First published in 1931, this book is the second edition of a 1917 original. The text provides an account of the method of least squares, aiming to obtain the best interpretation of the results of experiment without consideration of the way in which these results are obtained. Elaborate descriptions of instruments and experimental methods are avoided, allowing for a concise and economical account that concentrates on key elements of the subject. This is a detailed and well-organized book that will be of value to anyone with an interest in least squares and the development of mathematics.