Causation, Comparative, Correlation...'C' words for all!

Gosh, Susanne. You weren't lying when you said this blog would be a toughie. I think the reason I find it so difficult is because my natural inclination is to infer causation when I'm reading a comparative, or especially correlative study. While reading a few articles to prepare for my lit review (and for this blog entry), I've had to catch myself not assuming that one variable automatically causes the other. I don't know what innate in all human being that makes us want to do that...but something is and it has got to be stopped.

In a study that examined family instability, school context, and the academic careers of adolescents, Cavanaugh and Fomby desired to discover a correlation between family instability (changes in the family structure any time during the child's life up to the present point) and the type of courses a student takes in high school. These researchers used data from the National Longitudinal Study of Adolescent Health and a research study from UNC to form a list of participants and parents. The parents were then given an in-home interview to self-report the family structure changes. Academic transcript were used as data for the type of coursework track the student was on, specifically focusing on the math trajectory. In addition, the school context was evaluated by means of the proportion of families within the school who had experienced at least one family structure transition.

Results showed multiple correlations between the three variables, but for this blog, I'd like to zero in on the correlation that was found between school-level family instability and the math course trajectories. The findings indicate that adolescents in schools with low exposure to family instability were more likely to be on time (paced) with the ninth grade math course enrollment. By the end of high school, the majority of students from these school contexts (84%) completed college-prep math courses. Like I mentioned above, it is hard for me (and I'm sure others) to not take that finding and draw an assumption that families that exhibit stability cause adolescents to be a higher level trajectory in school courses, particularly math.

This automatic inference is dangerous and potentially misleading. There are a number of other variables that need to be considered (average SES of the families in the school, parental education, teachers in the high schools and feeder schools--to name a few) because they may have a factor in the causation. Additionally, who's to say that the student's trajectory isn't causing the family instability (ok, maybe this isn't the best study to illustrate this point, but another danger in making a causation inference is the uncertainty of the direction of the possible causation). Implying causation in a correlational study is far from the purpose of it, which is just to determine if a relationship exists. Inferring causation then not only is ignorant, but minimizes the beauty that is research methods.

Maybe one day researchers can unite and change the license plate to say...NO CAUSATION FROM CORRELATION!

Ethics!

Educational researchers can dance a fine line of ethical and unethical behavior. Even when there is no attempt to act in an unethical manner, precautions must be made to ensure that the participants in each study are being treated with dignity, respect, and rights that all human beings deserve. Thankfully, there are a few organizations who have devoted time in developing guidelines that can be upheld while designing and administering research with humans.

I think the most critical of these guidelines for all researchers to keep in mind while preparing and conducting their research is honesty. Researchers should inform their participants of all parts of the research study before the participant consents to his/her participation. This allows the participant to make an informed decision as to if he/she really wants to have a role in the research and the data that is collected. If the researcher neglects to disclose all aspects of the research, he/she may lose the participant and either results may be skewed or incomplete, causing the researcher to lose time and money.

In the same regard, I think it is of utmost importance that researchers always allow for participants to remain voluntary in the entire research process. From the very beginning, no human being should ever be forced to participate against their will. Likewise for the entirety of the study. If a participant feels as if he/she should no longer have a role in the research, the participant should have the freedom to discontinue his/her participation.

Finally, all participants' confidentiality should be honored. At no point during or after the study should a participant feel as if his/her identity could be exposed. For the respect of the participant, confidentiality should never be jeopardized, unless there was a specific disclaimer was clearly communicated and agreed upon by each participant before the study began.

Calling All Participants!

What's a research study without participants??? Some would say, "well, that's no study at all". I agree...especially in the social science field. So to examine the research question--how do adolescent females perceive their single parent homes affecting their school performance?--we're going to have to get some participants. So a-sampling we will go...

But first, here's a little background on the study before we dive into the pros and cons of each sampling method (and the WINNING sampling procedure). My hope in this study is to discover the perceptions early and middle adolescent girls have regarding the effects their single parent homes have on their school performance (which includes grades, attendance, involvement in activities). The purpose of this study is to not generalize that every adolescent girl has a certain perception regarding their home life's influence on their school life. However, the intent is to gain knowledge and understanding of the beliefs these girls have pertaining to the relationship of their single parent homes and school performance to better support these students by either supplying interventions or resources. Ok, so now really, a-sampling we will go...

Simple Random Sampling: Simple random sampling is a probability sampling method used to give every member of the population the same chance of being selected. To do this type of sampling, I would have to make a list of every middle and high school female student who lives in a single parent home in all of America. Although it would give a vast representation of the sampling population, it would not be a wise use of time (or money...if I was getting paid to do this) to develop the list alone--and then contact all of the randomly selected participants. On top of that, I can't even begin to imagine to interview (the planned methodology) all the participants. Simple random sampling, you are not this researcher's friend.

Systematic Sampling: Like simple random sampling, systematic sampling is another probability sampling. The difference between this procedure and the previous one is that every nth member of the list is selected. Again, what a spectrum of responses that could lead to a broad understanding of exactly what adolescent girls from single parent homes need in the school to support them, BUT the time it would take to develop the list and then contact every nth name from the list of all middle school and high school girl students whose home life consists of one parents would be unfathomable. Thank you systematic sampling for existing...just not for this research question.

Stratified Sampling: Like the name denotes, this method of probability sampling involves identified subgroups of the population. If I wanted to analyze the difference between early ( approximately middle school aged) and middle (approximately high school aged) adolescent girls, then this sampling technique would be useful in ensuring that an adequate number from both groups were selected for sampling (proportional stratified sampling). For the purposes of this particular study, that isn't a variable I am considering, so it wouldn't be that useful. Also, since stratified sampling is an probability sampling, the big ol' list would have to still be made encompassing the population of all adolescent girls hailing from single parent homes. Thanks, but no thanks, stratified sampling.

