Two techniques for determining a straight line fit to data are compared. This article reviews two simple techniques for fitting a straight line to a set of data, namely the method of averages and the method of least squares. These methods are compared by showing the results of a simple analysis, together with a number of tests based on randomized data, and it is concluded that the methods give similar results. An example is also included from chemistry showing that these two methods give estimates which are within the normal range for experimental errors. It is not the intention of this note to suggest one method in favour of the other, but to provide evidence on which an informed choice can be made. This material is aimed at educators who currently use least squares at a basic level with their students, particularly in science and engineering at high school and first year university. It is not intended to address problems which require higher level statistics or more sophisticated techniques that would be beyond such students. A typical problem of this kind is that of outliers, and we briefly discuss this aspect.