Triangulation is proposed by many nurse researchers as a means of solving the quantitative/qualitative debate and integrating the two approaches. While this view is accurate, it does not take into account the possible complexity and usefulness of triangulation, nor does it fully recognize the two goals of triangulation: confirmation and completeness of data. In this paper the five types of triangulation (data, investigator, theoretical, methodological, and unit of analysis) are described and the advantages and disadvantages of using this method are discussed. It is argued that the view that triangulation is merely the combination of different methods of investigation is a narrow one, and it is recommended that nurse researchers increase their utilization of the four less frequently used types of triangulation: data, investigator, theoretical and unit of analysis. When using triangulation of methods, researchers should also consider whether the use of within-method triangulation would be beneficial to their study. Sequential use of quantitative and qualitative methods to develop and refine tools of enquiry may also be more effective for certain studies than the more usual simultaneous use. The 'triangulation state of mind', the conscious employment of multiple data sources and methods to cross-check and validate findings continuously, should permeate all studies and lead to the goal of confirmation. Above all, triangulation must be chosen deliberately, for the correct reasons, and an adequate description of the rationale, planning and implementation of procedures should be given in reports, to give credence to this emerging method of research.