| Course | MHA FPX 5017 Data Analysis for Healthcare Decisions |
|---|---|
| Assessment | Assessment 1 |
| Paper type | Descriptive statistics analysis |
| Length | About 1,120 words, 5 pages |
| Format | APA 7 student paper |
| School | Capella University |
| Program | Master of Health Administration (MHA) |
| Updated | September 2026 |
Free sample paper for MHA FPX 5017 Assessment 1
Nursing Home Data Analysis: Describing 120 Residents So the Numbers Can Guide Staffing
Student Name
Capella University
MHA FPX 5017: Data Analysis for Healthcare Decisions
Instructor Name
Month Day, Year
Introduction
The administrator of a composite 130-bed nursing home, here called Maplewood Care Center, asked for a clear description of the facility's current residents to support a review of staffing on its three units. The dataset contains records for all 120 current residents: age, length of stay in days, activities of daily living (ADL) score, number of scheduled medications, number of falls in the last 90 days, and unit. This paper describes each variable, interprets what the numbers mean for staffing, examines unusual values, and identifies the variable that will be carried into the next analysis.
The ADL Score
The ADL score used here is the 28-point scale built from the Minimum Data Set, which sums self-performance ratings for seven activities, each scored from 0 (independent) to 4 (total dependence). Morris et al. (1999) developed and tested scales of this kind and showed that a summed ADL scale from the Minimum Data Set is a reliable measure of physical function among nursing home residents. Higher scores mean a resident needs more help, which translates directly into nursing assistant time.
Distribution Examined, Not Assumed
Each variable was examined with a histogram and summary statistics before any average was reported, because the right summary depends on the shape of the data. Field (2018) emphasizes that the mean is a good summary only when data are roughly symmetric, and that skewed data are better described by the median and interquartile range.
| Variable | Mean | Median | Standard deviation | Interquartile range | Range | Shape |
|---|---|---|---|---|---|---|
| Age (years) | 82.4 | 84 | 8.9 | 77 to 89 | 58 to 101 | Slight left skew |
| Length of stay (days) | 412 | 238 | 486 | 41 to 610 | 6 to 2,910 | Strong right skew |
| ADL score (0 to 28) | 16.8 | 17 | 6.1 | 12 to 21 | 2 to 28 | Roughly symmetric |
| Scheduled medications | 11.2 | 11 | 3.9 | 8 to 14 | 3 to 24 | Slight right skew |
Age and ADL score are close enough to symmetric that the mean and median tell the same story. Length of stay is not. Its mean of 412 days is far above its median of 238, because a few residents have lived at Maplewood for many years. The histogram showed two groups: 34 short-stay residents admitted for rehabilitation after a hospital stay, with a median stay of 24 days, and 86 long-stay residents, with a median of 540 days. Reporting a single average length of stay would describe neither group. Examining the distribution first revealed that Maplewood serves two different populations, which a single average would have hidden. Falls are a count with many zeros: 78 residents had no falls in the last 90 days, 27 had one, 10 had two, and 5 had three or more. For a variable like this, the percentage of residents with any fall, 35%, is more useful than a mean.
Spread Interpreted for Staffing
Spread matters for staffing as much as the average does. An ADL interquartile range of 12 to 21 means that the middle half of residents range from needing limited help with several activities to needing extensive help with most of them. The spread differs by unit.
| Unit | Residents | Mean ADL score | Standard deviation |
|---|---|---|---|
| Memory care | 44 | 20.1 | 5.2 |
| Long-stay general | 42 | 17.3 | 5.9 |
| Short-stay rehabilitation | 34 | 12.4 | 4.8 |
The memory care unit has the highest average need. The long-stay general unit has the widest spread, meaning that on any shift its aides care for some residents who are nearly independent and others who need total help. Staffing that unit by its average would leave aides overstretched on the shifts when the most dependent residents need care at the same time, such as morning care and meals. The rehabilitation unit has the lowest average need, but its residents change quickly as they recover and are discharged, so its staffing needs to be reviewed weekly rather than quarterly.
Outliers as Residents
Several values fell far from the rest. Rather than removing them, each was checked against the resident's record, because an outlier in a nursing home dataset is a person. A length of stay of 2,910 days belongs to a resident who has lived at Maplewood for about eight years; the value is correct. The youngest resident, aged 58, has an ADL score of 28, the maximum, and lives with a progressive neurological condition; that resident's needs are different from those of older residents with similar scores and include specialized equipment and psychosocial support. Three residents take 20 or more scheduled medications, which the consultant pharmacist was asked to review. One ADL score of 31 was found to be a data entry error, since the scale's maximum is 28, and was corrected to 21 after checking the assessment. Treating outliers as residents turns data cleaning into a review of whose needs the averages do not capture.
Output Edited Into Tables
The statistical software produced several pages of output, including frequency tables for every value and statistics the administrator did not need, such as kurtosis and standard errors of skewness. The tables in this paper were edited from that output to show only what supports a decision: the center, the spread, the shape, and the range. Values were rounded to one decimal place, and each table has a title and clear column headings. Presenting the raw output would have forced the reader to find the useful figures among many that are not.
Limitations
The dataset describes residents at one point in time and will change as residents are admitted and discharged, especially on the rehabilitation unit. ADL scores come from the most recent Minimum Data Set assessment, which may be up to three months old for long-stay residents. Falls are drawn from incident reports and may be underreported for falls that no one witnessed.
