Objectives After completing this module, you will be able to:

• Understand the kinds of research questions that can be answered through cross sectional designs;
  
• Identify inappropriate or inadequate uses of the cross-sectionaldesigns, including multi-point in time cross-sectional studies which do have a time component but are not equivalent to longitudinal designs;
• Take steps to reduce the threats to internal and external validity inherent in cross-sectional designs, particularly the threats that result from limited ability to anticipate unanticipated or accounted for differences among groups that threaten the validity of results;
• Assess the explanatory power, and internal and external validity of cross-sectional designs;
• Evaluate the quality of sampling strategies used in these designs and develop sampling strategies to help ensure that samples are adequate and that the samples for comparison groups are reasonable;
  
• Create cross-sectional designs to answer research and evaluation questions.
  

Assigned Materials

You must select a cross-sectional design for Assignment 5. Purely descriptive cross-sectional designs will NOT be accepted. Single-group cross-sectional designs will NOT be accepted.

Topic 1: What is a cross-sectional design?

You need to explore the resources about these designs in depth. We are at a point in this class where you should be able to understand and apply the concepts in these last modules well. They should make sense to you now. If they do not, come to class prepared to ask questions. Anything that is not clear to you is probably not clear to others as well.

This piece by the Institute for Work & Health provides a very short explanation of the differences between cross-sectional and longitudinal designs. What Researchers Mean by Cross-Sectional vs. Longitudinal Studies

Slide show Cross Sectional Designs My comments, for what they are worth -- which may not be very much

Have a copy of Comparative Characteristics of Design Groups in class

Some Clarifications about Multiple Comparison Populations in Cross-Sectional Designs This is my cheat sheet about the use of multiple comparison groups.

Topic 2: What can we do to make cross-sectional designs better? Or should we just give them up altogether?

Improving the Internal Validity of Cross-Sectional Designs

Learning Guide to Cross-Sectional Designs

This is another week when it wouldl be good to share a valuable resource with your colleagues. Remember that you must complete and post two of htese reviews to the Sharing Materials discussion board in Canvas. These are graded materiasl (25 possible points). Here are some recommended materials.

There are two articles that can be especially useful for Assignments 4 and 5. The Duncan & Magnuson one really helps you understand the very fundamental differences in what you can conclude, how confident you can be in your conclusions, and how much you can generalize your conclusions if you use non-experimental designs (any non-experimental design, not just a cross-sectional). It is good food for thought. The Wheaton one provides an excellent overview of some of the important limitations of cross-sectional designs. I strongly encourage you to consult these materials as you complete Assignment 5.

Duncan, G.J. & Magnuson, K.A. (2003) The promise of random assignment social experiments for understanding well-being and behavior. Current Sociology 51(5), 529-541. Compares cross-sectionals to experiments -- why you cannot conclude that A causes B.

Wheaton, B. (2003) When methods make a difference. Current Sociology 51(5), 543-571. Insightful piece about some pitfalls with cross-ssectional designs.

Additional Materials with a focus on sampling: Sampling is critical to the internal validity, external validity, and explanatory power of conclusions reached through cross-sectional designs. Consult the appropriate materials from this list for Assignment 5 -- a crucial component in my assessment criteria.

Bennett, C., Khangura, S., Brehaut, J.C. et al. (2011) Reporting guidelines for survey research: An analysis of published guidance and reporting practices. PLoS Medicine 8(8), 1-11. DOI: 10.1371/journal.pmed.1001069.

Bethlemem, J. (2016) Solving the nonresponse problem with sample matching? Social Science Computer Review 34(1), 59-77. DOI: 10.1177/0894439315573926.

DeBoni, R., Do Nascimento Silva, P.L. Bastos, F.I. et al. (2012) Reaching the hard-to-reach: A probability sampling method for assessing prevalence of driving under the influence of drinking in alcohol outlets. PLoS ONE 7(4), 1-9. DOI: 10.1371/journal.pone.0034104.

Dragulis, J.R. & Plaza, C.M. (2009) Best practices for survey research reports revisited: Implications of target population, probability sampling, and response rate. American Journal of Pharmaceutical Education 73(8), 1-3.

Kamholz, B.W., Gulliver, S.B., Helstrom, A. et al. (2009) Implications of participant self-selection for generalizability: Who participates in smoking laboratory research. Substance Use and Misuse 44(3), 343-356. DOI: 10.1080/10826080802345051.

McInroy, L.B. (2016) Pitfalls, potentials and ethics of online survey research: LGBTQ and other marginalized and hard-to-access youths. Social Work Research 40(2), 83-93. DOI: 10.1093/swr/svw005

Miller, P.G., Johnston, J., Dunn, M. et al. (2010) Comparing probabiity and non-probability sampling methods in ecstasy research: Implications for the Internet as a research tool. Substance Use & Misuse 45(3), 437-450. DOI: 10.3109/10826080903452470.

Walia, R., Bhansali, A. Ravikiran, M. et al. (2014) Self weighing and non-probability samples. Indian Journal of Medical Research 140(1), 150-151.