Calibrating the zoom - a test of Zitt's hypothesis

Bibliometric indicators are widely used to compare performance between units operating in different fields of science. For cross-field comparisons, article citation rates have to be normalised to baseline values because citation practices vary between fields, in respect of timing and volume. Baseline citation values vary according to the level at which articles are aggregated (journal, sub-field, field). Consequently, the normalised citation performance of each research unit will depend on the level of aggregation, or 'zoom', that was used when the baselines were calculated. Here, we calculate the citation performance of UK research units for each of three levels of article-aggregation. We then compare this with the grade awarded to that unit by external peer review. We find that the correlation between average normalised citation impact and peerreviewed grade does indeed vary according to the selected level of zoom. The possibility that the level of 'zoom' will affect our assessment of relative impact is an important insight. The fact that more than one view and hence more than one interpretation of performance might exist would need to be taken into account in any evaluation methodology. This is likely to be a serious challenge unless a reference indicator is available and will generally require any evaluation to be carried out at multiple levels for a reflective review.