• A key to innovation is the willingness of the senior managers pres­ent at the workshop to provide the necessary leadership and to follow through on the ideas discussed at the workshop.

• The Office of Management and Budget is responsible for providing leadership in eliminating bureaucratic barriers in contracting and recruitment.

• A system-wide marketing plan to academic institutions could stim­ulate academic work on federal statistical problems.

• Case studies of best practices could be useful in providing guid­ance on how to stimulate innovation.

• Communication within and between agencies could be improved.

• Progress in innovation needs to be measured periodically.

Edward Sondik followed Wallman’s overview with some ideas on next steps for the federal statistical system:

• Annual or biannual reports on key innovations and research could be developed and disseminated.

• Although he does not support a centralized research program, the federal statistical system could develop a joint federal statistics research agenda.

• The Interagency Committee on Statistical Policy (ICSP) could take the lead in developing a marketing program with academic institutions.

• The ICSP could provide leadership in establishing an innovation culture in the federal statistical system.

Thomas Louis stressed the importance of accountability and agreed with others on the importance of a periodic review and evaluation of statistical programs. He also made the general comment that it is important for at least a subset of the agencies to work on specific innovation projects while discussion proceeds on the larger issue of innovation in the federal statistical system. He stressed that he is not implying that innovation is not taking place, but perhaps the discussion today could lead to a different angle to implementing innovation projects. For example, he suggested looking at innovation in an existing area, like seasonal adjustment, that proceeds from databases to tables and figures with reasonably seamless connections. The project need not be a new procedure but an embodiment of many new changes. It is important for such a project to be examined by a variety of agencies to disseminate the lessons learned.

Lawrence Brown (University of Pennsylvania) asked Hermann Habermann (Committee on National Statistics), who was charged with writing the summary of the workshop, what he had heard. Habermann