After you have designed your study, collected your data, and analyzed it, you have to figure out what it means and communicate that to potential interested audiences. This section of the chapter is about how to make sense of your study, in terms of data interpretation, data write-up, and data presentation, as seen in the above diagram.
Once you have run your statistics, you have to figure out what your findings mean or interpret your data. To do this, you need to tie back your findings to your research questions and/or hypotheses, think about how your findings relate to what you discovered beforehand about the already existing literature, and determine how your findings take the literature or current theory in the field further. Your interpretation of the data you collected will be found in the last section of your paper, what is commonly called the "discussion" section.
Your research questions and hypotheses, once developed, should guide your study throughout the research process. As you are choosing your research design, choosing how to operationalize your variables, and choosing/conducting your statistical tests, you should always keep your RQs and Hs in mind.
What were you wanting to discover by your study? What were you wanting to test? Make sure you answer these questions clearly for the reader of your study in both the results and discussion section of the paper. (Specific guidelines for these sections will be covered later in this chapter, including the common practice of placing the data as you present it with each research question in the results section.)
As you have seen in chapter 3 and the Appendix, and will see in chapter 7, the literature review is what you use to set up your quantitative study and to show why there is a need for your study. It should start out broad, with the context for your study, and lead into showing what still needs to be known and studied about your topic area, justifying your focus in the study. It will be brought in again in the last section of the paper you write, i.e., the discussion section.
Your paper is like an hourglass – starting out broad and narrowing down in the middle with your actual study and findings, and then moving to broad implications for the larger context of your study near the end.
One of the things you will write about in your discussion or last section of your paper is the implications of what you found. These implications are both practical and theoretical. Practical implications are how the research can provide practical applications to real-world people and issues. Theoretical implications are how the research takes the current academic literature further, specifically, in relationship to theory-building.
Did any of the research you reviewed for your literature review mention a theory your findings could expand upon? If so, you should think about how your findings related to this theory. If not, then think about the theories you have already studied in your communication classes. Would any of them provide a possible explanation of what you found? Would your findings help expand that theory to a different context, the context you studied? Does a theory need to be developed in the area of your research? If so, then what aspects of that theory could your findings help explain?
All quantitative studies, when written, have four parts. The first part is the introduction and literature review, the second part is the methods section, the third section is the results or findings, and the fourth section is the discussion section. This portion of this chapter will explain what elements you will need to include in each of these sections.
The beginning of your paper and first few pages sets the tone for your study. It tells the reader what the context of your study is and what other people who are also interested in your topic have studied about your topic.
There are many ways to organize a literature review, as can be seen in the following website.
Literature Reviews — The Writing Center at UNC-Chapel Hill
After you have done a thorough literature search on your topic, then you have to organize your literature into topics of some kind. Your main goal is to show what has been done and what still needs to be done, to show the need for your study, so at the end of each section of your literature review, you should identify what still needs to be known about that particular area.
For quantitative research, you should do your literature review before coming up with your research questions/hypotheses. Your questions and hypotheses should flow from the literature. This is different from the other two research methods discussed in this book, which do not rely so heavily on a literature review to situation the study before conducting it.
In the methods section, you should tell your reader how you conducted your study, from start to finish, explaining why you made the choices you did along the way. A reader should be able to replicate your study from the descriptions you provide in this section of your write-up. Common headings in the methods section include a description of the participants, procedures, and analysis.
For the participants' subheading of the methods section, you should minimally report the demographics of your sample in terms of biological sex (frequencies/percentages), age (range of ages and mean), and ethnicity (frequencies/percentages). If you collected data on other demographics, such as socioeconomic status, religious affiliation, type of occupation, etc., then you can report data for that also in the participants' sub-section.
For the procedures sub-section, you report everything you did to collect your data: how you recruited your participants, including what type of sampling you used (probability or non-probability) and informed consent procedures; how you operationalized your variables (including your survey questions, which often are explained in the methods section briefly while the whole survey can be found in an appendix of your paper); the validity and reliability of your survey instrument or methods you used; and what type of study design you had (experimental, quasi-experimental, or non-experimental). For each one of these design issues, in this sub-section of the methods part, you need to explain why you made the decisions you did in order to answer your research questions or test your hypotheses.
In this section, you explain how you converted your data for analysis and how you analyzed your data. You need to explain what statistics you chose to run for each of your research questions/hypotheses and why.
In this section of your paper, you organize the results by your research questions/hypotheses. For each research question/hypothesis, you should present any descriptive statistic results first and then your inferential statistics results. You do not make any interpretation of what your results mean or why you think you got the results you did. You merely report your results.
Reporting Significant Results
For each of the inferential statistics, there is a typical template you can follow when reporting significant results: reporting the test statistic value, the degrees of freedom 3, and the probability level. Examples follow for each of the statistics we have talked about in this text.
