Category Archives: Data collection

“Please answer….” (cont.)

What do people HATE about online surveys?   If you want to improve your response rates, check out SurveyMonkey Eric V’s (May Mail2017)  Eliminate survey fatigue: Fix 3 things your respondents hate 

For more info: Check out my earlier post “Please Answer!”


Nightingale: Avante garde in meaningful data

In honor of Nurse Week, I offer this tribute to the avante garde research work of Florence Nightingale in the Crimea that saved lives and set a precedent worth following.

Nightingale was a “passionate statistician” knowing that outcome data are convincing when one wants to change the world.  She did not merely collect the data, but also documented it in a way that revealed its critical meaning for care.

As noted by John H. Lienhard (1998-2002): Nightingale coxcombchart“Once you see Nightingale’s graph, the terrible picture is clear. The Russians were a minor enemy. The real enemies were cholera, typhus, and dysentery. Once the military looked at that eloquent graph, the modern army hospital system was inevitable.  You and I are shown graphs every day. Some are honest; many are misleading….So you and I could use a Florence Nightingale today, as we drown in more undifferentiated data than anyone could’ve imagined during the Crimean War.” (Source: Leinhard, 1998-2002)

As McDonald (2001) writes in the BMJ free, full-text,  Nightingale was “a systemic thinker and a “passionate statistician.”  She insisted on improving care by making policy & care decisions based on “the best available government statistics and expertise, and the collection of new material where the existing stock was inadequate.”(p.68)

Moreover, her display of the data brought its message home through visual clarity!

Thus while Nightingale adhered to some well-accepted, but mistaken, scientific theories of the time (e.g., miasma) her work was superb and scientific in the best sense of the word.   We could all learn from Florence.

CRITICAL THINKING:   What issue in your own practice could be solved by more data?  How could you collect that data?   If you have data already, how can you display it so that it it meaningful to others and “brings the point home”?






Listen up! Don’t interrupt!

Researchers collect two types of data in their studiescounting-sheetword-art

  1. Numbers (called quantitative data)
  2. Words & narratives (called qualitative data)

StorytellerOne source of rich word or narrative (qualitative) data for answering nursing questions is nurses’ stories.  Dr. Pat Benner RN, author of Novice to Expert explains two things we can do to help nurses fully tell their stories so we can learn the most from their practice.

  1. Listen well without interrupting
  2. Help nurses ‘unpack’ their stories 

Check out this excellent 2:59 video of Dr. Benner’s and revolutionize how you learn about nursing from nursing stories:  Preview: The use of Narratives 

Critical thinking:  For a study using narratives in research see  Leboul et al. (2017).  Palliative sedation challenging the professional competency of health care providers and staff: A qualitative focus group and personal written narrative study.  [full text available thru PubMed at].    1) Do you think the authors listened and unpacked information from the focus groups & written narratives; 2)  Do you think there might be a difference in the way people write narratives and verbally tell narratives?   3) How might that difference if any affect the research findings?

For more information:  Check out The Power of Story  by Wang & Geale (2015) at


Direct speaking about INdirect outcomes: HCAHPS as a measurement

When you first plan a project, you need to know what OUTCOMES you want to achieve.  You need STRONG outcomes to show your project worked! imagesCALQ0QK9

Outcome measures are tricky & can be categorized into Indirect & Direct measures:

  1. INDIRECT outcome measures are often affected by many factors, not just your innovation
  2. DIRECT outcome measures are specific to what you are trying to accomplish.

For example: If you want to know your patient’s weight, you put them on the scale (direct). weight-scaleYou don’t merely ask them how much they weigh (indirect).

Another example?  If you planned music to reduce pain, you might a) measure how many patients were already using music and their pain scores (& perhaps those not using music and their pain scores), b) begin your music intervention, and c) thmusicen directly measure how many patients started using it after you started your intervention and their pain scores.  These data DIRECTLY target your inpatient outcomes versus looking at INDIRECT HCAHPS answers of discharged patients’ feelings after the fact in response to “During this hospital stay, how often was your pain well controlled?”

Nurses often decide to measure their project outcomes ONLY with indirect HCAHPS scores.  I hope you can see this is not as good as DIRECT measures.

So why use HCAHPS at all?measuring-tape

  • They reflect institutional priorities related to quality and reimbursement
  • Data are already collected for you
  • Data are available for BEFORE and AFTER comparisons of your project outcomes
  • It doesn’t cost you any additional time or money to get the data

Disadvantages of indirect HCAHPS measures?

  • HCAHPS data are indirect measures that are affected by lots of different things, and so they may have little to do with effect of your project.
  • HCAHPS responders often do Not represent all patients because the number responding is so small–sometimes just 1 or 2

Still, I think it’s good to include HCAHPS.  Just don’t limit yourself to that. Include also a DIRECT measure of outcomethat targets the precisely what you hope will be the result of your study.

imagesCALQ0QK9You need STRONG outcomes to convince others that your project works to improve care!

