Refer to the model for the randomized block design with
Chapter 13, Problem 90SE(choose chapter or problem)
Refer to the model for the randomized block design with random block effect given in Exercise
a Give the expected value and variance of \(Y_{i j}\).
b Let \(\bar{Y}_{i *}\) denote the average of all of the responses to treatment . Use the model for the randomized block design to derive \(E\left(\bar{Y}_{i *}\right)\) and \(V\left(\bar{Y}_{i *}\right)\) Is \(\overline{Y_{i}}\) an unbiased estimator for the mean response to treatment ? Why or why not? Notice that \(\left(\bar{Y}_{i *}\right)\) depends on and both \(\sigma_{\beta}^{2}\) and \(\sigma_{\varepsilon}^{2}\).
c Consider \(\bar{Y}_{i *}-\bar{Y}_{i^{\prime}}\), for \(i \neq i\) Show that \(E\left(Y_{i *}-Y_{i^{\prime} *}\right)=\boldsymbol{\tau}_{i}-\boldsymbol{\tau}_{i^{\prime}}\) This result implies that
, is an unbiased estimator of the difference in the effects of treatments and
d Derive \(V\left(\bar{Y}_{i *}-\bar{Y}_{i *}\right)\) Notice that \(V\left(\bar{Y}_{i *}-\bar{Y}_{i *}\right)\) depends only on and \(\sigma_{\varepsilon}^{2}\).
Equation transcription:
Text transcription:
Y{i j}
bar{Y}{i *}
E(\bar{Y}{i *})
V(bar{Y}{i *})
overline{Y{i}}
(\bar{Y}{i *})
sigma{beta}^{2}
sigma{varepsilon}^{2}
bar{Y}{i *}-bar{Y}{i^{\prime}}
i neq i
E(Y{i *}-Y{i^{prime} *})=boldsymbol{tau}{i}-boldsymbol{tau}{i^{\prime}}
V(bar{Y}{i *}-\bar{Y}{i *})
Unfortunately, we don't have that question answered yet. But you can get it answered in just 5 hours by Logging in or Becoming a subscriber.
Becoming a subscriber
Or look for another answer