"T-tests results show there was a significant difference found between men and women on their levels of self-esteem, t (df) = t value, p < .05, with men's self-esteem being higher (or lower) (men's mean & standard deviation) than women's self-esteem (women's mean & standard deviation)."
"ANOVA results indicate there was a significant difference found between [levels of independent variable] on [dependent variable], F (df) = F value, p < .05."
If doing a factorial ANOVA, you would report the above sentence for all of your independent variables (main effects), as well as for the interaction (interaction effect), with language something like: "ANOVA results indicate a significant main effect for [independent variable] on [dependent variable], F (df) = F value, p < .05. .... ANOVA results indicate a significant interaction effect between [independent variables] on [dependent variable], F (df) = F value, p < .05."
See example YouTube tutorial for writing up a two-way ANOVA at the following website.
For goodness of fit results, your write-up would look something like: "Using a chi-square goodness of fit test, there was a significant difference found between observed and expected values of [variable], χ2 (df) = chi-square value, p < .05." For test of independence results, it would like like: "Using a chi-square test of independence, there was a significant interaction between [your two variables], χ2 (df) = chi-square value, p < .05."
"Using Pearson's [or Spearman's] correlation coefficient, there was a significant relationship found between [two variables], r (df) = r value, p < .05." If there are a lot of significant correlation results, these results are often presented in a table form.
For more information on these types of tables, see the following website:
Reporting regression results is more complicated, but generally, you want to inform the reader about how much variance is accounted by the regression model, the significance level of the model, and the significance of the predictor variable. For example:
A regression analysis, predicting GPA scores from GRE scores, was statistically significant, F(1,8) = 10.34, p < .05.
The regression equation is: Ŷ = .411 * .005X. For every one unit increase in GRE score, there is a corresponding increase in GPA of .005 (Walen-Frederick, n.d., p. 4).
For more write-up help on regression and other statistics, see the following website location:
Multiple Regression (pp. 217-220)
Reporting Non-Significant Results
You can follow a similar template when reporting non-significant results for all of the above inferential statistics. It is the same as provided in the above examples, except the word "non-significant" replaces the word "significant," and the p values are adjusted to indicate p> .05.
Many times readers of articles do not read the whole article, especially if they are afraid of the statistical sections. When this happens, they often read the discussion section, which makes this a very important section in your writing. You should include the following elements in your discussion section: (a) a summary of your findings, (b) implications, (c) limitations, and (d) future research ideas.
Summary of Findings
You should summarize the answers to your research questions or what you found when testing your hypotheses in this sub-section of the discussion section. You should not report any statistical data here, but just put your results into narrative form. What did you find out that you did not know before doing your study? Answer that question in this sub- section.
You need to indicate why your study was important, both theoretically and practically. For the theoretical implications, you should relate what you found to the already existing literature, as discussed earlier when the "hourglass" format was mentioned as a way of conceptualizing your whole paper. If your study added anything to the existing theory on a particular topic, you talk about this here as well.
For practical implications, you need to identify for the reader how this study can help people in their real-world experiences related to your topic. You do not want your study to just be important to academic researchers, but also to other professionals and persons interested in your topic.
As you get through conducting your study, you are going to realize there are things you wish you had done differently. Rather than hide these things from the reader, it is better to forthrightly state these for the reader. Explain why your study is limited and what you wish you had done in this sub-section.
The limitations sub-section usually is tied directly to the future research sub-section, as your limitations mean that future research should be done to deal with these limitations. There may also be other things that could be studied, however, as a result of what you have found. What would other people say are the "gaps" your study left unstudied on your topic? These should be identified, with some suggestions on how they might be studied.
There are other parts of the academic paper you should include in your final write-up. We have provided useful resources for you to consider when including these aspects as part of your paper. For an example paper that uses the required APA format for a research paper write-up, see the following source:
Varying Definitions of Online Communication.
Abstract & Titles.
Tables, References, & Other Materials.
You will probably be called upon to present your data in other venues besides in writing. Two of the most common venues are oral presentations such as in class or at conferences, and poster presentations, such as what you might find at conferences. You might also be called upon to not write an academic write-up of your study, but rather to provide an executive summary of the results of your study to the "powers that be," who do not have time to read more than 5 pages or so of a summary. There are good resources for doing all of these online, so we have provided these here.
Congratulations! You have learned a great deal about how to go about using quantitative methods for your future research projects. You have learned how to design a quantitative study, conduct a quantitative study, and write about a quantitative study. You have some good resources you can take with you when you leave this class. Now, you just have to apply what you have learned to projects that will come your way in the future.
Remember, just because you may not like one method the best does not mean you should not use it. Your research questions/hypotheses should ALWAYS drive your choice of which method you use. And remember also that you can do quantitative methods!
[NOTE: References are not provided for the websites cited in the text, even though if this was an actual research article, they would need to be cited.]
