ACRL News Issue (B) of College & Research Libraries 3 2 2 / C&RL News Proportionate probability sampling By Margaret H aw thorn an d Elaine G oettler A technique to f i n d o u t the needs o f library users a n d nonusers T oday’s financial stringencies as well as good m anagem ent practice have forced aca­ dem ic libraries constantly to review services and make decisions as to w here retrenchm ent or, optimistically, expansion will take place. A sophisticated and com prehensive user survey o r needs assessment provides a solid starting point for the decision process.1 But w hen the question of updating user information arose at Erindale College, a satellite campus of the Uni­ versity o f Toronto, w e very much w anted to improve on previous survey efforts. Survey needs As in many other libraries, questionnaires had b een h an d ed out at the library door during sample time periods, surveying some of those students w ho entered the library but obtaining no information on students w ho were n o t li­ brary users. This time w e wanted: • To differentiate betw een nonusers w ho judged that they did not need the library and students w ho h ad found it unsatisfactory at some point and no longer used it for their li­ brary needs • To obtain a statistically valid survey of student library needs by major area of study to make sure w e w ere providing essential library resources in every case. • To gather an accurate student “vote” on possible library im provem ents, inform ation need ed by a recently constituted Student Li­ brary Enhancement Fund committee. • To m eet our requirements, w e decided to try a statistical approach borrow ed from so­ ciological survey research: the proportionate probability sample. Proportionate p ro b ab ility sam pling Proportionate probability sampling or propor­ tional allocation is a statistical approach w hich proves particularly useful for a survey of stu­ dent library use. Using this sampling technique involves obtaining student enrollment figures by subject area and by year from a registrar’s office and then apportioning a sample to match the distribution outlined. In our case, first a sam ple size of 550 representing 10% of college enrollment was selected. We then divided the sam ple into a group representing first-year stu­ dents (10% of 1,200) and a group representing upper-year students (10% o f 4,300). (Upper- year students have a greater range of courses available which may be taken in various se­ quences not necessarily restricted by year of study.) Next, individual classes in different subject areas w ere chosen to represent the proportion o f subject enrollm ent w ithin the tw o major groups representing year of study. For instance, if first-year English represented 25% of the first- year enrollment (1,200), then an English 101 class (or classes) totalling 30 students, or 25% of the first-year sample (120), w ould be selected to receive questionnaires. In this way, each sur­ veyed class was a sample of similar students throughout the college population. Q uestionnaire distribution A two-sided questionnaire sheet on library ser­ vices was designed, timed to take no more than five minutes to complete. The time frame and the com prehensibility of the questions w ere pretested using library student assistants. Then faculty teaching the “sam ple” classes w ere contacted and the project explained. In M argaret H aw thorn a n d Elaine Goettler are reference librarians a t Erindale College, University o f Toronto, Mississauga, Ontario Receive first class treatment at Ballen.. no matter w hat your size. W hether your order is for a thousand books or just one, w hether you are a prestigious university, medical school, or a little-known junior college, every Ballen customer receives our legendary one-to-one customized service. That means y o u ’ll have a personal Ballen customer service representative to answer questions, report status and solve problems. Y ou’ll have a specific location in our staging area for maximum quality control. Y ou’ll have instant access to important information through BallenNet™, our interactive on-line service for order entry data and current order status. Even direct telephone access to a Ballen corporate officer, if necessary. And despite our elephantine inventory o f over 100,000 titles, w ith thousands o f books shipped every w eek, our return rate squeaks in at less than 1% — the industry’s lowest. Find out h o w you can reap the big benefits o f Ballen’s personal service. Call Toll-Free (800) 645-5237 or Fax (516) 864-5850. . 3 2 4 /C&RL News most cases, permission w as given for use of the first five minutes o f class time to distribute and collect questionnaires. If not, another class was selected that fit the enrollment profile. Instructors w ere present and the response rate was close to 100%. Analysis a nd results The answers w ere coded on the questionnaire itself and analyzed using the Statistical Analy­ sis System program. Counting our respondents by year and major validated our use o f pro p o r­ tionate probability sampling. O ur sample cor­ responded very closely to the actual distribu­ tio n o f th e s tu d e n t p o p u la tio n , a lth o u g h part-time students w ere underrepresented, as they tend to cluster in certain classes rather than be random ly distributed across subject areas. W hy w e r e s o m e stu d en ts n o t u s in g th e library? C ollection inadequacies, too -sh o rt hours, and overcrow ded study space em erged as major reasons. Some subjects, of course, did not require library use. Even am ong those w ho did use the library frequently, over half replied that it did not fill all their library needs and a large p ercen tag e u se d o th e r university and public libraries as well. It was then op en to us to make the assum p­ tion that if the suggested im provements w ere m ade, if longer hours and more study space w ere provided and more books and journals purchased, more o f our students w ould use the library and use it more often. W ere th e re d ifferen ces in library n eed s a m o n g th e subject areas? Using a chi-square analysis, w e found that reported use of and n ee d for journals differed significantly, with almost 100% o f science students answering that journals w ere “very im portant” in a num ber of categories. Specialized reference handbooks and reports w ere rated as “im portant” by students in social sciences and humanities. Differences em erged in the use of docum ent delivery ser­ vices and, most interestingly, in reported use o f the library with science students using it significantly m ore often than those in th e h u ­ manities. We felt that w e had gained a clearer picture of the student b ody as library users o r n o n ­ users within subject areas. W hat lib rary im p r o v em en ts w o u ld be m o s t p o p u la r w it h stud en ts? More study space (87%), more reserve material (85%), more staff help (76%), more new books (78%), more journals (51%), and longer hours (61%) w ere am ong the most frequently checked. Students o n the Library Enhancement Fund Committee have been working on funding these improvements with some success since the survey was done. Conclusions O nce the sample classes had b een selected, the w ork involved in carrying out a propor­ tionate probability survey w as no greater than in previous, more conventional surveys that had b ee n done. With these results, however, we w ere able to press for budget improvements and to recom m end expenditures to the student co m m ittee b a s e d o n g rap h s in c o rp o ratin g collegewide information. Now that a num ber of the improvements so clearly requested have b een implemented (jour­ nal subscriptions have increased as has our m onograph budget, more study space is on the way, and hours have b een lengthened) w e an­ ticipate redoing the survey to ensure that the library is meeting the needs o f our current stu­ dent body. By using the proportionate probability sam­ pling technique outlined here, w e gathered accurate and powerful data from o ur library survey. The staff time and effort expended w ere more than justified by the range and the suc­ cess o f subsequent applications. Notes 1R obert C. N ew house, “A library essential: N eeds assessm ent,” Library Review (Glasgow, Scotland) 39 (February 1990): 33-36. ■ Share your opinion with C&RL News readers Do you feel strongly about a particular issue and w ant to share your thoughts with a w ider audience than just your colleagues dow n the hall? Now you have the opportu­ nity to share your thoughts with a national audience. C&RL News is looking for well-rea­ soned commentaries on issues of interest to academic and research librarians for its col­ umn, “The Way I See It.” Essays should be 750 to 1,000 w ords and should be sent to “The Way I See It,” C&RL News, ACRL, 50 E. H uron St., Chicago, IL 60611-2795; fax: (312) 280-7663; e-mail: U38398@UICVM.