Elusive evidence 2

In the "for and against" rankings a few weeks ago ("Debate reignited by new league tables", August 17), you omitted one of the most telling factors against, which is again relevant in the students satisfaction ratings ("Students: yes, we're satisfied", September 14).

Academics are teaching students the crucial need for a careful and correct statistical analysis of results to determine whether two groups of results are significantly different. Yet here we have another example of major conclusions being drawn from a list of averages with no statistical comment. No fewer than 49 institutions fall between 3.90 and 3.80. One might be forgiven for thinking that Staffordshire (34) is a much better place than Strathclyde (50), whereas their scores are 3.88 and 3.86 respectively.

I strongly suspect that, with the possible exception of the top few, there is no statistically significant difference between any of the institutions in the entire list.

Trevor Stone
Glasgow University