in linear models, the error varianceσ2 of random errors is usually estimat-ted by the residual sum of squares (divided by a su ita ble degree of free-dom), based on the first n observation, (denote it by σn2). it is well known t that under certain conditions, the distribution of this estimate, when standardised, converges to the standard normal distribution. In this paper, it is shown that |Gn(x)-Ф(x)|=O(n-δ/2(1+|x|)-(2+δ)). when the errors are indepedent (maynot be identically distributed) and their 4 + 2δ order moments exist, where Gn(x) is the distribution of (σn2-σ2/(varσn2)1/2,Ф(x)=1/(2π)1/2∫-∞xe-r2/2dt. |