Cluster Sampling: Cluster sampling is our last look at probability sampling. The catch of cluster sampling is that it is used when a list of individuals doesn't exist by selecting naturally occurring groups (i.e. middle and high schools---DING DING DING!!!). Though a list of all middle school and high school females from single parent homes COULD possibly exist, the reality of it ever coming into fruition is VERY slim to none. This gives cluster sampling a leg up on the others. It would be MUCH easier (and wiser with time and money) to choose a state (like Virginia, for instance), and list all the school districts, then all the middle and high schools from the school districts, and randomly selecting one of each to contact. After contacting them, a list of the names given will be created, and this is where the final random selection will happen. SHEESH! That still seems like a lot of work, though it could give a comprehensive understanding. Cluster sampling, you feel so right, but you're still so wrong!

Convenience Sampling: This is our first look at non-probability sampling. Convenience sampling is a less time-consuming and costly procedure, allowing the researcher to choose an available sample of participants. Anything with the word "convenient" in the name is something I tend to be a fan of. Unfortunately, for this study, a convenience sample wouldn't allow for the specific criteria (adolescent female, single parent home) to be addressed. Convenience sampling=just not that convenient for this study.

Quota Sampling: The second type of probability sampling is quota sampling. This involves the researcher selecting a sample that would represent an entire population. I like the method because instead of the dreaded "list" (see above), it would allow for a geographic area, e.g., Richmond City or Henrico County, to be selected, and to obtain names from chosen schools in those districts. However, the representation of the entire population isn't necessarily a goal of this research study, so it would save time (and again, potentially money) if I went with...(DRUMROLL)...

Purposive Sampling: This is the chosen sampling procedure I would utilize for this research study. Purposive sampling, the final non-probability method, gives the researcher the freedom to select the participants knowing that they would be particularly informative. Since the criteria of the participants gets specific and can be a somewhat sensitive topic for adolescent females to talk about, utilizing purposive sampling makes the most since for time purposes and to receive a better result. So congratulations, purposive sampling--you do serve a purpose in this research study!

True Confession: I kind of like the idea of a lit. review

The phrase "literature review" is one that may get a lot of yawns, drooping eyelids, and tilting heads. As nerdy and shameful as it is to proclaim this to the entire cyber-universe, my response is actually one that is quite different. Call me crazy, but my nosey and curious nature LOVES to find out as much knowledge as possible. So, though I've never really conducted a search for a lit. review before, I'm kind of a bit excited to begin (until I hit the wall of frustration or monotony...whichever comes first). I plan for my extensive lit. review to look something like this:

Step One. Pull out the trusty ol' laptop, go to library.vcu.edu, and start typing in those keywords and search terms into that blank slot. Press enter and watch the results start piling up. Change the search topics with as many synonyms are other related words and combinations of words as possible. Write down as many periodicals, books, and other materials that appear to have ANYTHING to do with the topic at hand, including library call numbers.

Step Two. After the seat belt is fastened, start the car and take off for Cabell Library. Begin the scavenger hunt, finding the previously searched for materials. Gather them together and hunker down at a table with a warm cup o' joe (it could be a long night).

Step Three. Start the "rummaging" process with secondary sources. These sources are helpful in offering a focus to the topic and further references. Begin a list of all primary sources the secondary sources are providing that could be of further benefit to the literature review. With laptop at hand, search for the references. If they are available at the library, leave the cup o' joe behind and go on a mission to get these sources!

Step Four. At this point, the glasses are out (tired eyes can be a poor combination with a tired body and/or body). Let the search continue! Go to the indexes in the books. If there are sub-topics that are more relevant to the research topic, start with those. Extend search to other pages of books and articles, as needed. Highlighting tape and a photocopier are helpful in this process. Gather as much info as possible.

Step Five. CITE ALL SOURCES IN A WORD DOCUMENT USING APA FORMAT!

Step Six. (Can be done in the comfort of home or in the library) Go to my.vcu.edu webpage. After logging in, click on the library tab, the "VCU Libraries My Search Tools" link. Since this is the first time I have ever used this lovely little future (I mean, seriously, VCU people. After investing thousands of dollars, what more does a girl need to do to learn about these sort of tricks of the trade), I would begin adding databases to my database clipboard. After clicking on my fair share of "+" signs, the search can commence!

Step Seven. Much like the library search, use as many synonyms and related terminology to pull up as much info concerning the topic as possible. Make a mental note that the most credible research will be in a peer-reviewed journal, so focus in on these periodicals more than others. I will have hit the jackpot if articles come up with a full text option. If an article does not have a full text option, I will hopefully get an ounce of inspiration to take an additional trip back to the library to go on a wild goose chase once again.

Step Eight. After browsing the found articles (being careful not to spend any time on the introduction and conclusion with a more intense look at results and methods), use highlighters to emphasize the important and relevant information.

Step Nine. CITE ALL SOURCES IN A WORD DOCUMENT USING APA FORMAT

Step Ten. Now that sources have been gathered and information has been found, summarize each source using note cards or half sheets of paper, include the in-text APA citation format with each summary. Once summaries have been completed, arrange them in a logical flow and progression. I plan to be very critical and only use research that is applicable to the research question and its development. If there are gaps that seem to be missing the flow of the lit. review, go back to Step Two or Step Six and search for the missing pieces, using adequate search terminology. Examine these new pieces of the literature review puzzle and write their summaries. Work them into literature review flow.

Step Eleven. Write the review!

Step Twelve. Celebrate the amazing accomplishment of writing a lit. review!