C797 Data Science and Analytics, catalog number NURS 6701, is a two-CU course in the MSN Nursing Informatics specialty covering interdisciplinary healthcare data science: statistics, computer science, data visualisation and social science tools applied to data analysis, database management and both descriptive and inferential methods. The course rewards restraint. The commonest failure is an analysis that answers a question nobody asked, presented in a chart that hides the answer.
What NURS 6701 is actually testing
Analytics work has a fixed order and the course is testing whether you follow it. The question comes first, then the data that could answer it, then the method that suits both, then the analysis, then the presentation, then the decision. Students who start from a dataset and look for something interesting produce results that cannot be acted on, which is the analytic equivalent of a solution without a problem.
Method selection is the technical core. Descriptive statistics summarise what happened. Inferential statistics support a claim about a population beyond the data you hold, and they carry assumptions. Choosing between them is a judgment about what your question actually requires, and a great many healthcare questions need nothing more than a well-constructed rate with a denominator.
Data quality is the part clinicians underestimate least often once they have seen real extracts. Clinical data is dirty in specific ways: values entered as free text, defaults never changed, timestamps recording when someone documented rather than when something happened, missingness that is not random because the sickest patients have the most gaps. An analysis that does not address quality is an analysis nobody should act on.
Visualisation is scored too, and badly done charts are common. A graph exists to make a comparison easy. Truncated axes, three-dimensional effects, colour that carries meaning invisible to a colour-blind reader and pie charts with nine slices all fail that test.
Turning scored aspects into a section plan
WGU keeps rubric detail in your Course of Study rather than the catalog, so count the scored aspects first. Each is judged on its own against a three-point scale and each needs a 2, so a sophisticated method with no data quality section will still come back.
The word budget, worked. Take six scored aspects and directions asking for roughly 1,500 words alongside any required output. Reserve 110 for an opening stating the question and 90 for the close, leaving 1,300 across six aspects, or about 216 each. Then weight it. The method justification aspect deserves 300, because it needs the choice, the assumptions and the alternative you rejected. The data quality aspect deserves 260. That leaves 740 for four aspects at 185 each, which is workable when charts and tables carry part of the evidence.
Write the decision sentence before the analysis. If the result comes out this way we do X, and if it comes out that way we do Y. An analysis whose result would not change anything is a report, and it is worth finding that out before you build it.
A structure that fits an analytics deliverable
Task directions win where they specify a format. Where they do not, this arrangement follows the order analytics work is judged in.
| Section | What belongs in it | What earns the aspect |
|---|---|---|
| Question | The decision to be made and the question that informs it | A question specific enough to be answered wrongly |
| Data source | Where the data comes from, what it covers, what period, what it excludes | Coverage and exclusions stated, since both bound the conclusion |
| Data quality | Missingness, entry errors, timestamp meaning, duplicates and how each is handled | Handling described, not just problems listed |
| Method | Descriptive or inferential, which technique, assumptions checked | The rejected alternative named, which shows the choice was made |
| Analysis | Results with the numbers that matter, including denominators | Uncertainty expressed rather than a single figure asserted |
| Visualisation | Charts chosen for the comparison, with honest axes and accessible colour | A chart whose message survives being read in five seconds |
| Interpretation | What the result means in clinical or operational terms, and what it does not | Limits stated; overreach is the commonest analytic error |
| Recommendation | The decision the analysis supports and the confidence behind it | A recommendation tied to the decision sentence you wrote first |
| References | APA list of methods sources, data documentation and health analytics literature | Datasets cited with version, period and custodian |
Keep one chart per point. Analytics deliverables often arrive with eight figures and no argument, and evaluators reading a visualisation aspect are looking for charts that carry a claim rather than charts that display everything available.
Evidence craft in healthcare analytics
Analytic claims are checkable in a way narrative claims are not, so precision protects you.
- Document the dataset properly: custodian, period, geography, version and any inclusion rule you applied.
- Cite the method to a statistics or analytics source, and state its assumptions. An inferential test used without its assumptions checked is a result nobody should trust.
- Report denominators everywhere. Percentages without them are the most common way healthcare analysis misleads.
- Give uncertainty a form. A confidence interval, a range, or a plain statement of how small the sample is.
- Distinguish association from causation explicitly. Observational healthcare data supports the first far more often than the second.
- Quote sparingly. Method definitions are reproduced everywhere and WGU runs submissions through a similarity check.
Presentation carries its own obligations in healthcare analytics because the audience is usually senior and time-poor. A finding that is correct and takes eleven minutes to explain will lose to a finding that is roughly right and takes ninety seconds, which is an argument for building the one-sentence version of your result before you build the deck around it. Write the sentence a chief nursing officer would repeat in a meeting, then check that your analysis actually supports that sentence and not a weaker one. Where it does not, the honest move is to change the sentence rather than the emphasis.
The habit that separates strong analytics work is naming what would have changed your conclusion. A different exclusion rule, a longer period, a variable you did not have. Analysts who describe the sensitivity of their own result are trusted more than analysts who present a single number, and it is exactly the judgment an interpretation aspect is written to reward.
What separates Competent from a submission sent back
Aspects score on their own, and data quality and interpretation are the ones that come back.
- The question is stated before the data and the decision is stated before the analysis.
- Data quality problems are named and each has a stated handling.
- The method is justified against a named alternative and its assumptions are checked.
- Every result carries a denominator and some expression of uncertainty.
- Charts make one comparison each, with honest axes and accessible colour.
Performance assessment work at WGU can be revised and resubmitted with no grade penalty, so a return costs time. Terms run six months at a flat rate, so the effective cost of the specialty falls with every course you close inside a term. C797 is a two-CU course that students often stretch by exploring data instead of answering a question, and the discipline of writing the question first is usually what closes it quickly.
Six mistakes that cost time in C797
- Starting from the data. Interesting findings that answer no question cannot be acted on and score poorly.
- Percentages with no denominator. A 50 percent increase from two events to three is technically true and useless.
- Ignoring missing data. Missingness in clinical data is rarely random, and pretending otherwise biases the result.
- Using an inferential test because it looks rigorous. Many healthcare questions need a clean rate, not a p value.
- Charts that decorate. Every figure should carry a claim, and figures that do not should be cut.
- Concluding causation. Observational data supports association, and the interpretation aspect is watching for the slip.
How support works on this course
C797 goes quickly once the question is right and slowly when it is not. Send the rubric out of your Course of Study with the task directions and the first pass is the question and the decision sentence, because those two decide whether the analysis is worth running. From there you get a data source documented properly, a quality section with handling for each problem, a method justified against a named alternative, charts rebuilt so each carries one claim, and an interpretation that states its own limits.
The boundaries hold. Objective assessments at WGU are proctored, so we prepare only, never sit them, and never ask for portal credentials. On field-based courses in this specialty we never complete practice hours, contact mentors or sites, sign placement paperwork or fill in hour logs.
Questions students ask about C797
Is C797 the same course as NURS 6701?
How much statistics does C797 assume?
Which tools should I use?
Running an analysis for C797?
Send your Course of Study rubric and the task directions. We fix the question and the decision first, then handle data quality, method and charts.
Where C797 sits in WGU's programs
The July 2026 catalog places this code in 2 current WGU programs. Open a program page for the complete standard path and term positions. The live Degree Plan remains authoritative after transfer credit, substitutions, and mentor planning.
The assessments, one by one
The public catalog does not publish this course's PA/OA identity or task count. WGU Tutors publishes at most one PA manual per course and only from a WGU-controlled public rubric. Until that source exists, PA help begins from the student's real Course of Study and OA support remains preparation only.