Abstract

Abstract There are of course inevitable errors in these estimates which caution us against taking differences, especially small differences, at face value. The ‘noise’ surrounding estimates for a party at two consecutive elections may produce an impression of movement, whereas in fact no real change has actually taken place. Our estimates for error, already presented for Left-Right scores in our previous book (Budge et al. 2001: 139) and in Chapters 4 and 5, indicate however that it is limited to about 10 per cent of variation. While confidence intervals can be formed around each individual score on this basis the figure indicates more generally that estimates can be taken broadly at face value as indicating real change and movement in policy positions.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call