Statistics remains an integral part of baccalaureate and graduate nursing education. It is suggested that statistics continues to be incorporated into the nursing curriculum. Specifically, the American Association of Colleges of Nursing (AACN) Essentials of Baccalaureate Education for Professional Nursing Practice (2008) requires baccalaureate education to provide the student with a basic understanding of how evidence is developed. This includes the research process as it is applied to clinical nursing practice, and recommended sample content includes qualitative and quantitative research processes, as well as basic applied statistics. The Institute of Medicine (2010) also has recommended better evidence in measuring the quality of health care. Patient databases of clinical information are critical to evaluating care processes and outcomes and may play a vital role in measuring quality (Aktan, Fagan, & Sorkin, 2012; High-Value Health Care Project, 2010).
Further, master’s-prepared nurses must become proficient in the evaluation of research findings and the development and implementation of evidence-based practice guidelines, which include basic statistical analysis as a component of the research process (AACN, 2006). Recent changes in graduate nursing education and advanced practice nursing certification requirements have resulted in modifications to or elimination of the master’s thesis in many graduate nursing programs (DiMaria-Ghalili & Ostrow, 2009). When the master’s thesis is eliminated, there is less incentive for students to learn to use statistics, resulting in students who are less prepared to interpret evidence. These changes and the resultant recommendations promote and encourage further inquiry on the continued integration of statistics into nursing education.
Many reasons exist as to why this curricular shift in nursing education has occurred. First, research requires an understanding of statistics. However, it has been reported that, at times, nursing students’ attitudes toward statistics can be a factor influencing the mastery of important concepts (Ashcroft, 2006). When faculty repeatedly encounter student resistance to learning statistics, there is a disincentive to emphasizing it in the curriculum. Second, nursing students can recite definitions of mean, median, mode, and standard deviation; yet, they lack the ability to integrate statistical concepts (Ashcroft, 2006). Finally, barriers to learning are present. These may include unfamiliar statistical language and nonstimulating teaching methods in an area where innovative modalities are integral to a successful learning environment (Niven, Roy, Schaefer, Gasquoine, & Ward, 2013; Taylor & Muncer, 2000).
The need to incorporate the teaching of statistics in nursing education has been an ongoing issue (Taylor & Muncer, 2000; Zellner, Boerst, & Tabb, 2007). Many educators believe that learning statistics is essential for evidence-based practice. For example, Taylor and Muncer (2000) stated that the skill of reading and interpreting research reports is vital to the nursing profession and contributes to the development of a sound basis for nursing intervention. Zellner et al. (2007) identified 10 primary statistics used in nursing research and recommended that those statistics be used in undergraduate nursing education for advancement in nursing research. Therefore, it is essential to the discipline that nurse researchers understand students’ attitudes toward statistics to facilitate the development and implementation of a curriculum that will effectively address student needs and foster understanding of statistical and related concepts. Thus, the nurse academic is led to conclude that statistics, although an integral part of nursing education, presents ongoing challenges.
The aim of this study was to explore whether there is a difference in overall attitude toward statistics among undergraduate and graduate nursing and non-nursing majors and whether a variety of demographic variables are related to student attitudes. The first hypothesis to be addressed is, Does a difference exist in student attitudes toward statistics in baccalaureate and graduate nursing and non-nursing majors? The second hypothesis is, Does a relationship exist among student attitudes toward statistics and certain demographic variables?
Little current evidence exists in the scholarly literature of nursing and related disciplines that reflects nursing student attitudes toward statistics. Hagen, Awosoga, Kellett, and Dei (2013) explored the attitudes of 104 undergraduate nursing students toward statistics courses before and after taking a mandatory course and found that student anxiety was reduced by 40%. A variety of positive teaching–learning strategies, such as the use of real-life examples and visual teaching aids, as well as supportive faculty characteristics (e.g., patience, approachability, and a sense of humor), was identified by the sample, and students indicated by moderate agreement that statistics would be useful to their nursing careers (Hagen et al., 2013).
