NotesFAQContact Us
Search Tips
ERIC Number: ED049278
Record Type: RIE
Publication Date: 1971-Feb
Pages: 23
Abstractor: N/A
Reference Count: 0
Violation of Homogeneity of Variance Assumption in the Integrated Moving Averages Time Series Model.
Gullickson, Arlen R.; And Others
This study is an analysis of the robustness of the Box-Tiao integrated moving averages model for analysis of time series quasi experiments. One of the assumptions underlying the Box-Tiao model is that all N values of alpha subscript t come from the same population which has a variance sigma squared. The robustness was studied only in terms of homogeneity of variance. The variances of the alpha subscript t values of n subscript l observations before the treatment event T and the variances of the alpha subscript t values for the n subscript 2 observations after event T were systematically varied so as to simulate realistic conditions under which the variances of the alpha subscript t would be heterogeneous. The actual percent of t-ratios exceeding 1-alpha superscript t N-2 for these cases was found when the null hypothesis was true. The results of this empirical study were then compared with the percent of t-ratios exceeding 1-alpha superscript t N-2 values for the null hypothesis with homogeneous variances. The trends visible from the results lead to the conclusion that if possible heterogeneity of error variance is suspected then conservative nominal significance levels should be set if the IMA model is to be used in determining the effect of a treatment. (Author)
Publication Type: N/A
Education Level: N/A
Audience: N/A
Language: N/A
Sponsor: N/A
Authoring Institution: N/A
Identifiers: Time Series Experiments
Note: Paper presented at the Annual Meeting of the American Educational Research Association, New York, New York, February 1971