CRITICAL THINKING:  McClelland, L.E., &  Vogus, T.J. (2014) used HCHAPS as an outcome measure in their study, Compassion practices & HCAHPS: Does rewarding and supporting questionworkplace compassion influence patient perceptions?    What were the strengths & weaknesses of using HCHAPS in this study? [hint: check out the discussion section]  What would be a good direct measure that you could add to HCAHPS outcomes to improve the study?

FOR MORE INFORMATION:  Whole books of measurement instruments are available through the library or a librarian can help you search for something that will measure motivation, pain, anxiety, medication compliance, or whatever it is you are looking for!!  You can limit your own literature searches by selecting “instrument” as part of your search, or you can consult with a nurse researcher for more help.

DATA COLLECTION SECTION! (Methods in the Madness)

Key point! The data collection section of a research article includes: who collects what data when, where & how.

In previous blogs we’ve looked at title, introduction, and other elements of methods section (design, sample, & setting). In this one let’s take a look at data collection.

Data are a collection of measurements. For example, student scores on a classroom test might be 97, 90, 88, 85, & so on. Each single score is a datum; collectively they are data.

What data are collected is answered in this section. The data (or measurements) can be counting-hashmarksnumbers OR words. For example, numbers data might include patient ratings of their pain on a 0-10 scale. An example of word data would asking participants to describe something in words without counting the words or anything else.  For example, word data might include patient descriptions pain in words, like word-art“stabbing,”  “achy,” and so on.  Sometimes a researcher collects both number and word data in the same study to give a more complete description.  You can see how knowing the patient’s pain rating and hearing a description would give you a much clearer picture of pain.

  • Studies reporting data in numbers are called quantitative studies
  • Studies reporting data in words/descriptions are called qualitative studies
  • Studies reporting number & word data are called mixed methods studies

How the data are collected includes what instrument or tool was used to gather data (e.g., observation, biophysical measure, or self-report) and how consistently & accurately that tool measures what it is supposed to measure (e.g., reliability & validity). Also included is who collected the data and the procedures that they followed—how did they obtain consent, interaction with subjects, timing of data collection and so on.

Now you know!

Critical thinking question: Did these authors use qualitative or quantitative data collection methods?  Coelho, A., Parola, V., Escobar-Bravo, M., & Apostolo, J. (2016). Comfort experience in palliative care, BMD Palliative care, 15(71). doi: 10.1186/s12904-016-0145-0.  Explain your answer.

Self-Report Data: “To use or not to use. That is the question.”

[Note: The following was inspired by and benefited from Rob Hoskin’s post at]Penguins

If you want to know what someone thinks or feels, you ask them, right?

The same is true in research, but it is good to know the pros and cons of using the “self-report method” of collecting data in order to answer a research question.  Most often self-report is done in ‘paper & pencil’ or SurveyMonkey form, but it can be done by interview.

Generally self-report is easy and inexpensive, and sometimes facilitates research that might otherwise be impossible.  To answer well, respondents must be honest, have insight into themselves, and understand the questions.  Self-report is an important tool in much behavioral research.

But, using self-report to answer a research question does have its limits. People may tend to answer in ways that make themselves look good (social desirability bias), agree with whatever is presented (social acquiescence bias), or answer in either extreme terms (extreme response set bias) or always pick the non-commital middle Hypothesisnumbers.  Another problem will occur if the reliability  and validity of the self-report questionnaire is not established.  (Reliability is consistency in measurement and validity is the accuracy of measuring what it purports to measure.) Additionally, self-reports typically provide only a)ordinal level data, such as on a 1-to-5 scale, b) nominal data, such as on a yes/no scale, or c) qualitative descriptions in words without categories or numbers.  (Ordinal data=scores are in order with some numbers higher than others, and nominal data = categories. Statistical calculations are limited for both and not possible for qualitative data unless the researcher counts themes or words that recur.)

Gold_BarsAn example of a self-report measure that we regard as a gold standard for clinical and research data = 0-10 pain scale score.   An example of a self-report measure that might be useful but less preferred is a self-assessment of knowledge (e.g., How strong on a 1-5 scale is your knowledge of arterial blood gas interpretation?)  The use of it for knowledge can be okay as long as everyone understands that it is perceived level of knowledge.

Critical Thinking: What was the research question in this study? Malaria et al. (2016) Pain assessment in elderly with behavioral and psychological symptoms of dementia. Journal of Alzheimer’s Disease as posted on questionat with link to full text.  How did the authors use self-report to answer their research question?  Do you see any of the above strengths & weaknesses in their use?

For more information: Be sure to check out Rob Hoskins blog: