LOWER BOUNDS FOR THE CHI-SQUARE QUANTILES
In some statistical considerations lower bounds for the chi-square quantiles seem to be as useful as the upper ones. For example, both lower and upper bounds were used by Brain and Mi [2] to prove some properties of confidence bounds for the maximum likelihood estimators. However, it turns out that it is hard to find in the literature sufficiently accurate lower bounds for u(α, k) in the case when α tends to zero and simultaneously k increases. As was said previously, some results were obtained, among others, in Lemma 3 of Inglot and Ledwina [4]. A global lower bound which may be considered as a counterpart of the Laurent and Mas- sart upper bound was proposed in (4) of Lemma 3 in [4]. Using (3.2) it can be significantly improved. The corresponding result is stated in the next propositio