Week 5: Secondary Analysis of Archived Data

Secondary Analysis of Archived Data

Consider the scenario from the Week 4 Introduction. Imagine once again that you are a public health professional attempting to gather data to help answer a research question. Is there a link between diabetes and vision problems within the Taos Pueblo population in New Mexico? You decide to mail a written survey to this target population. The survey includes questions on diet, exercise, health and vision problems, and other related variables. What might threaten the validity of these self-reported data? What other types of secondary archived data sets might be helpful to you and your organization in answering your research question? What might you need to consider in terms of the validity and integrity of these data sets?

This week, you examine possible threats to the validity and integrity of self-reported data, as well as the benefits and limitations of self-reported data. You explore strategies for overcoming the limitations of secondary data. In addition, you explore the process for conducting a secondary analysis of archived data (SAAD) based on evaluating identified data sets for validity and integrity.

 

SDA/SAAD involves manipulation of raw data to answer a unique research question (one not previously answered by the originators of the datafile,  not just gleaning information from a report (which represents descriptive statistics) or a website or peer reviewed article.   If you took these courses, you may revisit your notes and coursework on SDA/SAAD from these courses as a refresher and to assist you in completing the assignments on SDA/SAAD for this course.

 

Students will:

• Evaluate threats to validity of self-reported data
• Analyze benefits and limitations of secondary data
• Apply strategies to overcome limitations of secondary data
• Evaluate data sets for validity and integrity
• Analyze processes for determining data set integrity.
• In addition to collecting data through archived databases, researchers often employ qualitative or quantitative studies to collect information directly from individuals within a target population. This is called self-reported data, and it may be prospective or retrospective. It might seem that the individuals taking a survey about their own health would have the most valid data on the subject. But is this true? What aspects of self-reported data might threaten validity??

 

RESOURCES/REQUIRED READINGS:

 

1)Smith, A. K., Ayanian, J. Z., Covinsky, K. E., Landon, B. E., McCarthy, E. P., Wee, C. C., & Steinman, M. A. (2011). Conducting high-value secondary dataset analysis: An introductory guide and resources. Journal of General Internal Medicine, 26(8), 920–929.

 

HERE is the LINK to this Resource article https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3138974/

 

2) Look at the following links databases

Centers for Disease Control and Prevention. (2011). About the National Center for Health Statistics. Retrieved from http://www.cdc.gov/nchs/about.htm

Centers for Disease Control and Prevention. (2015). Accessing data from the National Center for Health Statistics. Retrieved from https://www.cdc.gov/nchs/data_access/index.htm

Centers for Disease Control and Prevention. (2012b). Public-use data files and documentation. Retrieved from http://www.cdc.gov/nchs/data_access/ftp_data.htm

Centers for Disease Control and Prevention. (2012c). Surveys and data collection systems. Retrieved from http://www.cdc.gov/nchs/surveys.htm

Centers for Disease Control and Prevention. (2013c). SMART: BRFSS city and county data and documentation. Retrieved from http://www.cdc.gov/brfss/smart/smart_data.htm

Centers for Disease Control and Prevention. (2014a). Behavioral risk factor surveillance system. Retrieved from http://www.cdc.gov/brfss/

Centers for Disease Control and Prevention. (2014b). National Survey of Family Growth. Retrieved from http://www.cdc.gov/nchs/nsfg.htm

Grady, D. G., Cummings, S. R., & Hulley, S. B. (2013). Designing Clinical Research (4th Edition). Wolters Kluwer. Retrieved July 25, 2015, from http://freecontent.lww.com/wp-content/uploads/2015/09/Chapter-13-Research-Using-Existing-Data.pdf

Inter-University Consortium for Political and Social Research. (n.d.). ICPSR: Find and analyze data. Retrieved December 31, 2014, from http://www.icpsr.umich.edu/icpsrweb/ICPSR/

Kornegay C, Segal JB. Selection of Data Sources. In: Velentgas P, Dreyer NA, Nourjah P, et al., editors. Developing a Protocol for Observational Comparative Effectiveness Research: A User’s Guide. Rockville (MD): Agency for Healthcare Research and Quality (US); 2013 Jan. Chapter 8. Retrived from: http://www.ncbi.nlm.nih.gov/books/NBK126195/

