March 15, 2010

Scoop of Ice-cream or Pizza? Choosing the Right Research Method

new janis By Janis Prince Inniss

In the recently published book, The Politics of Black Women’s Hair, I wrote an essay about my evolving experiences and feelings regarding the styling and care of my hair. (Read a sample from the book here.) The book features interviews and recollections of a few other women on the same topic, using what might be akin to a convenience sample. Therefore, the author does not claim that the experiences chronicled in the book are reflective of all black women—they are not generalizable to the entire population.

Do you know what a convenience sample is? A convenience sample, as the name indicates, is based on convenience. Researchers engage the respondents they can rather than trying to reach a particular, representative group of people. And of course, convenience samples may suffer some particularly dramatic biases.

For example, if I passed out surveys in a hospital, maybe my findings would be applicable only to the ill. This might be okay if I only wanted to learn about the ill—in which case I would have to think about whether the people in my convenience sample were a good representation of all sick people—but I would be unable to say anything about others. In other words, a convenience samples lack a major selling point of random samples—generalizability.

clip_image002Back to black women’s hair: How could I approach the topic of black women’s hair as sociological research? (Although your study topic might differ, the process would be the same.)

A first step would be to learn whether other scholars had already studied this topic. It is not helpful to the research community if investigator after investigator repeats the same study with no sense of what has already been done on a topic. Why is this so? Unless I intend to replicate your study and see whether I can get the same results as you did, this would be a waste of time and money.

Sociological research is designed to answer a specific set of questions, so if we already have answers to those questions in the field, we can pursue others; this is a major impetus for researchers to publish their study findings—so that we know what has already been learned. Because many of the questions that sociologists wrestle with are so complex, different researchers may chip away at various aspects of a question, and together those studies can provide a more complete understanding of an aspect of our lives. Therefore, a review of the literature is a good starting point to learn what has been done and what additional questions may remain on a topic.

clip_image004clip_image006Once I had reviewed the sociological literature on black women’s hair, assuming there was either no research already published on the topic, or the previous research did not address the questions I thought of, I would have to consider the appropriate research methodology for the type of questions I want to pose.

Do I want to learn about the experiences and attitudes of these women regarding their hair, for example? Am I interested in what most women think or feel? Or do I want an in-depth understanding of the experiences of some women? Do I want a scoop of Neapolitan ice cream or a slice of pizza? With this less than perfect analogy, I’m comparing a pizza to the survey I could do. I could find out how most black women think and/or feel about their hair and be able to report things like: “Eighty percent the women surveyed felt X Y Z.” I could get a “thin view” of this issue, and if I chose a representative sample, I could generalize the findings to all black women.

Another possibility is to conduct some in-depth interviews with women and get a “thick description” of their experiences with hair (not only how they feel for example, but I could learn what kinds of experiences may have formed their current perspective). I liken this to a scoop of ice-cream: When I take a scoop of Neapolitan ice-cream, because I don’t like it, I try to avoid the chocolate. So my scoop, although “thick,” is not truly representative of all the ice-cream in that container. A third possibility would be to use a mixed methods approach – have pizza and ice-cream—conduct some clip_image008interviews and also collect survey data.

Methodological purists on either side—quantitative and qualitative—engage in huge debates about the merits of each. However, perhaps as a result of my early experiences with sociological research I am open to both. My first forays into research were quantitative and helped me decide to become a sociologist. However, it was when I read Lillian Rubin’s awe-inspiring book, Intimate Strangers: Men and Women Together which is a brilliant example of what careful qualitative research coupled with impeccable writing can produce, that I felt I had found something to help me answer the question I have been asking since I learned to speak: Why?. These experiences have taught me that methodology must be guided by the research questions being examined.

Think of a topic you might be interested in researching; what would an “ice cream scoop” study look like? A “pizza” study?


TrackBack URL for this entry:

Listed below are links to weblogs that reference Scoop of Ice-cream or Pizza? Choosing the Right Research Method:


Hello! I read your blog about survey methods because I am in a sociology class and it helped me greatly understand what a representative and mixed method approach methods of surveying are. Thanks!

This is truly an excellent explanation of mixed method approaches for sociological functions. Thankyou.

Hello. I searched and read your blog about convienence sample and it reminded me of representative sample. They seem to be almost the opposite of eachother. I read that convienence sample does not generalize people into one group where representative does exactly that.

You're welcome. I hope that you all continue to find the postings helpful.

I read your article for a sociology class I am taking and it was very interesting. It's always good to understand how to survey others better to get a wider sample of individuals.

My first forays into research were quantitative and helped me decide to become a sociologist. However, it was when I read Lillian Rubin’s awe-inspiring book,

Very informative post. Thank you for sharing!

"A third possibility would be to use a mixed methods approach – have pizza and ice-cream—conduct some interviews and also collect survey data." ...This is the method I would use, but you're right, it is hard to determine which process would be best.

I read your article for a sociology class I am taking and it was very interesting. It's always good to understand how to survey others better to get a wider sample of individuals.

Great post! I think I'll chose a slice of pizza ;)

Hello. I read your posting for my Sociology online class. I am interested in whether or not the convenience sample is comparable to a random sample? The two seem similar to me. If they are not, could you explain how they are not please? I am just curious and eager to learn.

Your post, overall, I found to be very informative. I strongly agree with you that unless a researcher is attempting to further the same accuracy of the results, he should not repeat the same experiment, but rather create a new linking experiment that truly adds new information for the subject of research as a whole.

I was reading this poat for an assignment for sociology class, and I had just read a chpater in my text book about surveys and research. Your analogies and explanations helped me better understand the surveying and researching processes of sociologists. Thank you for sharing!

I read your post and found that it was very helpful in explaining what a representative sample is, as well as what a mixed example is. Using ice cream as an explanation of a type of sociological research is a creative way on getting people to understand the difference. Thank you for your post!

I'm a writer and can't tell you what a pleasure it was to read a scientific explanation that was so clear and easy to understand. Yet the topic is not transparently simple. Great job!

so is a convenience sample the same as a random sample? How do you decide, representative sample or random sample, when doing an experiment?

I am currently in a Sociology class and felt your essay was written really well. I learned a lot from it. I never understood how much research that you have to go through to get so much information. Using a topic that everybody knows (ice cream) well to illustrate your point was very clever.

I am in a Sociology class, and I found this essay to be very helpful when understanding the different ways to use a survey. Thank you!

Interesting, good information, thanks for sharing

Verify your Comment

Previewing your Comment

This is only a preview. Your comment has not yet been posted.

Your comment could not be posted. Error type:
Your comment has been posted. Post another comment

The letters and numbers you entered did not match the image. Please try again.

As a final step before posting your comment, enter the letters and numbers you see in the image below. This prevents automated programs from posting comments.

Having trouble reading this image? View an alternate.


Post a comment

Become a Fan

The Society Pages Community Blogs

Interested in Submitting a Guest Post?

If you're a sociology instructor or student and would like us to consider your guest post for please .

Norton Sociology Books

The Real World

Learn More

Terrible Magnificent Sociology

Learn More

You May Ask Yourself

Learn More

Essentials of Sociology

Learn More

Introduction to Sociology

Learn More

The Art and Science of Social Research

Learn More

The Family

Learn More

The Everyday Sociology Reader

Learn More

Race in America

Learn More


Learn More

« Research Methods, Statistics, and Video Games | Main | Rethinking Nudity and Deviance »