DiBartolo, Salimian, Kotteman, and DiBartolo (2012) studied nursing student engagement in statistics by implementing an integrated, semester-long technique that used a questionnaire to address issues relevant to students and then incorporated the resulting dataset throughout the course. Topics such as typical hours slept, patterns of Internet use, work habits, and regular exercise are incorporated into items, resulting in data that can be analyzed to enhance the concepts taught. Those authors reported student engagement through active learning modalities, the ability to critically appraise research, and positive student and faculty feedback (DiBartolo et al., 2012). However, they did not provide the results of such feedback, nor did they formally measure student attitudes toward statistics, indicating a gap in the nursing education literature.
Pierce and Jameson (2008) explored differences in student attitudes toward statistics among academic majors. They reported that the Affect and Cognitive subscales of the Survey of Attitudes Toward Statistics Scale-36 (SATS-36) showed no differences among majors, but the Value subscale of the SATS-36 did show differences. Post hoc analyses showed that education and computer science majors differed significantly, with computer science majors scoring more positively on student attitudes than education majors (Pierce & Jameson, 2008). Although that study did not include nursing students, it is of importance to mention because it is the only published report to explore differences in student attitudes toward statistics among other majors.
Schield and Schield (2008) conducted research on student attitudes toward statistics. They found that although 61% of students (n = 62) appreciated more value in statistics after taking the course than before the course, the differences were not statistically significant. However, the students surveyed did report a statistically significant increase in feelings of cognitive competence after completion of the course, even though they found the course to be difficult (Schield & Schield, 2008). Average student cognitive competence increased from 4.6 to 5.0 on a scale of 1 to 7 after course completion. Therefore, after thoughtful consideration of gaps in the existing empirical literature and a review of the AACN Essentials (2008), the purpose of the current research study was to explore whether there is a difference in overall attitudes toward statistics among undergraduate and graduate nursing and non-nursing majors and whether a variety of demographic variables related to student attitudes exists.
After obtaining institutional review board approval, nursing faculty used a cross-sectional design to develop and distribute research packets to baccalaureate and graduate nursing and non-nursing students enrolled in a public institution in the northeastern United States. A convenience sample was used. The research packet consisted of the SATS-36, as well as a demographic data sheet.
Setting and Sample
The convenience sample was composed of all students invited to participate, and the response rate was 100%, as all students who were asked to participate returned a completed packet. The respondents’ ages ranged from 19 years to the low 50s. The majority of respondents were women. The recommended sample size of 63 for each group was determined as being appropriate for a power of 0.8 and moderate size effect of alpha = 0.05 for a two-sample t test (Polit & Beck, 2010).
The first instrument to measure attitudes toward statistics, the Statistics Attitude Survey (SAS), was designed by Roberts and Bilderback (1980). Since that time, two other widely used instruments measuring attitudes toward statistics have been developed, the Attitudes Toward Statistics Scale (ATS; Wise, 1985) and the SATS (Schau, Stevens, Dauphinee, & DelVecchio, 1995). The SATS is an updated version of the ATS and is composed of four subscales to measure positive and negative feelings concerning statistics (Affect scale); attitudes about intellectual knowledge and skills when applied to statistics (Cognitive Competence scale); the usefulness, relevance, and worth of statistics (Value scale); and the difficulty of statistics as a subject (Difficulty scale; Schau et al., 1995). The most recent version of the SATS-36, composed of 36 items, is more detailed with respect to determining attitudes because it adds the Interest and Effort subscales, along with Affect, Cognitive Competence, Value, and Difficulty subscales (Schau, 2003). The instrument uses a 7-point Likert scale, with higher scores denoting more positive attitudes. After reverse scoring, total scores range from 36 to 252, with greater scores indicating a more positive attitude toward statistics. The survey also includes demographic- and academic-related questions. Internal consistency reliability estimates were >0.90 for total scores and >0.70 for subscale scores for the instrument.
