Research Advances in Agricultural Statistics

1997 Renewal

I. NCR 170: RESEARCH ADVANCES IN AGRICULTURAL STATISTICS

II. Duration: October 1, 1997 through September 30, 2002

III. Justification

Statisticians who consult and do research in an Agricultural Experiment Station environment have a unique relationship with the University. Their multi-disciplinary, collaborative role is generally more extensive than that of other faculty within the University. This increased level of collaboration allows Land Grant institutions, through the use of Experiment Station statisticians, to perform their agricultural research missions more effectively and efficiently than would otherwise be possible.

As State and Federal appropriations continue to fall short of funding levels needed for research and grants become more competitive, it becomes even more imperative that research dollars go as far as possible. This requires Experiment Station statisticians to keep abreast of the latest statistical research as well as work to develop methodology appropriate to their consulting roles. With the increased availability of computers, a plethora of new computationally intensive statistical methods and relevant software have become available.

Never has the charge to remain current in the statistical profession been more challenging. Assessing the utility of the new statistical methods and software is increasingly important. Further, dissemination of the information to agricultural researchers must be made in a timely manner. Thus, it is useful for Station statisticians to work cooperatively to determine the best current approaches to common statistical problems and to help direct future directions of statistical research and software development.

In this respect, Experiment Station statisticians can work together to provide more effective assistance to the agricultural researchers of their respective states. An NCR committee can play an extremely important role by serving as a focal point for the development and implementation of sound statistical practice. The members of NCR-170 are committed to this purpose.

IV. General and Specific Objectives

A. Committee objectives

  1. To identify, foster, and coordinate cooperative research efforts among statisticians serving food and agriculture research programs.

  2. To explore current as well as anticipated statistical problems of mutual interest in food and agriculture research and seek solutions for these problems.

B. Specific goals for next five years

  1. Improve the statistical methodology used by researchers conducting on-farm trials.

  2. Facilitate more rapid transfer of new statistical methodology, especially linear mixed models, to Experiment Station statisticians and to agricultural researchers.

V. State and Active Participants E. Gbur (AR) B. Shafii (ID) S. Aref (IL) W. Nyquist (IN) P. Hinz (IA) G. Milliken (KS) P. Cornelius (KY) R. Tempelman (MI) G. Krause (MO) L. Young (NE) M. Payton (OK) P. Evenson (SD) D. Sisson (UT) J. Alldredge (WA) E. Nordheim (WI) G. Richardson (USDA, CO) D. Holt (Admin. Advisor, IL) J. Meadows (CSREES) In addition to the above list of active official state representatives, approximately 15 other statisticians have expressed an interest in continuing their past active participation in the Committee’s projects. This list includes the following individuals. T. Bailey (IA) D. Bullock (IL) T. Nelsen (USDA, IL) D. Johnson (KS) L. Douglass (MD) K. Eskridge (NE) S. Kachman (NE) D. Marx (NE) A. Parkhurst (NE) W. Stroup (NE) J. Holman (OH) B. Yandell (WI) D. Kratzer (UpJohn Co.) J. Gill (MI ) L. Tucker (SD) VI. Highlights of Activities and Accomplishments Since Last Approval. A one-day workshop on the design and analysis of on-farm trials was conducted in conjunction with the NCR committee meeting in July, 1994, in Madison, WI. Participants included representatives from agronomy, animal science, and rural sociology. It became clear through this workshop that several different user groups need access to this information, and a single workshop format would probably not be successful. Alternative methods of approaching dissemination of on-farm trials were investigated.

An annotated bibliography of the design and analysis of on-farm trials is being developed and will be placed on a web site. A short summary of content and a critique of the material is available for each reference. A format for answering questions related to on-farm trials is also being developed for the web. Since these are being developed during Fall, 1996, it is too early to measure their success. However, because it is such an active area of interest for most land grant institutions, the interest is expected to be high. A manual relating to on-farm trials is also being planned by committed members.

During July, 1995, the committee met with the University Statisticians at Southern Experiment Stations (USSES/SRIEG-13) in Fort Collins, CO. Focus groups concentrated on generalized linear models, mixed model analysis, spatial statistics, and categorical and non-normal data. Reports were given by each group followed by extensive discussion on the potential applications within land-grant institutions.

Generalized linear models was the focus of the committee’s meeting in July, 1996. At this time, it was decided that the software needed for extensive implementation of these newer statistical methods was not available. Extension dialogue was exchanged with a SAS representative about the additions to the procedure GENMOD that would be needed before it would receive wide implementation within Experiment Stations. Further, it was determined that the software was available for the implementation of linear mixed models. However, the need to update both Experiment Station statisticians and agricultural researchers on these methods was apparent. Therefore, a committee, chaired jointly by George Milliken (KS) and Larry Douglass (MD) was assigned the task of developing a workshop for researchers to be presented at the committee’s meeting in July, 1996. The workshop would then be presented in various forums within the statistical community and to interested groups of researchers.

The committee has continued an active interest in the Journal of Agricultural, Biological, and Environmental Statistics (JABES). Dallas E. Johnson, an active participant in committee activities, is the founding editor. Other committee members serve as associate editors and on the journal management committee for JABES. Because the emphasis of the journal is on statistical approaches to solving real-world problems, the journal has been, and is expected to continue to be, extremely useful to experiment station statisticians and to statistically-literate researchers.

VII. Recommendation of Appropriate NCA Committees VIII. Required signatures


Committee Chair


Administrative Advisor