| Course | RES 6551 Analyzing the Dissertation Research |
|---|---|
| Module | Module 5 |
| Paper type | Complete dissertation Chapter 4 |
| Length | 1,200 words, about 4 pages plus title and reference pages |
| Format | APA 7 student paper |
| School | American College of Education |
| Program | Ed.D. and DBA doctoral core |
| Updated | October 2026 |
Free sample paper for RES 6551 Module 5
Chapter 4: Results of a Study of Transformational Leadership, Team Psychological Safety and Voice Among Hospital Revenue Cycle Employees
Student Name
American College of Education
RES6551: Analyzing the Dissertation Research
Module 5 Assignment
Instructor Name
November 9, 2026
Introduction
This study asked whether the transformational leadership of front-line supervisors is related to the voice behavior of hospital revenue cycle employees and whether team psychological safety accounts for part of that relationship. Three research questions addressed the leadership-voice association, the leadership-safety association and the indirect path from leadership through safety to voice. This chapter reports how data were collected and prepared, who took part, how the variables were distributed and related and what the analyses showed for each question. Additional analyses follow, and the chapter closes with a summary. Discussion of what the results mean is reserved for Chapter 5.
Data Collection
After IRB approval, revenue cycle leaders at three health systems, two in North Carolina and one in Virginia, forwarded an invitation to about 640 eligible employees, and the anonymous survey remained open for five weeks with two reminders. The procedures followed Chapter 3 with one minor change: the survey closed after five weeks rather than six because the recruitment target had been passed and reminders were producing few new responses, a change approved by the dissertation chair and noted for the IRB. In all, 241 surveys were started. Response counts were monitored daily by system so that no single employer dominated the sample.
Data Preparation
Preset rules removed 20 cases in sequence: 9 with fewer than 80% of scale items answered, 8 that failed both attention checks and 3 that gave identical answers across all 20 items, leaving 221 (Appendix C). Missing item values were rare, 17 in all, and showed no systematic pattern on Little's test, so scale scores were averaged over answered items. Three psychological safety items were reverse-scored. No univariate or multivariate outliers met the preset cutoffs, distributions were close to normal and variance inflation factors were all below 1.6. Six unusually fast responders who passed every quality check were retained and examined in a sensitivity analysis.
Participants
System A supplied 100 of the 221 participants, System B 68 and System C the remaining 53. Patient access staff were the largest group (32.6%), followed by coders (24.4%), denials and follow-up staff (21.7%) and billers (21.3%). Just under half (47.5%) worked remotely or hybrid. Median tenure in the current role was 3.6 years (M = 4.95, SD = 3.64). The usable response rate was about 34.5%, and the role mix differed from each system's workforce by no more than about four percentage points (Table 1).
Descriptive Statistics
Supervisors received an average transformational leadership rating of 3.48 on the five-point scale (SD = 0.81). Psychological safety averaged 4.90 and voice 4.61 on their seven-point scales (SDs = 1.08). Reliability was high for all three measures, with alphas between .91 and .92. Leadership correlated .59 with psychological safety and .35 with voice, and safety correlated .44 with voice, all p < .001; neither tenure nor work location correlated significantly with any study variable (Table 2). Safety scores differed modestly across health systems, and leadership ratings differed modestly across roles, each explaining under 5% of the variance.
Assumption Checks
The regression assumptions named in Chapter 3 were examined on the residuals of the full model before results were interpreted. Residuals plotted against fitted values showed no curve, so a linear form was appropriate. The Durbin-Watson value of 2.05 gave no sign of dependent errors, and residuals tracked the reference line of a normal Q-Q plot closely. The Breusch-Pagan statistic sat right at the conventional threshold, chi-square(4) = 9.50, p = .050, with residuals spreading slightly more at low predicted values; this prompted the robust re-estimation reported under additional analyses. Collinearity was low throughout. Overall, the data met the conditions for ordinary least squares regression closely enough for the planned models to be interpreted as specified (Appendix D).
