Survey as a research method

Original Editors - Shaimaa Eldib

Top Contributors - Ammar Suhail, Shaimaa Eldib and Adam Vallely Farrell

Introduction

Survey is a common research method used in health and social care services. Survey research is a form of inquiry that rests on the assumption that meaningful information can be obtained by asking the parties of interest what they know, what they believe, and how they behave.[1]

In survey research, the data usually collected by using standardised form whether by interview or questionnaire. Surveys are designed to give a snapshot of how things are at specific time or condition without any control or manipulation of participants or variables [2].

Definition:

A survey is defined as a “system for collecting information from or about people to describe, compare, or explain their knowledge, attitudes, and behaviour.” [3]

The Process of survey research:

The Survey system comprises seven activities.[3]

  1. Setting objectives for information collection
  2. Designing the study
  3. Preparing a reliable and valid survey instrument
  4. Administering the survey
  5. Managing survey data
  6. Analyzing survey data
  7. Reporting the results

Setting objectives for information collection

It is very important to have a clear objective beforehand. The researcher should identify why he wants to conduct the survey. This step will guide in designing the data collection tool. Various authors consider this as the most important step of survey research.

Study Design

A design is a way of arranging the environment in which a survey takes place. The environment consists of the individuals or groups of people, places, activities, or objects that are to be surveyed.[3] Choosing an appropriate design for any research survey depends on various factors[4]. In literature, there have been various classifications of research designs. Broadly speaking the survey research is a non-experimental design with descriptive nature[5]. Designing a study should always consider the sample of the study. Sample selection usually depends on target population size, its homogeneity and sampling media.

  • Sample size calculation depends on following 5 factors:

- Statistical power

- The ability of the researcher to access target population.

- The Degree of precision required ( to measure precision by the level of significance type 1 error or confidence interval)''

- The Degree of population stratification.

- Selection of analysis unit [6][7].

Designing the Survey Instrument

While planning to design the survey instrument the researcher should look for existing questionnaires available. This will enhance the process of research as it will avoid wastage of time in designing a questionnaire which already exists. When researchers determine that they require unique information for their study, they must develop their own questionnaire. There are five basic steps to questionnaire development: drafting, expert review, first revision, pilot test, and final revision[1].

Administering the survey

There are different ways to adminster surveys ( face to face or telephone interview- mailed surveys using postal or electronic media)[4].

Managing and Analyzing survey data

The survey data can be analyzed in multiple ways. The descriptive and inferential statistics can be used to analyze the data. The statistics or qualitative analysis used depends on the objective of the survey, what sort of information was intended to be gathered by the survey will guide the statistical measure to be used.

Reporting the result

Fair and accurate reporting of survey results means staying within the boundaries set by the survey's design, sampling methods, data collection quality, and analysis. We can use lists, charts, and tables to display your data.[3]

Format of Interviews and Questionnaire Items

The broadest distinction among item types is open-format versus closed format items.[1][3]

Open Format Items

Open-format items permit a flexible response. These are commonly used in interviews and allows a greater breadth of response. The depth of response usually depends on the respondents willingness and articulating capabilities. The major issue that is associated with open format items is the analysis as respondents responses may vary.

Closed-Format Items

Closed-format items restrict the range of possible responses. Mailed questionnaires often include a high proportion of closed-format responses. Highly structured interviews also use closed-format items. There are basically four types of closed-format items:

  1. Multiple Choice
  2. Likert Type
  3. Semantic differential
  4. Q-Sort Items

Methods of collecting Survey Data

Following are the three ways of collecting survey data[1]

  1. Personal Interviews
  2. Mailed Surveys
  3. Internet-based surveys

Personal Interviews

In this method, the researcher conducts personal interviews of the respondents. Interviews can be conducted using different forms of questionnaires and the response can be documented accordingly. Interviews usually achieve greater depth of response, maintain control over who actually responds, determine the opinions of those who cannot read and may have higher response rates.

Mailed Surveys

In this method, the researcher mails the survey tool or questionnaire to the respondent Compared to personal interviews mailed surveys are more economic permit a broader sampling frame and larger numbers of participants. Disadvantages of this method include unavailability of appropriate mailing lists of participants, low response rates, inability to gain information from individuals who cannot read, and lack of control over who actually responds to the questionnaire  

Internet-based Surveys

In this method, the researcher uses the internet to get the responses from the respondents. With the wide availability of the internet in recent time has led to an increase in the use of this method. The most basic way to conduct an Internet-based survey is to send an e-mail to a group of respondents, with the questionnaire embedded within the e-mail. There are softwares available to design the survey and collect information, with use of these survey software the survey can be conducted in an easy and fast way.Following are the advantages and disadvantages of internet-based survey:

Advantages of internet based survey:
  1. Less cost .
  2. Easy access to thousands of social and vocational groups.
  3. Time saving.( In process of data collection and analysis).[8]
Disadvantages of internet based survey:
  1. Sampling problems ( like generating a sampling frame )
  2. Selection bias ( which may affect generalisation of study findings ).
  3. Access issues ( some virtual community users could consider research invitations as a rude behaviour or email may be considered as a spam[8] [9].

References

  1. 1.0 1.1 1.2 1.3 Carter R, Lubinsky J. Rehabilitation Research-E-Book: Principles and Applications. Elsevier Health Sciences; 2015 Jun 30.
  2. Kelley, K., Clark, B., Brown, V. & Sitzia, J. 2003, Good practice in the conduct and reporting of survey research, Oxford :.
  3. 3.0 3.1 3.2 3.3 3.4 Fink A. The survey handbook. Sage; 2003.
  4. 4.0 4.1 Dillman, D.A., Smyth, J.D. and Christian, L.M., 2014. Internet, phone, mail, and mixed-mode surveys: the tailored design method. John Wiley & Sons.
  5. Page P. Research designs in sports physical therapy. International journal of sports physical therapy. 2012 Oct;7(5):482.
  6. Glasow, P.A., 2005. Fundamentals of survey research methodology. Retrieved January18, p.2013.
  7. Barlett, J.E., Kotrlik, J.W. and Higgins, C.C., 2001. Organizational research: Determining appropriate sample size in survey research. Information technology, learning, and performance journal19(1), p.43.
  8. 8.0 8.1 Wright, K.B., 2005. Researching Internet-based populations: Advantages and disadvantages of online survey research, online questionnaire authoring software packages, and web survey services. Journal of computer-mediated communication10(3), p.JCMC1034.
  9. Andrews, D., Nonnecke, B. and Preece, J., 2003. Electronic survey methodology: A case study in reaching hard-to-involve Internet users. International journal of human-computer interaction16(2), pp.185-210.