SURVEY RESEACRH DESIGN

Survey research designs are procedures in quantitative research in which investigators administer a survey to a sample or to the entire population of people to describe the attitudes, opinions, behaviors, or characteristics of the population.

When Can One Use Survey Research design?

One can use survey research design when they want to describe trends, such as:

·        Community interests in school bond issues or state.

·         National trends about mandatory student uniform policies.

You also can use survey research design to determine individual opinions about policy issues, such as whether students need a choice of schools to attend.

A brief History of a survey research design.

Surveys have been widely used in education for many years. Early surveys date back to 1817, when Marc Antoine Julien de Paris designed a 34-page international survey of national education systems (De-Landsheere, 1988). In the 1890s, G. Stanley Hall surveyed children, and by 1907, the Pittsburgh Survey examined social problems, including educational issues ranging from educational planning for school buildings to issues of children in classrooms who are slow learners (Bogdan & Biklen, 1998).During the period from World War I to World War II, the modern survey as we know it began to emerge. Factors that contributed to its development were improvements in sampling techniques and the development of different scales of measurement. Surveys found wide application in many social science fields, including marketing research, journalism, public opinion research, and organizations and charities (Neuman, 2000). By midcentury, efforts were under way to establish standardized questions through surveys at the U.S. Department of Agriculture. Scales improved through the development of the Likert scale (e.g., strongly agree to strongly disagree). Also, guidelines were written for writing clear questions, standardizing interviewing questions, training interviewers, and checking for consistency among interviewers (Fowler, 2009).

 TYPES OF SURVEY DESIGNS

Despite the many applications of surveys today, there are still only two basic types of research surveys: cross sectional and longitudinal survey research designs.

Cross-Sectional Survey Designs:-

In a cross-sectional survey design, the researcher collects data at one point in time. For example, when middle school children complete a survey about teasing, they are recording data about their present views. This design has the advantage of measuring current attitudes or practices. It also provides information in a short amount of time, such as the time required for administering the survey and collecting the information. There are basically two main types of cross sectional survey research designs which include:-group comparisons-compares two or more educational groups in terms of attitudes, beliefs, opinions, or practices. These group comparisons may compare students with students, students with teachers, students with parents, or they may compare other groups within educational and school settings. For example, one study compared 98 rural and urban secondary school teachers from 11 school systems in Georgia and North Carolina in terms of their sources of stress and symptoms of burnout (Abel & Sewell, 1999). This group consisted of 52 rural teachers and 46 urban teachers (a nonprobability sample) who volunteered to participate in the study. The researchers delivered packets that included two instruments, the Sources of Stress Questionnaire and the Maslach Burnout Inventory, to participating school districts. The teachers mailed the instruments back to the researchers. The statistical analysis of the data showed significantly greater self-reported stress for urban teachers than rural teachers because of poor working conditions and poor staff relations.Furthmore, a cross-sectional study for example could involve surveying primary school teachers from different districts at one time to understand their current job satisfaction and the factors influencing it, like compensation and school environment. Methodologies used in quantitative research where researchers administer a survey to either a sample of individuals or the entire population to describe their attitudes, opinions, behaviors, or characteristics. In this process, survey researchers gather quantitative data using questionnaires (such as mailed surveys) or interviews (such as one-on-one conversations). They then analyze this data statistically to identify trends in responses and to test research questions or hypotheses.

Longitudinal survey research design:- An alternative to using a cross-sectional design is to collect data over time using a longitudinal survey design. A longitudinal survey design involves the survey procedure of collecting data about trends with the same population, changes in a cohort group or subpopulation, or changes in a panel group of the same individuals over time. Thus, in longitudinal designs, the participants may be different or the same people. A longitudinal survey for example   can study a particular   cohort of primary school children from enrollment in a rural district for several years, collecting data on their academic performance, health, and family background periodically to track their development and identify long-term predictors of success. Several types of longitudinal designs are available to the educational researcher, including trend, cohort, and panel designs (Babbie, 1998). 