Baker, E., Baker, W., & Tedesco, J. C. (2007). Organizations respond to phishing: Exploring the public relations tackle box. Communication Research Reports, 24 (4), 327-339.
Benoit, W. L., & Hansen, G. J. (2004). Presidential debate watching, issue knowledge, character evaluation, and vote choice. Human Communication Research, 30 (1), 121-144.
Chatham, A. (1991). Home vs. public schooling: What about relationships in adolescence?Doctoral dissertation, University of Oklahoma.
Cousineau, T. M., Rancourt, D., and Green, T. C. (2006). Web chatter before and after the women's health initiative results: A content analysis of on-line menopause message boards. Journal of Health Communication, 11(2), 133-147.
Derlega, V., Winstead, B. A., Mathews, A., and Braitman, A. L. (2008). Why does someone reveal highly personal information?: Attributions for and against self-disclosure in close relationships. Communication Research Reports, 25, 115-130.
Fischer, J., & Corcoran, K. (2007). Measures for clinical practice and research: A sourcebook (volumes 1 & 2). New York: Oxford University Press.
Guay, S., Boisvert, J.-M., & Freeston, M. H. (2003). Validity of three measures of communication for predicting relationship adjustment and stability among a sample of young couples. Psychological Assessment, 15(3), 392-398.
Holbert, R. L., Tschida, D. A., Dixon, M., Cherry, K., Steuber, K., & Airne, D. (2005). The West Wing and depictions of the American Presidency: Expanding the domains of framing in political communication. Communication Quarterly, 53 (4), 505-522.
Jensen, J. D. (2008). Scientific uncertainty in news coverage of cancer research: Effects of hedging on scientists' and journalists' credibility. Human Communication Research, 34, 347- 369.
Keyton, J. (2011). Communicating research: Asking questions, finding answers. New York: McGraw Hill.
Lenhart, A., Ling, R., Campbell, S., & Purcell, K. (2010, Apr. 10). Teens and mobile phones. Report from the Pew Internet and American Life Project, retrieved from http://www.pewinternet.org/Reports/2010/Teens-and-Mobile-Phones.aspx.
Maddy, T. (2008). Tests: A comprehensive reference for assessments in psychology, education, and business. Austin, TX: Pro-Ed.
McCollum Jr., J. F., & Bryant, J. (2003). Pacing in children's television programming. Mass Communication and Society, 6 (2), 115-136.
Medved, C. E., Brogan, S. M., McClanahan, A. M., Morris, J. F., & Shepherd, G. J. (2006). Family and work socializing communication: Messages, gender, and ideological implications. Journal of Family Communication, 6(3), 161-180.
Moyer-Gusé, E., & Nabi, R. L. (2010). Explaining the effects of narrative in an entertainment television program: Overcoming resistance to persuasion. Human Communication Research, 36, 26-52.
Nabi, R. L. (2009). Cosmetic surgery makeover programs and intentions to undergo cosmetic enhancements: A consideration of three models of media effects. Human Communication Research, 35, 1-27.
Pearson, J. C., DeWitt, L., Child, J. T., Kahl Jr., D. H., and Dandamudi, V. (2007). Facing the fear: An analysis of speech-anxiety content in public-speaking textbooks. Communication Research Reports, 24(2), 159-168.
Rubin. R. B., Rubin, A. M., Graham, E., Perse, E. M., & Seibold, D. (2009). Communication research measures II: A sourcebook. New York: Routledge.
Serota, K. B., Levine, T. R., and Boster, F. J. (2010). The prevalence of lying in America: Three studies of reported deception. Human Communication Research, 36, 1-24.
Sheldon, P. (2008). The relationship between unwillingness-to-communicate and students' facebook use. Journal of Media Psychology, 20(2), 67–75.
Trochim, W. M. K. (2006). Reliability and validity. Research methods data base, retrieved from http://www.socialresearchmethods.net/kb/relandval.php.
Walen-Frederick, H. (n.d.). Help sheet for reading SPSS printouts. Retrieved from http://www.scribd.com/doc/51982223/help-sheet-for-reading-spss-printouts.
Weaver, A. J., & Wilson, B. J. (2009). The role of graphic and sanitized violence in the enjoyment of television dramas. Human Communication Research, 35(3), 442-463.
Weber, K., Corrigan, M., Fornash, B., & Neupauer, N. C. (2003). The effect of interest on recall: An experiment. Communication Research Reports, 20(2), 116-123.
Witt, P. L., & Schrodt, P. (2006). The influence of instructional technology use and teacher immediacy on student affect for teacher and course. Communication Reports, 19(1), 1-15.
3 Degrees of freedom (df) relate to your sample size and to the number of groups being compared. SPSS always computes the df for your statistics. For more information on degrees of freedom, see the following web-based resources:
http://www.youtube.com/watch?v=wsvfasNpU2s and http://www.creative-wisdom.com/pub/df/index.htm.