A Variable Carried Forward
The ADL score will be carried into the next analysis. It is the variable most directly tied to staffing, it is roughly symmetric, and its means differ across units in a way that raises a question the administrator needs answered: is the difference between the memory care unit and the long-stay general unit large enough, and reliable enough, to justify different staffing ratios? That question calls for a hypothesis test comparing the two units.
Conclusion
Describing Maplewood's 120 residents carefully showed two populations hidden in the length-of-stay data, differences in the level and spread of care needs across units, and a small number of residents whose needs the averages do not capture. Editing the output into clear tables makes these findings usable for staffing decisions, and the ADL score is carried forward for testing.
References
Field, A. (2018). Discovering statistics using IBM SPSS Statistics (5th ed.). SAGE.
Morris, J. N., Fries, B. E., & Morris, S. A. (1999). Scaling ADLs within the MDS. The Journals of Gerontology Series A: Biological Sciences and Medical Sciences, 54(11), M546-M553.
What the MHA FPX 5017 Assessment 1 instructions ask for
The first assessment in MHA FPX 5017 asks you to analyze a health care data set, usually provided in the courseroom, using descriptive statistics. You describe the data set and its variables, compute measures of central tendency and spread, examine the shape of the distribution, identify outliers and explain what the results mean for an administrative decision. Software output from Excel, SPSS or similar tools should be edited into tables rather than pasted raw. The course expects interpretation in the language of the setting, such as staffing hours or resident acuity, not only statistical terms. Show which procedure produced each figure so the reader can reproduce it. The variable you choose often carries into the hypothesis testing and regression assessments that follow.
How this MHA FPX 5017 Assessment 1 example is built
Variables, descriptives, distribution, meaning. The opening states the data set, its size and what each variable represents in the facility. A descriptives block computes the measures required with the arithmetic or the software procedure named. A distribution block examines shape, noting skew and outliers and saying what each means in the setting rather than only statistically. An interpretation block reads the results for an administrator: what the spread implies for staffing, what the outlier suggests about a particular resident group or unit. A limits block states what the data cannot support. The closing says which variable warrants the closer analysis in the next assessment. Tables are formatted for a reader rather than pasted from output, and every figure carries its units.
MHA FPX 5017 Assessment 1 scoring guide: what Distinguished looks like
Capella's scoring guide rates the description of the data, the calculations, the distribution analysis, the interpretation and the presentation. Calculations reach Distinguished when correct and when the procedure is named. The distribution criterion scores higher when skew and outliers are examined and the choice between mean and median is explained, since a skewed dependency score makes the mean misleading. Interpretation earns credit when each statistic is translated into what it means for the facility, for example how many residents need two-person transfers. Presentation rewards clean APA-style tables rather than raw output. Limitations, such as a single time point or self-reported data, show judgment. Writing quality and APA references are part of the grade as well.
Common MHA FPX 5017 Assessment 1 mistakes, and how to avoid them
The most common mistake is pasting software output without explanation, which the scoring guide treats as incomplete. Another is reporting the mean for a skewed variable when the median describes the typical resident better. Students often delete outliers without explaining who they are, when in a nursing home an outlier may be a resident needing total care. Statistics are reported without units or context. Tables are formatted inconsistently or missing titles. Interpretation stays statistical instead of administrative. Limitations are left out. Check each figure against the data set, since small errors in counts undermine the analysis. A short paragraph under each table explaining what it shows is the simplest way to earn the interpretation marks.
Get a MHA FPX 5017 Assessment 1 example written to your instructions
Send the Assessment 1 instructions and the scoring guide from your MHA FPX 5017 courseroom, plus the data set your version supplies. We write a custom example against those exact criteria and return it in 24 to 48 hours. The first custom sample is free, and statistical work is generated entirely from the given data, so send yours. The paper above is an original model document written by our desk, not a submitted student paper and not an official Capella University document.
More MHA FPX 5017 papers and MHA samples
- MHA FPX 5017 Assessment 2: Hypothesis Testing for Differences Between Groups
- MHA FPX 5017 Assessment 3: Regression and Combined Techniques
- MHA FPX 5020 Assessment 1: Capstone Project Framing
- MHA FPX 5016 Assessment 1: Mapping Information Systems by the Work They Support
- MHA FPX 5028 Assessment 1: Health System Profile
- MHA FPX 5014 Assessment 1: Measuring a Quality Problem Correctly
MHA FPX 5017 Assessment 1 questions, answered
Should I paste my software output?
No. Edit it into a table with the statistics the assessment asked for, labeled and with units. Raw output shows that you ran a procedure; a formatted table shows you understood which results mattered. Where your instructions ask for output as evidence, put it in an appendix rather than in the analysis.
When is the mean misleading?
Whenever the distribution is skewed or has extreme values, which in facility data is common. Length of stay and cost per resident are frequently skewed. Report the median alongside, note the skew, and say which measure an administrator should plan around, since that judgment is what the criteria reward.
What do I do with outliers?
Investigate before removing. In facility data an outlier is usually a real resident with unusual needs or a unit with a different case mix, which is information rather than noise. Removing it silently discards the most interesting finding and misrepresents the population you are describing.
Where can I find a free MHA FPX 5017 Assessment 1 sample paper?
The nursing home data analysis is on this page in full, with the ADL score, distribution, spread interpreted for staffing, outliers, tables and limitations. A custom analysis of your own data set can be requested free.
Should I report the mean or median in MHA FPX 5017 Assessment 1?
Report both, then explain which describes the data better. For skewed variables, such as dependency scores or length of stay, the median usually represents the typical case more accurately.