Data were analyzed using SPSS® version 19. Coefficient alpha reliabilities of the instruments were assessed. Using a two-tailed test, the Pearson product–moment correlation coefficient was used. An independent samples t test and a one-way analysis of variance were used to analyze study hypotheses.
Descriptive statistics of select demographic variables are as follows. Seventy-three percent of participants were below age 30 years, with the remainder being between 30 and 50 years. Ninety percent of participants identified themselves as women. Thirty-seven percent of participants reported their grade point average to be between 2.5 and 3.5, 47% reported an average of 3.5 or above, and 16% did not report their grade point average. Undergraduate nursing students represented 36% of the participants, 30% were undergraduate education majors, and 34% were graduate nursing students. Seventy-nine percent of participants reported no exposure to statistics in high school, and 54% reported that at least one parent attended college.
Scores for the SATS-36 in the current study ranged from 71 to 226 (X = 150, SD = 29.3) and statistically significant results were obtained (Table 1). In a sample of 175 undergraduate and graduate nursing and non-nursing students, the one-way analysis of variance was significant in evaluating differences among groups for student attitudes toward statistics (F[3, 158] = 7.43, p = 0.001), with graduate nursing students having a significantly lower total score in the SATS-36 (136.98), compared with baccalaureate nursing (153.45) and non-nursing (157.26) students.
Group and Survey of Attitudes Toward Statistics Scale (SATS-36) Scores
Pearson correlations were conducted to investigate the relationship between student attitude toward statistics and college level, and statistically significant negative relationships were found (r = −0.26, p = 0.005) with Spearman’s test (r = −0.27, p = 0.004); high school rank (r = −0.28, p = 0.013), exposure to statistics in high school (r = −0.19, p = 0.019) with Spearman’s test (r = −0.20, p = 0.012); and previous exposure to statistics in college (r = −0.18, p = 0.024) with Spearman’s test (r = −0.16, p = 0.037), which is summarized in Table 2.
Study Participant Demographics
When comparing the means of two groups (Table 3), moderate statistically significant differences were found among students who had exposure to statistics in high school (t = 2.17, p = 0.032), students who took basic skills mathematics in college (t = −1.60, p = 0.082), and students who took a research statistics course in college (t = 2.29, p = 0.024).
Study Participants’ Survey of Attitudes Toward Statistics Scale Results
Statistically significant differences were also found when comparing nursing and non-nursing students (t = −2.27, p = 0.025), with significantly lower total SATS-36 scores found for nursing students compared with non-nursing students. Additional statistically significant findings include attitude toward statistics and major (F[3, 158] = 7.58, p = 0.000); current number of credits (r = −0.28, p = 0.000), with significance at 0.01 (two tailed); anticipated grade in course by Pearson test (r = −0.24, p = 0.003), with significance at 0.01 (two tailed), and Spearman’s test (−0.19, p = 0.021), with significance at 0.05 (two tailed).
The majority of the study sample was aged younger than 30 years, were women, had a grade point average of 3.0 or higher, had SAT® mathematics scores more than 500, and did not have exposure to statistics in high school. Thirty-six percent of the sample were enrolled in undergraduate nursing, 30% were undergraduate education majors, and 34% were graduate nursing students. Fifty-four percent had parents who had attended college. Therefore, this relatively young, mostly female sample displayed moderate attitudes toward statistics. They had limited previous exposure toward statistics and were students in good academic standing.
Statistically significant relationships were found among students’ attitude toward statistics and their program (i.e., nursing, non-nursing, undergraduate, graduate), college class (i.e., undergraduate freshmen, sophomore, junior, senior), exposure to statistics in high school and college, major, number of credit hours for which students were currently enrolled, and anticipated grade in the course. On the basis of this analysis, one can conclude that differences in student attitudes toward statistics exist among nursing and non-nursing majors. Further, graduate nursing students’ SATS-36 scores were also significantly lower than those of undergraduate nursing and non-nursing students. It is important to note that this study resulted in nursing students having less favorable SATS-36 scores than non-nursing students. However, significant correlations were negative, and the lesser exposure the students had to statistics, the higher their attitude, which was not reported previously in the literature. Therefore, this is an avenue for future exploration. Another possible area for future research is the further investigation of differences in less favorable student attitudes toward statistics of graduate nursing students versus baccalaureate students, as this has not been researched to date.
Some possible methodological limitations of the current study include the use of only one university from which data were collected, which could have led to homogeneity of the sample. Another possible limitation is gender, as the majority of the sample were women. A third possible methodological limitation could be the timing of data collection, as data were collected in the classroom, where students could have been distracted or preoccupied.
Study findings can be further correlated to nursing curricula. Innovative nursing curricula that creatively incorporate information regarding student attitudes and knowledge of key demographic student variables may result in favorable student outcomes. This study partially supports the findings reported by Pierce and Jameson (2008), which show statistically significant differences in SATS-36 scores between majors. It is the responsibility of nurse academics to continue to explore student attitudes toward statistics to determine best practices for nursing education today and in the future.
Implications and Conclusions
Millennial learners present a variety of challenges to nursing faculty. Previous research demonstrates that effective educators connect with students by using innovative learning strategies to clearly articulate the value of linking research to evidence-based nursing practice (McCurry & Martins, 2010). Significant results of the current study may be used by nursing faculty to make curricular changes that may enhance the incorporation of statistics, particularly student attitudes toward statistics, into nursing education. Recommendations may include pre-admission assessment of whether students have had previous exposure to statistics. Subsequently, students could be placed in statistics courses according to their unique status. Additional recommendations include further inquiry into nursing student attitudes toward statistics. Offering a two-course series of statistics and research that is co-taught by mathematics and nursing faculty may be another strategy to allow students to better understand statistics and to make it more interesting to apply research in real-world situations.
Another key area of exploration is nursing faculty knowledge, attitudes, competence, and confidence in incorporating statistics and research into all courses in relation to evidence-based nursing practice. Faculty may be as uneasy as students in the area of statistics and research. All courses in the nursing curriculum must incorporate research and evidence-based practice, using innovative strategies, such as including real-world examples of research and statistics, to increase student comfort levels and to encourage positive attitudes to make research meaningful to students. Perhaps collecting data about tasks that impact the life of a nursing student, such as the number of assignments, pages to read prior to a class, and the effect of multitasking to grade performance, may make research more meaningful and improve attitudes. An undergraduate curriculum that fosters statistics and research may significantly improve graduate student attitude toward statistics and research.
To fully comprehend and incorporate research, nurses must possess knowledge of both qualitative and quantitative research processes, as well as basic applied statistics. The nursing profession has been guided by evidence-based practice in the 21st century. To understand research and apply evidence into practice, nurses must be knowledgeable in statistics and statistical methods, thus it is crucial to promote a positive attitude toward statistics among nursing students (Resha & Cowell, 2011).
- Aktan, N., Fagan, J. & Sorkin, C. (2012). Characterizing encounter data for patients using an indigent medical clinic. Journal of the Nurse Practitioners, 8, 32–37. doi:10.1016/j.nurpra.2011.06.002 [CrossRef]
- American Association of Colleges of Nursing. (2006). AACN position statement on nursing research. Washington, DC: Author.
- American Association of Colleges of Nursing. (2008). The essentials of baccalaureate education for professional nursing practice. Washington, DC: Author.
- Ashcroft, A. (2006). Statistical graffiti. Journal of Nursing Education, 45, 44–45.