Trend Studies:- In some surveys, researchers aim to study changes within some general population over a period of time (Babbie, 1998). This form of longitudinal research is called a trend study. Trend studies are longitudinal survey designs that involve identifying a population and examining changes within that population over time. A popular example of this design is the Gallup Poll, which is used during elections to monitor trends in the population of voters from the primary to the final election. Applied to education, this type of study might focus on university students/learners (a population) and study the trends of their attitudes toward dating during the years, say 2023, 2024, and 2025. In this study, different students are studied each year, but they all represent the same population (university students). The researcher can use this data to assess how trends change over time.

Cohort Studies

Rather than studying changing trends in a population, the researcher may be interested in identifying a subgroup in the population, called a cohort that possesses a common defining characteristic. A cohort study is a longitudinal survey design in which a researcher identifies a subpopulation based on some specific characteristic and then studies that subpopulation over time. All members of the cohort must have the common characteristic, such as being 18 years old in the year 2020. If age is that characteristic, the researcher studies the group as the group ages. For example, a cohort group of 18-year-olds is studied in the year 2020. Five years later (in 2025), a group of 23-year-olds is studied. (They may or may not be the same individuals studied in 2020.) Five years after that (in 2030), a group of 28-year-olds is studied. While the individuals studied each time might be different, they must have been 18 years old in the year 2020 to qualify as representatives of the cohort group.

Panel Studies: A third type of longitudinal survey design is the panel study design. Distinct from both the trend and the cohort study, a panel study is a longitudinal survey design in which the researcher examines the same people over time. For example university students   studied in 2018 will be the same people studied in 2020, 2 years after graduation, and again in 2022,

4 years after graduation. One disadvantage of a panel design is that individuals may be difficult to locate, especially 2 years after graduating from university. The advantage to this type of study, however, is that the individuals studied will be the same each time, allowing the researcher to determine actual changes in specific c individuals. Because of this, the panel study is the most rigorous of the three longitudinal designs. Examples of panel study designs in Ugandan educational research are seen in the Uganda National Panel Survey (UNPS), which tracks household and individual outcomes, including education, over several years to inform policy. Other examples include studies analyzing how child and family factors affect academic achievement over time, and research using longitudinal data to track fertility and contraceptive use to understand educational attainment's role in family planning decisions.

According to Creswell (2008), survey research is characterized by four fundamental elements1. Sampling from a Population 

1. Sampling from a population:-Survey researchers begin by selecting a representative sample from a broader population. At point we need to define three key terms which include:-population, sampling frame or a target group and a sample. The Population is the group of individuals having one characteristic that distinguishes them from other groups whereas the Target Population or Sampling Frame is the actual list of sampling units from which the sample is selected on other hand The Sample is the group of participants in a study selected from the target population from which the researcher generalizes to the target population. This sampling is crucial  because it allows researchers to draw meaningful conclusions about the entire population based on the characteristics and responses of the sample whereas The choice of sampling method—whether it be random, stratified, or convenience sampling—can significantly influence the reliability and validity of the findings. Salant and Dillman (1994) identified several factors in good survey research that may compromise drawing these inferences:

◆ To reduce coverage error, have a good sampling frame list on which to select individuals. When researchers use a good, complete list, their coverage of the population is adequate and not error prone.

◆ To reduce sampling error, select as large a sample from the population as possible. The larger the sample, the more the participants will be representative of the entire population and reflect attitudes, beliefs, practices, and trends of the population. Recognize that all samples selected will be only estimates of population values.

◆ To reduce measurement error, use a good instrument, with clear, unambiguous questions and response options. Such instruments will encourage individuals to respond and answer correctly. Later in this chapter, we discuss how to construct a questionnaire to reduce this error.

