Check Chapter 14 in Cohen, Manion and Morrison ( 2011) Research Methods in Education  

I am a big fan of Robert Yin's work on case study methodology. I was able to find clarification in the amazon free preview of his book in chapter 2, page 31. 

http://www.amazon.com/gp/product/1452242569?psc=1&redirect=true&ref_=oh_aui_detailpage_o00_s00

If you wish to clarify the concept for your students, you might prefer to help them ‘feel’ what a ‘unit of analysis’ is, rather than give them a rhetorical explanation. As hinted by Simone de Beauvoir, in “The Ethics of Ambiguity”, the Bible offers a good example! When asked “who is my neighbor?”, Jesus didn’t give a rhetorical answer. He responded by telling the Parable of the Good Samaritan (Luke 10:25-37): “A man was going down from Jerusalem to Jericho, when he was attacked by robbers. They stripped him of his clothes, beat him and went away, leaving him half dead. A priest happened to be going down the same road, and when he saw the man, he passed by on the other side. So too, a Levite, when he came to the place and saw him, passed by on the other side. But a Samaritan, as he traveled, came where the man was; and when he saw him, he took pity on him. He went to him and bandaged his wounds, pouring on oil and wine. Then he put the man on his own donkey, brought him to an inn and took care of him ... “

The priest and the Levite didn’t see the poor man as their neighbor, but the Samaritan did: he decided, on his own, who was his neighbor, and no one could have decided that for him. As I see it, the same goes for the recognition of the unit of analysis – only the researcher knows what she wants to find out and where she wants to look for it. The unit of analysis can be a person, part of a person (in the medical sciences), a community, or even a whole ecosystem, but only the researcher knows the context where the research is going to happen. The clarification of this context tends to be exploratory at first, but will need to be adjusted – by the researcher herself, again – as the research progresses.

Wow Antonio!

Many thanks,

Debra

Debra,

To keep my previous response readable, I didn't suggest any examples, but you can find a few in chapter 2 (page 31) of Robert Yin's book "Case Study Research: Design and Methods" (4th edition, Sage, 2009), available online at http://www.sagepub.com/upm-data/24736_Chapter2.pdf

You might also like to have a look at chapter 1 (and figure 1.1) of Robert Yin's book "Applications of Case Study Research" (3rd edition, Sage, 2012), available online at http://www.sagepub.com/upm-data/41407_1.pdf

Kind regards

Debra,

I´m completely agreed with Antonio. "..for the recognition of the unit of analysis – only the researcher knows what she wants to find out and where she wants to look for it"

This is an interesting discussion.  While I can see the merits of choosing your own unit of analysis, there may also be circumstances when it is important to have a rationale - for example, when one's work is being peer reviewed or examined.  Forgive me if I recommend my own book on this, Doing Research in the Real World (2014) 3rd ed.  London: Sage, especially the chapter on Designing Case Studies.

In order to get a usable answer, I think you need to specify the nature of your case study and the datamaterial included. With inpiration from Emde, Luborsky and Philps, I have developed a model suited to psychodynamic (child) psychotherapy in which the boundaries of a qualitative, relational unit are demarcated by three steps: The child's statement, the therapist's answer, and the outcome (= the child's answer t therapist's intervention). From this you can draw up a thematic chart, allowing you to compare units in single child psychotherapy sessions in relation to  thematic developments in the therapy. More details can be found in this PhD-thesis:

Grünbaum, L. (2014) A Study of Anxieties and Dilemmas Relating to Breaks in the Therapeutic Relationship with Children Whose Relationships in Early Infancy were Reported to have been Emotionally Unstable and Traumatised: A systematic Study of a Young Child who had suffered early abuse and neglect. University of East London Institutuiona Repository/The British Library EThOS

Colleagues:

Thanks very much for sharing your insights and resources in answering my question. The different perspectices have certainly deepened my understanding of the "Unit of Analysis."

With many thanks,

Debra

Interesting discussion I agree wit Antonio.  The Yin text gives a very good explanation of case study.  

I recommend consulting Yin, although for many does not apply this type of estdudio, this author supports very well the advantages thereof. And while it does not define the conditions of a sample for analysis, I think you should at least contain the minimum elements that need to be evaluated in the study.

Greetings to this beautiful land.

Dear Debra,

please be more specific with your question. The unit of analysis highly depends on adopted research methods in your case study (the first difference is in using quantitative or qualitative methods). If you provide more details about methods you use (plan to use) in your case study, you can expect more reliable and useful answers.

Regards,

Zeljko

specifically, the unit of analysis emerges from your research question directly.

Regards

Rafique

Zelijko:

I was looking for generally good examples of describing different unit of analyses (persons, organisations, processes etc.) so that I can have a bank of good examples that I can share with my research students, who seem to sometimes get mix-up with the variables studied regarding the Unit of Analysis and the actual Unit. Hope this is specific enough.

Many thanks,

Debra

Dear Debra,

Unit of analysis is a difficult concept to explain. There are so many confusing explanations to the concept. The concept became clearer to me when I started thinking of unit of analysis as a separate entity from what I was studying at the beginning of my study.

Allow me to explain. While conducting a case study, we start with few questions in mind and study a phenomenon in a real life context to seek answers. Most of us consider the subject of our study as a unit of analysis. It might be true in some cases but it might also not be the case in others.

While collecting data (interviews, observations, field notes etc.) and initial coding, many a times new themes emerge that are unexpected and interesting, so much so that these become the main focus of your analysis. In such cases, the unit of analysis becomes different from the one that you began with.