- DiBartolo, M., Salimian, F., Kotteman, J. & DiBartolo, G.R. (2012). Engaging baccalaureate nursing students in statistics. Nurse Educator, 37, 145–146. doi:10.1097/NNE.0b013e31825a87ff [CrossRef]
- DiMaria-Ghalili, R. & Ostrow, C. (2009). Using Microsoft Excel to teach statistics in a graduate advanced practice nursing program. Journal of Nursing Education, 48, 106–110. doi:10.3928/01484834-20090201-03 [CrossRef]
- Hagen, B., Awosoga, O., Kellett, P. & Dei, S. (2013). Evaluation of undergraduate nursing students’ attitudes towards statistics courses, before and after a course in applied statistics. Nurse Education Today, 33, 949–955. doi:10.1016/j.nedt.2012.11.005 [CrossRef]
- High-Value Health Care Project. (2010). How registries can help performance measurement improve care. Retrieved from http://www.rwjf.org/en/research-publications/find-rwjf-research/2010/06/latest-from-aligning-forces-for-quality-communities/how-registries-can-help-performance-measurement-improve-care.html
- Institute of Medicine. (2010). The future of nursing: Leading change, advancing health. Retrieved from http://www.iom.edu/∼/media/Files/Report%20Files/2010/The-Future-of-Nursing/Future%20of%20Nursing%202010%20Report%20Brief.pdf
- McCurry, M. & Martins, D. (2010). Teaching undergraduate nursing research: A comparison of traditional and innovative approaches for success with millennial learners. Journal of Nursing Education, 49, 276–279. doi:10.3928/01484834-20091217-02 [CrossRef]
- Niven, E., Roy, D.E., Schaefer, B.A., Gasquoine, S.E. & Ward, F.A. (2013). Making research real: Embedding a longitudinal study in a taught research course for undergraduate students. Nurse Education Today, 33, 64–68. doi:10.1016/j.nedt.2011.10.024 [CrossRef]
- Pierce, R.L. & Jameson, M.M. (2008, August). Students’ attitudes toward statistics: Are there differences among various majors? Paper presented at the Joint Statistical Meetings. , Denver, CO. .
- Polit, D.F. & Beck, C.T. (2010). Essentials of nursing research: Appraising evidence for nursing practice (7th ed.). Philadelphia, PA: Wolters Kluwer, Lippincott Williams and Wilkins.
- Resha, C. & Cowell, J.M. (2011). Statistics for school nursing practice. The Journal of School Nursing, 27, 399–400. doi:10.1177/1059840511427686 [CrossRef]
- Roberts, D. & Bilderback, E. (1980). Reliability and validity of a statistics attitude survey. Educational and Psychological Measurement, 40, 235–238. doi:10.1177/001316448004000138 [CrossRef]
- Schau, C. (2003, August). Students’ attitudes: The “other” important outcome in statistics education. Paper presented at the Joint Statistical Meetings. , San Francisco, CA. .
- Schau, C., Stevens, J., Dauphinee, T. & DelVecchio, A. (1995). The development and validation of the survey of attitudes toward statistics. Educational and Psychological Measurement, 55, 868–875. doi:10.1177/0013164495055005022 [CrossRef]
- Schield, M. & Schield, C. (2008, August). Student attitudes toward statistics at Augsburg College. Paper presented at the Joint Statistical Meetings. , Denver, CO. .
- Taylor, S. & Muncer, S. (2000). Redressing the power and effect of significance. A new approach to an old problem: Teaching statistics to nursing students. Nurse Education Today, 20, 358–364. doi:10.1054/nedt.2000.0429 [CrossRef]
- Wise, S.L. (1985). The development and validation of a scale measuring attitudes toward statistics. Educational and Psychological Measurement, 45, 401–405.
- Zellner, K., Boerst, C.J. & Tabb, W. (2007). Statistics used in current nursing research. Journal of Nursing Education, 46, 55–59.
Group and Survey of Attitudes Toward Statistics Scale (SATS-36) Scores
|Undergraduate nursing students||153.45|
|Graduate nursing students||136.98|
|Undergraduate non-nursing students||157.26|
Study Participant Demographics
|Demographic||r Value||p Value|
|High school rank||−0.28||0.013|
|Exposure to statistics in high school||−0.19||0.019|
|Previous exposure to statistics in college||−0.18||0.024|
Study Participants’ Survey of Attitudes Toward Statistics Scale Results
|Demographic||t Value||p Value|
|Exposure to statistics in high school||2.17||0.032|
|Took a basic skills mathematics course in college||−1.60||0.082|
|Previous exposure to statistics in college||2.29||0.024|