Partners in Information Access for the Public Health Workforce. (n.d.). Health data tools and statistics. Retrieved December 31, 2014, from http://phpartners.org/health_stats.html#National%20Public%20Health%20Data%20Sets

Substance Abuse and Mental Health Data Administration. (n.d.). Substance abuse and mental health data archive. Retrieved December 31, 2014, from http://www.icpsr.umich.edu/icpsrweb/SAMHDA/download

U.S. Department of Health and Human Services. (n.d.). National Center for Chronic Disease Prevention and Health Promotion—NCCDPHP Centers for Disease Control and Prevention. Retrieved December 31, 2014, from http://healthfinder.gov/FindServices/Organizations/Organization.aspx?code=HR0069

 

Assignment: Final Project: Stage II—Secondary Analysis of Archived Data (SAAD)

Data sets often are compiled for the purposes of original research or recordkeeping. Researchers, such as those in the field of public health, may choose to do their own original research. This prospective research might be quantitative or qualitative. It might take the form of self-reported surveys or many other types of research.

However, not all researchers have the time or the budget to conduct their own thorough research. Instead, they might have to use preexisting data. However, not all databases are collected for research purposes. The data may have been collected for recordkeeping. Either way, researchers might find such databases germane to their own research and research questions. This fresh analysis of existing data in order to answer a research question is considered secondary analysis of archived data (SAAD). A SAAD is a retrospective study and is usually quantitative; however, there is a trend to conduct SAADs with qualitative archived data.

Three essential questions about the database relating to study feasibility must be answered before proposing or initiating a SAAD:

1. Will I have access to the data to conduct the analysis? (Some databases are in the public domain, whereas others are privately owned and require that permission be obtained from the owner to use.)
2. Does the database include the variables of interest for my study? (Are the variables that I want to explore or analyze actually included in the data set?)
3. Can the validity and integrity of the data be verified?

For this week’s Assignment, from the Learning Resources or your own research, identify local and national health-related data sources related to your Final Project. You may use data that are maintained and collected by a community based organization but that have not been analyzed. You may use any available data set to which you have access. You are also free to use any statistical software with which you are familiar.

 

 

 

Submit a 2- to 3-page paper in which you:

 

• Explain how the data set relates to your Final Project.
• Evaluate the data set for validity and integrity. Explain whether the data are valid and reliable and justify your response.
• Explain possible strategies for overcoming the limitations of the secondary data.
• Explain the process for selecting a data set and determining its integrity. Provide a rationale for your answer.

Support your work with specific citations from this week’s Learning Resources and additional scholarly sources as appropriate. Refer to the Essential Guide to APA Style and ensure that your in-text citations and reference list are correct.

 

Here is MY CHOSEN TOPIC (Obesity In ADULTS rural West Virginia) and I attached My Annotated Bibliography I have already done on the topic last week.

As you can see below I chose BRFSS, as my dataset for Obesity and you must address all the Assignment Instrcuct. onObesity in ADULTS and BRFSS dataset; therefore you must address these points ON MY OBESITY in ADULTS rural WV and on BRFSS dataset:

Submit a 2- to 3-page paper in which you:

 

• Explain how the data set relates to your Final Project (See above for my TOPIC and DATASET)
• Evaluate the data set for validity and integrity. Explain whether the data are valid and reliable and justify your response.
• Explain possible strategies for overcoming the limitations of the secondary data.
• Explain the process for selecting a data set and determining its integrity. Provide a rationale for your answer.

 

I want you to design the Assignment in this way: YOU copy paste each title point REQUESTED ABOVE in the Assignment and you address it under the title in few paragraphs; example:

 

Explain how the data set relates to your Final Project—.>You address this under this title in 1-2 paragraphs

 

Evaluate the data set for validity and integrity. Explain whether the data are valid and reliable and justify your response.—.> You address this under this title in few paragraphs

 

Explain possible strategies for overcoming the limitations of the secondary data-à You address this under this title in few paragraphs

 

Explain the process for selecting a data set and determining its integrity. Provide a rationale for your answer-à You address this under this title in few paragraphs