Thus, to be on the safer side, unit of analysis should always be considered to be the elements that are the focus of your case study analysis, not when you begin your study but when you begin analyzing your data.

I have attached a case study analysis that may be of benefit. 

Article A case study of the health literacy of a criminalized woman

Thanks a lot Antonio...I found Robert Yin's text very useful. Thank you for asking this question, Debra. 

More than the same examples, it is important that cases reconcoer themselves are not the Generalitat, but one might wonder if two organizations are alike ?. But it is very pertinent to recognize that the business relationship with stakeholders At least in the context, similar ien can be, and this is my version of the Case Study.

I hope I've helped

Hi, Debra, I am finding Yin's text to be really, really helpful in this area. especially with regard to embedded, single-case design.  I was having the same problem as you were and am grateful for question and for the answers you received.  I think that identifying the main unit (for me it is the team context) and then examining the sub-units that need to be examined in an effort to support my hypothesis made things much clearer for me.  Thank you so much, Noman, for your clarifications as well you, Antonio, for your thoughtful metaphor as a way of feeling into the unit(s) of analysis.  This was all very helpful.

Hi All,

I am also faced with the same challenge. In the event that the researcher Studies an IT innovation adoption by surveying employees who currently undertake this IT innovation(e.g. Artificial Intelligence Consultants). Now ,using a set of constructs found in literature to influence in an organization to adopt a n IT Innovation, i used the constructs to test "the consultants" in an effort to prove that this set of constructs influenced the adoption within an organization. Would i be correct in saying the Unit of Analysis is Artificial intelligence consultants? An example construct would be Senior Management Support. And an example question item would '' Senior management provides the necessary resources to adopt Artificial Intelligence? Using a Likert Scale.

This is what I wrote in my dissertation and don't know if it will help you:

Identifying the basic or elementary unit of study or focus unit can be rather problematic if a case is not unique or not otherwise dictated to the researcher. Therefore, if this is not the situation, the researcher must ask: "What data is needed to answer the research question(s) and connect to the conceptual framework?" "Where is the data to be ferret out?" "How is it characterized?" Stake (1995) reasoned that case study is "a choice of what is to be studied," the method does not define the case; and we must "concentrate on the case" (p. 443). The researcher must consider whether a single-focus case or a comparison of multifocal cases would be more relevant. The answer to these questions would clarify the characteristics of the unit(s) of analysis.

This might help, there are example as well:

Unit of Analysis: One of the most important ideas in a research project is the unit of analysis.

The unit of analysis is the major entity that you are analyzing in your study. For instance, any of the following could be a unit of analysis in a study:

• individuals
• groups
• artifacts (books, photos, newspapers)
• geographical units (town, census tract, state)
• social interactions (dyadic relations, divorces, arrests)

Why is it called the 'unit of analysis' and not something else (like, the unit of sampling)? Because it is the analysis you do in your study that determines what the unit is. For instance, if you are comparing the children in two classrooms on achievement test scores, the unit is the individual child because you have a score for each child. On the other hand, if you are comparing the two classes on classroom climate, your unit of analysis is the group, in this case the classroom, because you only have a classroom climate score for the class as a whole and not for each individual student. For different analyses in the same study you may have different units of analysis. If you decide to base an analysis on student scores, the individual is the unit. But you might decide to compare average classroom performance. In this case, since the data that goes into the analysis is the average itself (and not the individuals' scores) the unit of analysis is actually the group. Even though you had data at the student level, you use aggregates in the analysis. In many areas of social research these hierarchies of analysis units have become particularly important and have spawned a whole area of statistical analysis sometimes referred to as hierarchical modeling. This is true in education, for instance, where we often compare classroom performance but collected achievement data at the individual student level.

the smallest but very important point to understand in research practice ,therefore this is basic where can we begin our intention to work on

In the attached image 14.54.51 you have examples of unit of studies for data collection (Yin, 2003).

Here are examples of unit of studies as cases: "If the unit of analysis is a bounded system—a case, such as a person, a program, or an event...” Merriam and Tisdell, 2016 p. 24.

Yin talks about unit of analysis and unit of data collection. Very well explained in Yin, 2018.

In the attached image 14.49.00 (Yin, 2003, p. 46) you have the figure where in the single-case study you may (or not) have more than 1 unit of analysis, and the confusing part is that in the multiple case design, you may have more than 1 unit for each one of the cases.

My confusion is between case, unit, embedded unit, and focus of study. I mix them. I downloaded Yin 2018 to read more.

Hope this will help you with the examples that you were asking.

Yin, 2018. Case Study Research and Applications.

Yin, R. K. (2003). Case Study Research, Design and Methods (3rd ed.). Applied Social Research Methods Series 5. Thousand Oaks, CA: SAGE.

Much appreciated Christina!

Debra

I would probably share my recent experience and maybe it can be of help because I also had a design of a multisite study: Three selected African countries in which I analysed 6 newspaper publications (2 from each country). Driven by the kind of question I was interested in (how mediated climate change communication engage diverse subjectivities and allow for a plurality of views), my unit of analyses were not one but "embedded" (to use your Yin's concept). When the interest is on the medialisation process (analysing for the volume of attention to climate change, sections in which the articles appeared and scale of focus), my unit of analysis was the individual newspapers. When my interest shifted to accounting for diverse subjects and their perspectives, my unit of analysis was statements identified in the different newspapers. At the meta-level, the different countries were my unit of analysis as I compared patterns found from the first two stages.

So, to answer your question, your research question is the guiding link to identifying what unit you are to analyse.

I hope this helps!

Yes, thank you so much! I extend best wishes for every success with your publication and citations.

Debra