Research Question 1
With tenure and work location controlled, higher transformational leadership ratings were associated with more voice (b = 0.47, 95% CI [0.30, 0.63], beta = .35, p < .001). The model accounted for 13.2% of the variance in voice, F(3, 217) = 11.02, p < .001. Neither control reached significance. The first null hypothesis was rejected (Table 3, Model 1).
Research Question 2
Leadership was also associated with psychological safety under the same controls (b = 0.79, 95% CI [0.65, 0.94], beta = .59, p < .001), and the model explained 35.3% of the variance in safety, F(3, 217) = 39.45, p < .001. The second null hypothesis was rejected (Table 3, Model 2).
Research Question 3
When psychological safety and leadership were entered together, safety was associated with voice (b = 0.36, 95% CI [0.22, 0.51], p < .001), while the direct association of leadership with voice was smaller and not significant (b = 0.18, 95% CI [-0.01, 0.38], p = .068). Adding safety raised the explained variance in voice from 13.2% to 21.8%. Across 5,000 bootstrap resamples, the indirect path from leadership to voice through psychological safety was estimated at 0.29, with a 95% percentile interval of 0.16 to 0.42 that does not include zero; the third null hypothesis was rejected. The indirect path represented roughly three fifths of the total association (Table 3, Model 3; Figure 1; Figure 2).
Additional Analyses
Three checks examined the robustness of these results (Appendices D and E). Because a test for unequal residual variance was borderline, all models were re-estimated with HC3 standard errors, and no conclusion changed. A model adding indicators for health system and role, prompted by the descriptive differences, produced an indirect estimate of 0.30 and a direct estimate of 0.20 that again fell just short of significance (p = .051). Excluding the six fast responders produced an indirect estimate of 0.28 and a direct estimate of 0.15 (p = .13). Every hypothesis decision held in each check.
Hypothesis Decisions at a Glance
For ease of reference, the decisions are restated together. H01, no association between leadership and voice after controls: rejected. H02, no association between leadership and psychological safety after controls: rejected. H03, that leadership reaches voice through no path via psychological safety: rejected, on the basis of a bootstrap interval that excluded zero. No hypothesis was stated about the direct path, which is reported descriptively; it was positive but not statistically significant in the main analysis and in both sensitivity analyses. The measures used were the global transformational leadership scale (Carless et al., 2000), the team psychological safety scale (Edmondson, 1999) and the voice scale of Van Dyne and LePine (1998), and the indirect effect was estimated with the regression-based approach described by Hayes (2022).
Summary
Among 221 revenue cycle employees in three health systems, transformational leadership was positively related to both voice and psychological safety, and about three fifths of the leadership-voice link ran indirectly through psychological safety, an effect whose interval excluded zero. With safety in the model, the remaining direct association between leadership and voice was small and not statistically significant. These results held under robust standard errors, added controls and the removal of fast responders. Chapter 5 interprets the findings in light of the literature and the theoretical framework, discusses limitations and offers recommendations for practice and research.
References
Carless, S. A., Wearing, A. J., & Mann, L. (2000). A short measure of transformational leadership. Journal of Business and Psychology, 14(3), 389-405. https://doi.org/10.1023/A:1022991115523
Edmondson, A. (1999). Psychological safety and learning behavior in work teams. Administrative Science Quarterly, 44(2), 350-383. https://doi.org/10.2307/2666999
Hayes, A. F. (2022). Introduction to mediation, moderation, and conditional process analysis: A regression-based approach (3rd ed.). Guilford Press.
Van Dyne, L., & LePine, J. A. (1998). Helping and voice extra-role behaviors: Evidence of construct and predictive validity. Academy of Management Journal, 41(1), 108-119. https://doi.org/10.2307/256902
What the RES 6551 Module 5 instructions ask for
The closing module of RES 6551 asks for the results chapter in finished form. Typical contents are a brief introduction restating the purpose and questions, a description of data collection including any changes from the plan, data preparation, participant characteristics, descriptive results, results organized by research question, any additional or sensitivity analyses and a summary. Tables and figures should be integrated and referenced in the text. Keep the chapter factual and complete, without interpretation. Revise the earlier module drafts into one consistent document rather than pasting them together, and make sure every number agrees across text, tables and appendices. A short opening paragraph that restates the research questions helps readers who start with this chapter. Number every table and figure in order.
