Survey’s Perceptions and Biases

How true are your findings

Researcher have the choice to collect the data manually or use a computerized method. Each method has advantage and disadvantages. Computerized methods are more convenient especially for large number of data but adds complication to data entry since it involve computer knowledge and data analysis skills. The researcher would have to select which computerized method suitable for the research, and how powerful its analysis abilities versus the needed data refinements. The computerized method should not affect the data validity, but should be chosen to replace repetitive and tedious work (Kondracki, Wellman, & Amundson, 2002).

Strickland et al. (2003) discuss the need to have a valid online-based survey and stress that, similar to pencil and paper survey, the online-based survey needs creativity, expertise and good planning to harness the benefits of online-based survey. One-on-one interview allow the interviewer to ask clarification and follow up questions during the interview. The online-based qualitative survey may be improved by a follow up e-mail to clarify some points but the follow up answer would not be as accurate and related as the one-on-one interview.

Perceptions and Biases

Perceptions

Qualitative survey strength depend on the interviews and the open-ended questions asked during the interview. The researcher will ask and expect a different answer every time during the interview. The answers might be worded differently but the researcher would be able to interpret the answer to reach similar results. The challenge is to avoid being biased or steering the answers to the wanted outcome. Bias is defined “as the absence of a balanced presentation of information”(Cooper, 2003, p. 284). Another definition by Cooper (2003) state that bias is “the distortion of responses in one direction” (p. 372). This distortion or unbalance in the interview information could lead to wrong conclusion and results.

Preconceptions are common in qualitative research since the researcher had done a literature review and created a concept in his or her mind that will influence the interview’s outcome. Cohen and Carbtree (2008) stated that publications agree on researchers bias existence and recommend that researchers consider avoiding it during their interviews. Cohen and Carbtree (2008)  admit the difficulty in managing research bias and state that “managing bias was quite different depending on the paradigm grounding the work.” (p. 333). The biases and data irregularity can be identified and removed by one or more of the following methods:

1. Triangulations which involve multiple data sources;
2. Peer review which require sending the outcome to expert for review and validation;
3. External auditing by having a researcher not involved in the research to examine the research process and product;
4. Letting one of the survey population’s member to valuating the data.

What do you see in the data

Shank (2006) stressed that the researcher should reflect on the interviewee’s answers to look for the truth without letting his or her feelings interfere. Shank (2006) state that the interviewer should be ready to hear new ideas and feedback that he or she did not expect to hear. The researcher should practice self-disciple to strain himself or herself from leading the participant to a favorite answer.  Larger population sample would dilute the personal relationship reason the researcher might have with the survived population. The researcher might sympathies with a group because of the longtime spent during the research with them. But if larger sample is interviewed the researcher’s bias could be reduced.

One way to do it is by reviewing the questionnaire by peers to identify and remove biases (Cohen & Crabtree, 2008). Survey protocol should also help if  such protocol is available (de Boer, Wind, van Dijk, & Willems, 2009).

Planning The Survey

Take your research seriously

Good planning and structured survey will lead to consistency in asking question and similar understanding from the participant side. Available Interview protocol and written consent would help in reducing the interview bias. Smith (2008) stress the importance of explaining the survey to the participant clearly and he notice the comments the participant make on the survey questionnaire. A good method can be used to remove the researcher’s bias is the interview transcript review (ITR) process which mandate transcribing the interview and presenting it to the interviewee for review and further confirmation, addition or deletion. The advantage of ITR would be the accuracy of the information but the review might result in altering or deleting important information that was exchanged during the verbal interview (Hagens, Dobrow, & Chafe, 2009).

Data analysis according to Baptiste (2001) go through capturing the data, record it, interpret the data to suggest the information. These steps of data analysis are the first phase of the data analysis technique as stated by Baptiste (2001). The researcher start classifying the data by tagging and grouping after its information became clear to the researcher. The last step would be connecting between the tagged data to build a theme (Baptiste, 2001), the last step is set at the end but actually starts during the data collection and continue until the theme is completed. The researcher would be relating data and analyzing it as long as he or she is working with the data. The analysis include selecting an instrument. Data research outcome would be the try to answer the research questions (Creswell, 2005) and relating the resulting conclusion to existing published research.

See also in this blog:

• Research Overview
• Quantitative or Qualitative
• Preparing the Survey

References

Baptiste, I. (2001). Qualitative data analysis: Common phases, strategic differences. [Article]. Forum: Qualitative Social Research, 2(3), 193-206.

Cohen, D. J., & Crabtree, B. F. (2008). Evaluative criteria for qualitative research in health care: Controversies and recommendations. Annals Of Family Medicine, 6(4), 331-339.

Cooper, D., & Schindler, P. (2003). Business Research Methods (8th ed.): The McGraw−Hill.

Creswell, J. W. (2005). Educational research: Planning, conducting, and evaluating quantitative and qualitative research (2 ed.). Upper Saddle River, N.J.: Merrill Prentice-Hall.

de Boer, W. E. L., Wind, H., van Dijk, F. J. H., & Willems, H. H. B. M. (2009). Interviews for the assessment of long-term incapacity for work: a study on adherence to protocols and principles. [Article]. BMC Public Health, 9, 1-8. doi: 10.1186/1471-2458-9-169

Hagens, V., Dobrow, M. J., & Chafe, R. (2009). Interviewee transcript review: Assessing the impact on qualitative research. BMC Medical Research Methodology, 9, 47-47.

Kondracki, N. L., Wellman, N. S., & Amundson, D. R. (2002). Content analysis: review of methods and their applications in nutrition education. Journal Of Nutrition Education And Behavior, 34(4), 224-230.

Shank, G. D. (2006). Qualitative research: A personal skills approach (2nd ed.). Columbus: Pearson Prentice Hall.

Smith, M. V. (2008). Pain experience and the imagined researcher. Sociology of Health & Illness, 30(7), 992-1006.

Strickland, O. L., Moloney, M. F., Dietrich, A. S., Myerburg, S., Cotsonis, G. A., & Johnson, R. V. (2003). Measurement issues related to data collection on the World Wide Web. ANS. Advances In Nursing Science, 26(4), 246-256.