Statistics History at UNL

While statistics courses had long been offered by the Department of Mathematics, prior to 1947 there had apparently been no effort made to develop statistics as a program of study. No one with statistics as a major interest had ever been, until 1947, a member of the mathematics faculty. In the meantime, statistics courses (mostly at the introductory levels with respect to content but varying widely with respect to course number levels) became available in other departments and colleges.

Shortly after World War II, an attempt was made to develop a viable program in statistics. In 1953, Robert Kozelka, with a Ph.D. in Statistics from Harvard University, joined the faculty and a year later, Fred Andrews, whose degree was from the University of California, Berkeley, came on a joint appointment with the College of Agriculture.

Within the Department, there was a surge of interest in advanced work in statistics. Early on, students were enrolled in the masters program with emphasis on statistics under the direction of Andrews. One of them, Donald Ylvisaker, went on to get a doctorate in statistics at another university.

Andrews, in particular, was interested in developing a strong statistics program. He did not like the split administrative setup with which he was faced, and steps were being taken to revamp it. A separate Department of Statistics was being considered in 1957 when Andrews resigned to accept a position at the University of Oregon. Kozelka also left shortly afterwards. An immediate effort was made to fill the empty positions, but the separate department plans were set aside. Also, the College of Agriculture withdrew its support of a joint approach and decided to develop its own statistics program within the Experimental Station. So Bernard Harris, a Ph.D. from Stanford, was appointed full time in the Department, and John Birch, who had a Ph.D. from the University of California, Berkeley, joined him in 1960. Both were eager to see the University develop a Department of Statistics, but the administration was now reluctant to undertake such a project. One reason for the reluctance was that the development of Computer Science and the Computer Center were underway.

Harris went on leave in 1963 and did not return, and Birch resigned in 1964. During the short period these two were in residence, they worked hard to develop interest in statistics. There were students involved in doctoral programs at the time they resigned, but for most of them, satisfactory arrangements were made to allow them to finish. Jagdish Srivastava, who came as a visiting Associate Professor in 1963 to fill in for Harris, remained and was the cushion for the shock of the two resignations. With Srivastava, the advanced work offered in the Department continued. In 1965, Lal Saxena, a Ph.D. in Statistics from Minnesota joined Srivastava in the department. A year or so later, Srivastava resigned to join a promising program at Colorado State University headed by Franklin Graybill. Ironically, Graybill was the alternate applicant for the position which Andrews filled. Srivastava, like Birch and Harris, kept his ties to the doctoral students who were working with him and saw to it that they finished.

The expanding areas of Actuarial Science and Computer Science along with the increased emphasis on statistics through the development of the Industrial Engineering Department made creation of other positions in Statistics possible and soon after Srivastava's departure, Yung Tong and Chong Park joined Saxena in the Department. Tong received his Ph.D. degree in Statistics from Minnesota, and Park was working with Harris, who was now at the University of Wisconsin.

Because now it was clear that there was and would continue to be a demand for statistical training at several levels and in various areas, the proposal to create a separate department was broached anew in 1968 to Dean Peter McGrath of the Arts and Sciences College. He agreed that the proposal had merit and a decision was made to create a School of Computational Sciences in the College with two academic departments, namely Statistics and Computer Science. The position vacated by Srivastava was to be filled with a person who would then, with the statisticians in residence in the mathematics department, work out the organizational details. On this basis a search was undertaken. The one to whom the position was tendered indicated he would accept provided a commitment of support for other positions and for some graduate students would be made. The university could not make such a commitment and the candidate withdrew. The administration then changed its mind and decided that the best alternative would be to recognize the existence of mathematical statistics as a program by changing the name of the Department of Mathematics to the Department of Mathematics and Statistics. It should be noted that the change was from the name "Department of Mathematics." The "and Astronomy" had been dropped in the mid-sixties when no replacement for Collins was made.

During the eighties and early nineties again, numerous efforts were made to form a Department of Statistics by combining the statistics faculty of the Department of Mathematics and Statistics with the Department of Biometry or with the faculty of the Department of Actuarial Science. Every time, for one reason or the other, these efforts did not succeed. During this time, or a bit later, Biometry started offering a master's degree program and actuarial science joined the Department of Finance in the Business College.

In the meantime, in the late eighties, the faculty of the Department of Mathematics and Statistics decided to elevate the status of the departmental statistics advisory committee, which consisted of all the statisticians in the Department, to that of a Division of Statistics with its director being an ex-officio member of the department Executive Committee. This helped to bring a little more visibility to the statistics program, but the Division has not been recognized as an entity by the administration beyond the departmental level in any formal way. Lal Saxena was the first director of the division and served in that position three years. Next, Dong-Ho Park served as director for a couple of years before deciding to accept a position in South Korea. Partha Lahiri became the director of the Division of Statistics in 1993 and has served as director since that time.

The last five years have seen two new efforts to strengthen statistics at UNL. One is the relationship with the Gallup Research Center and UNL's interests in survey research. Partha Lahiri is a member of the Advisory Board for the Gallup Research Center and in the fall of 1997 he organized a major conference in survey sampling with funding coming from a wide range of sources both inside the university and without. In addition, a number of statisticians have received research support as part of the Center. Thus, the growth of this Center seems to imply corresponding growth in the importance of statistics at UNL.

The other effort to strengthen statistics began with a task force appointed by Graduate Dean Merlin Lawson to consider how UNL should meet the need for graduate education in statistics. The primary recommendation was for the department to offer courtesy appointments to the graduate faculty in mathematics and statistics to qualified individuals whose expertise included statistics or mathematics. As a result of that recommendation, Allan McCutcheon, Director of the Gallup Research Center and a distinguished professor of sociology; Linda Young, a professor or Biometry; and Kent Eskridge, a professor of Biometry, were given courtesy appointments as members of the graduate faculty in mathematics and statistics. In addition, Dr. Robert Tortora, Vice President and Chief Methodologist of The Gallup Organization was made an adjunct professor in the department and was made a member of the graduate faculty. While it is not clear at this point whether this action will lead to growth in the graduate program in statistics, in the spring of 1998 Tortora taught a graduate statistics course in survey research that was taught on site at the Gallup Organization Headquarters.

Demand for statistics instruction at both the graduate and undergraduate level has grown since World War II, paralleling the growth in interest in statistics nationwide. The growth of statistics at UNL has been hampered both by its lack of visibility within a Department of Mathematics and Statistics and by the fact that the resources which support undergraduate instruction in statistics have been spread across so many departments.

Within the department there has been a steady production of students with masters degrees in statistics and fifteen students have received the Ph.D. degree. The first of these, Ernest Cobb, received his degree under Harris in 1965. Srivastava had two students finish in 1968 and one more finish in 1973 (with Jackson's assistance). The recent past has been the most productive with eight degrees between 1985 and 1997. Saxena, who retired in 1997 served as thesis advisor for four of those students.

Over the past three decades the number of tenure track faculty in statistics in the department has ranged from two to six. The rapid turnover of faculty at various times during this period has added to the difficulty in building the statistics program. In 1998, there were two statisticians on tenure track lines (Partha Lahiri and Dan Nettleton) and a search was underway to fill two additional lines. Hopefully, the demand for statistics instruction and the recent steps to link statistics to other programs on campus will make it possible to strengthen and stabilize the department's commitment to statistics.