Inside the RES 6551 Module 5 example
Ten short sections make up the sample chapter. It restates the three research questions, reports collection with one approved change to the closing date and condenses screening into a paragraph that points to an appendix. Participants and descriptives are each summarized in a paragraph with references to Tables 1 and 2. Each research question receives its own brief section with rounded estimates, intervals and the hypothesis decision, and the third adds the bootstrapped indirect effect with references to both figures. An additional analyses section reports three robustness checks with their estimates, and the summary restates the findings without interpretation before pointing to Chapter 5. Appendix letters are cited where each check appears.
RES 6551 Module 5 rubric: what full marks look like
A finished Chapter 4 is judged on completeness, accuracy and restraint. Reviewers confirm that the planned analysis was run for each question, that statistics and effect sizes are reported correctly, that tables and figures are integrated and consistent with the text and that departures from the plan are disclosed and justified. Additional analyses should be clearly labeled. Interpretation and discussion are out of place here. Organization should follow the research questions, and the summary should restate results without adding meaning. Formatting, notation and references must follow APA 7, since the chapter moves almost unchanged into the final dissertation. Clear signposting to appendices also counts.
Common RES 6551 Module 5 mistakes, and how to avoid them
Assembling Chapter 4 often reveals small inconsistencies between drafts, such as a coefficient rounded differently in two places or a table no longer referenced in the text. If your chapter has grown out of several module drafts, or your chair has asked you to remove interpretation or add effect sizes, our writers can help. Attach your output, tables, current draft and the prompt; what comes back is a single, coherent Chapter 4 with consistent numbers, integrated displays and clearly labeled additional analyses. We work with regression, ANOVA, mediation, moderation and qualitative results. A clean results chapter makes the discussion far easier to defend. Appendix cross-references are checked as well.
Write yours, or have the desk draft it
This paper is an original model document written by our desk, not a submitted student paper and not an official American College of Education document. Read it for the moves, then write your own to the instructions in your classroom. If you want one built to your exact prompt and rubric, the first custom sample is free and arrives in 24 to 48 hours.
More RES 6551 and Ed.D. and DBA doctoral core sample papers
- RES 6551 Module 1: Data Preparation and Screening
- RES 6551 Module 2: Descriptive Results
- RES 6551 Module 3: Results by Research Question
- RES 6551 Module 4: APA Tables and Figures
- RES 6033 Module 3: Coding and Themes Paper
- RES 6003 Module 3: t Test and ANOVA Report
- RES 6531 Module 2: Chapter 2 Framework Section
- LEAD 6523 Module 2: Program Logic Model
RES 6551 Module 5 questions, answered
What does RES6551 Module 5 usually ask for?
The final RES6551 module usually asks for the complete Chapter 4, combining data collection, preparation, participant characteristics, descriptive results and the results for every research question with tables and figures.
Should Chapter 4 discuss what the results mean?
No. Chapter 4 reports what was found, accurately and completely; interpretation, comparison with the literature and implications belong in Chapter 5.
Do I report changes from my Chapter 3 plan in Chapter 4?
Yes. Describe any departure from the planned procedures, why it happened and who approved it, so readers can judge whether it affects the results.
Where can I find a free RES 6551 Module 5 sample paper?
You are reading it: an entire DBA Chapter 4 on leadership, safety and voice in hospital revenue cycle teams, from data collection through three research questions, robustness checks and a summary.
How long is a dissertation Chapter 4?
It varies with the number of research questions and analyses; many run 15 to 30 pages including tables. Clarity and completeness matter more than length.