Crimaldi, Irene Convergence results for a normalized triangular array of symmetric random variables. Expositiones mathematicae, 20 (4). pp. 375-384. ISSN 0723-0869 (2002)Full text not available from this repository.
For a triangular array of symmetric random variables (without any integrability condition) we replace the classical assumption of row-wise independence by that of row-wise joint symmetry. Under this weaker assumption we prove some results concerning the convergence in distribution of a suitable sequence of randomly normalized sums to the standard normal distribution. Then we exhibit a class of row-wise independent triangular arrays for which the ordinary sums fail to converge in distribution, while our results enable us to affirm the convergence in distribution of the normalized sums.
|Subjects:||H Social Sciences > HA Statistics
Q Science > QA Mathematics
|Research Area:||Economics and Institutional Change|
|Depositing User:||Irene Crimaldi|
|Date Deposited:||31 Oct 2011 15:04|
|Last Modified:||03 Nov 2011 13:19|
Actions (login required)