RES 6003 Module 1 Descriptive Statistics Report Example

One Hundred Eighty-Six Graduates in Numbers: Describing GPA, Exit Examination Scores, Clinical Ratings and Licensure Results in a Composite Kentucky Nursing Program

Student Name

American College of Education

RES6003: Applied Statistics

Module 1 Assignment

Instructor Name

October 12, 2026

Introduction

As assistant director of nursing for a two-year registered nursing program in central Kentucky, I keep the records this report draws on; the program here is a composite built for this exercise. Before the program can ask why some graduates fail the licensure examination, it needs an accurate description of who its graduates are and how they performed. This report describes the 186 students who completed the program in the 2023, 2024 and 2025 cohorts, using measures of center, spread and shape for continuous variables and counts and percentages for categorical ones. The data come from the program's records, stripped of names and student numbers.

The Variables

The data set contains seven variables. Three are continuous: nursing GPA, which runs from 0 to 4.0, the score on the standardized exit examination the program gives in the final semester and the final clinical evaluation rating, on a scale from 1 to 5. Four are categorical: cohort year; self-reported weekly hours of paid work, grouped as 10 or fewer, 11 to 20 and more than 20; participation in the program's remediation course; and first-attempt licensure result, pass or fail. Identifying the level of measurement first matters, because it determines which summaries are meaningful: a mean of cohort years, for example, would be arithmetic without meaning.

Data Preparation

Before computing anything, I checked the file for errors and gaps. All 186 records were complete on the seven variables, since the program enters exit scores, clinical ratings and licensure results as a condition of graduation and collects work hours on the graduation survey. Four GPA values sat exactly at 2.40, which I confirmed against transcripts rather than treating as entry errors. I also screened each continuous variable for extreme values using z-scores. Only one value lay more than 2.5 standard deviations from its mean: an exit score of 1132, about 2.7 standard deviations above the mean. It was a genuine score, so it stayed in the data, and with 186 cases removing it would lower the mean by only about one point.

Nursing GPA

Nursing GPA had a mean of 3.19 (SD = 0.32) and a median of 3.21, ranging from 2.40 to 3.82. The middle half of graduates fell between 2.98 and 3.41, an interquartile range of 0.43. The close agreement between mean and median suggests a roughly symmetric distribution, and the skewness statistic of -0.39 points to a mild lean toward the low end. A histogram confirmed the picture: most graduates clustered between 2.9 and 3.5, with a short tail below 2.8. The lower limit of 2.40 reflects the program's progression rule, since students below that level cannot continue, so the distribution is truncated rather than naturally bounded.

Exit Examination Score

Exit examination scores averaged 943.9 (SD = 70.6), with a median of 946.5 and a range from 781 to 1132. The interquartile range ran from 893 to 997. The distribution was close to symmetric, with a skewness of 0.04, so the mean and standard deviation summarize it well. Fifteen graduates, 8.1%, scored below 850, the benchmark the testing company associates with lower likelihood of passing the licensure examination, and 134, 72.0%, scored 900 or higher. A mean near 944 describes the typical graduate well, but the program's concern lies in the left tail, which the mean alone hides.

Clinical Evaluation Rating

Final clinical ratings averaged 3.85 (SD = 0.61), with a median of 3.9 and a range from 2.4 to 5.0; the interquartile range was 3.5 to 4.3. Because the rating is an instructor's judgment on a five-point scale, it is better treated with caution as an interval measure. Ratings bunched toward the upper end, a pattern common in clinical evaluation, which limits how well the rating can distinguish among strong students.

Categorical Variables

The three cohorts were similar in size: 57 graduates in 2023, 63 in 2024 and 66 in 2025. By work hours, 59 graduates (31.7%) worked 10 hours or fewer a week, 70 (37.6%) worked 11 to 20 hours and 57 (30.6%) worked more than 20 hours. Thirty-one graduates (16.7%) took the remediation course. On the licensure examination, 165 of 186 passed on the first attempt, a pass rate of 88.7%, and 21 (11.3%) did not. Pass rates by cohort were 87.7% in 2023 (50 of 57), 92.1% in 2024 (58 of 63) and 86.4% in 2025 (57 of 66). These year-to-year swings of a few percentage points rest on only seven or eight failures per cohort, so a single student's result can shift a cohort's rate noticeably.

Summary Table

Table 1 in the submitted report gathers the continuous variables in one place, the format APA style expects for a descriptive summary. Each row gives a variable's n, mean, standard deviation, median, interquartile range and minimum and maximum: nursing GPA, 186, 3.19, 0.32, 3.21, 2.98 to 3.41, 2.40 to 3.82; exit examination score, 186, 943.9, 70.6, 946.5, 893 to 997, 781 to 1132; clinical rating, 186, 3.85, 0.61, 3.9, 3.5 to 4.3, 2.4 to 5.0. A second table lists each categorical variable's levels with counts and percentages. Field (2018) recommended that tables carry the numbers and the text carry the interpretation, so the paragraphs above point to patterns rather than repeat every figure.

Licensure Results by Exit Score

A simple cross-tabulation gives a first look at the relationship that matters most to the program. Of the 3 graduates who scored below 800 on the exit examination, 2 passed; of the 12 scoring 800 to 849, 9 passed; of the 37 scoring 850 to 899, 30 passed; and of the 134 scoring 900 or higher, 124 passed, or 92.5%. The pattern rises with exit score, but the small numbers in the lowest bands mean percentages there are unstable; one more failure among the 3 graduates below 800 would move that band's pass rate from 67% to 33%. Comparing subgroups points the same way. Graduates who worked more than 20 hours a week had a lower mean exit score, 933.3, than those working 10 or fewer hours, 946.3, and the 31 graduates who took the remediation course averaged 911.6, which fits the course's purpose of serving students who were struggling.

Choosing the Right Summaries

Two choices in this report deserve comment. Means and standard deviations were reported for GPA and exit scores because both distributions were close to symmetric; for a skewed variable, the median and interquartile range would describe the typical case and spread more faithfully. And percentages were always reported with their counts, because a pass rate of 75% means something different when it rests on 12 graduates than when it rests on 134. Sullivan and Feinn (2012) made a related point about inference: statistics are most useful when they convey the size of a difference or relationship, not only whether one exists, and the same habit of reporting magnitudes with their basis applies to descriptive work. Wasserstein and Lazar (2016) warned that a single number rarely carries a conclusion on its own, which is one more reason to present several summaries side by side.

What Description Cannot Do

These summaries describe the 186 graduates; they do not explain why some failed or predict who will fail next year. The cross-tabulation shows that pass rates rise with exit scores, but it cannot show that exit scores cause passing, since both may reflect the same underlying preparation. Those questions belong to inferential statistics, which later modules of this course address.

Conclusion

The program's 186 recent graduates had a typical nursing GPA near 3.2, a typical exit score near 945 and clinical ratings concentrated at the high end, and 88.7% earned their license on the first try. A small group below the exit benchmark, and an apparent link between exit scores and licensure results, set up the questions for the modules that follow.

References

Field, A. (2018). Discovering statistics using IBM SPSS Statistics (5th ed.). Sage.

Sullivan, G. M., & Feinn, R. (2012). Using effect size: Or why the P value is not enough. Journal of Graduate Medical Education, 4(3), 279-282. https://doi.org/10.4300/JGME-D-12-00156.1

Wasserstein, R. L., & Lazar, N. A. (2016). The ASA statement on p-values: Context, process, and purpose. The American Statistician, 70(2), 129-133. https://doi.org/10.1080/00031305.2016.1154108