I Casella Berger: Why is distribution of F-statistic in ANOVA not T^2

  • I
  • Thread starter Thread starter shaikh22ammar
  • Start date Start date
  • Tags Tags
    anova Distribution
AI Thread Summary
The discussion centers on the ANOVA statistic as defined in Casella & Berger, highlighting that the supremum of the T^2 statistic leads to an F-distribution rather than a T^2 distribution. The formula presented shows how the ANOVA statistic is derived from the pooled sample variance and treatment means. It is noted that while the term inside the square follows a t-distribution, the overall supremum results in an F-distribution with degrees of freedom (k-1, n-k). The relationship F = t^2 holds true only when there are two groups, emphasizing the unique behavior of the F-statistic in ANOVA. This distinction is crucial for understanding the distribution of the ANOVA statistic in statistical analysis.
shaikh22ammar
Messages
1
Reaction score
0
Theorem 11.2.8 in Casella & Berger defines the ANOVA statistic as a maxima of T^2 statistic as:
<br /> \sup_{\sum a_i = 0} T_a^2 = \sup_{\sum a_i = 0} \left( <br /> \left( S^2_p \sum a_i^2 / n_i \right)^{-1/2} \left( \sum a_i \bar Y_{i \cdot} - \sum a_i \theta_i\right)<br /> \right)^2 = \left( S^2_p \right)^{-1} \sum n_i \left( \bar Y_{i \cdot} - \bar{\bar Y} - \theta_i + \bar{\theta} \right)^2<br />
where all the summations are from 1 to k the no. of treatments and S^2_p, n_i, \theta_i, \bar Y_{i \cdot} are the pooled sample variance, no. of observations of treatment i, its mean, and sample mean respectively. The term inside the square between equals signs follows t distribution but for whatever reason the supremum of the square follows (k-1) F(k-1, n-k), as opposed to t^2.
 
Physics news on Phys.org
$$F = t^2$$
only when there are two groups.
 
Back
Top