt+1,…, Xt+h} and {Xs, Xs+1,…, Xs+h} have to agree with h = t – s?

]]> By: Yijuan Du http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-306 Yijuan Du Thu, 12 Apr 2012 11:38:16 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-306 I don't quite understand, in the example of EEG and EPSC, 'the time scale their variation occurs', compared to observation interval.. I don’t quite understand, in the example of EEG and EPSC, ‘the time scale their variation occurs’, compared to observation interval..

]]> By: Amanda Markey http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-305 Amanda Markey Thu, 12 Apr 2012 10:24:46 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-305 You say, "many physical phenomena may be described by applying this technique". What are more of these? You say, “many physical phenomena may be described by applying this technique”. What are more of these?

]]> By: David Zhou http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-304 David Zhou Thu, 12 Apr 2012 08:13:30 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-304 I'm not clear about the utility of spectral analysis - you mention it but it doesn't seem to factor into autocorrelation analysis - is it more important for Fourier analysis (which we skipped)? I’m not clear about the utility of spectral analysis – you mention it but it doesn’t seem to factor into autocorrelation analysis – is it more important for Fourier analysis (which we skipped)?

]]> By: Jay Scott http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-303 Jay Scott Thu, 12 Apr 2012 05:15:37 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-303 I do not understand the generalization of 18.26 to 18.27: X_t = phi*X_(t-1) + W_y to X_t = Summation i=1 to p of [phi_i*X_(t-i) + W_y]. or how the magnitude of phi determines causality(pp527-8). I do not understand the generalization of 18.26 to 18.27:

X_t = phi*X_(t-1) + W_y
to
X_t = Summation i=1 to p of [phi_i*X_(t-i) + W_y].

or how the magnitude of phi determines causality(pp527-8).

]]> By: Rex Tien http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-302 Rex Tien Thu, 12 Apr 2012 04:05:29 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-302 You mention that harmonics can often be fitted with the form omega_2 = k*omega_1, where k is an integer. Could we also use fractional k values? Is there some mathematical reason why harmonics with integer k's should improve the fit? You mention that harmonics can often be fitted with the form omega_2 = k*omega_1, where k is an integer. Could we also use fractional k values? Is there some mathematical reason why harmonics with integer k’s should improve the fit?

]]> By: Ben Dichter http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-301 Ben Dichter Thu, 12 Apr 2012 03:25:11 +0000 http://www.stat.cmu.edu/~kass/smnp/?p=121#comment-301 Could you go through the math in the autocorrelation illustration? Could you go through the math in the autocorrelation illustration?

]]>