◆ To reduce nonresponse error, use rigorous administration procedures to achieve as large a return rate as possible. Later in this chapter, we discuss these procedures.

2. Collecting Data through Questionnaires or Interviews:-Data collection in surveys can take two primary forms: questionnaires and interviews. Questionnaires are structured forms that participants fill out, typically featuring a mix of closed-ended and open-ended questions. On the other hand, interviews involve direct interaction between the researcher and the participant, allowing for deeper insight through follow-up questions and probing. Both methods have their own advantages, with questionnaires facilitating broad data collection and interviews allowing for more in-depth exploration of complex topics.

3. Designing Instruments for Data Collection 

To effectively measure specific variables, researchers must design appropriate survey instruments. This involves careful consideration of the types of questions to include, the wording, and the format (e.g., Likert scales, multiple-choice). Researchers may have the option to modify an existing instrument that has demonstrated reliability and validity or create an entirely new instrument tailored to their particular study’s needs, ensuring it aligns closely with the research objectives.

4. Obtaining a High Response Rate 

A critical factor in the success of a survey research project is achieving a high response rate. A higher response rate enhances the confidence researchers have in generalizing their findings to the broader population. Strategies to improve response rates may include sending reminders, providing incentives, and making the survey as user-friendly as possible to encourage participation. Researchers often compute response rates to assess the effectiveness of their outreach efforts.

A survey research design is majorly conducted using questionnaires and interviews. A questionnaire is a form used in a survey design that participants in a study complete and return to the researcher. The participant chooses answers to questions and supplies basic personal or demographic information. An interview survey, however, is a form on which the researcher records answers supplied by the participant in the study. The researcher asks a question from an interview guide, listens for answers or observes behavior, and records responses on the survey. The quantitative interview procedures, discussed here, are not to be confused with qualitative interviewing. In quantitative survey interviews, the investigator uses a structured or semi structured interview consisting of mostly closed-ended questions, provides response options to interviewees, and records their responses. In qualitative survey interviews, an interviewer asks open-ended questions without response options and listens to and records the comments of the interviewee.

Several different types of questionnaires and interviews are used in quantitative survey research design and here the major types used in education:

◆ Mailed questionnaires

◆ Web-based questionnaires

◆ One-on-one interviews

◆ Focus group interviews

◆ Telephone interviews

A mailed questionnaire is a form of data collection in survey research in which the investigator mails a questionnaire to members of the sample. Researchers might develop their own questionnaire, modify an existing one, or use one that they have located in the literature. A mailed questionnaire is a convenient way to reach a geographically dispersed sample of a population. The mail facilitates quick data collection, often in as little time as 6 weeks from the first mailing to the conclusion of data collection. A mailed questionnaire is economical because it involves only duplication and mailing expenses. The disadvantage of mailed questionnaires is that individuals may lack any personal investment in the study and decide not to return the instrument. Also, because the researcher does not have a means for explaining questions, participants may misinterpret items on the survey.

Web-Based Surveys or Questionnaires:-With increased use of Web sites and the Internet, Web-based questionnaires are becoming popular. A Web-based questionnaire is a survey instrument for collecting data that is available on the computer. Several software programs are available for designing, gathering, and analyzing survey data with sample questions and forms (e.g., see Qualtrix at http://www.qualtrics.com/survey-software/ or Survey Monkey at http://www .surveymonkey.com/). Educational researchers need to weigh the advantages and disadvantages of using a Web-based survey. On the positive side, such surveys can gather extensive data quickly, employ tested forms and sample questions rather than having to design them, and take advantage of the extensive use of the Web by individuals today, including its use as a site for social networking. However, authors such as Sills and Song (2002) raise important methodological issues that educational survey researchers need to consider. They were concerned about the low response rates from e-mail and Web-based surveys. Contributing to this problem were nonrandom sampling, technological problems, security issues, and problems with Internet junk mail. Web-based surveys may be biased toward certain demographic groups that tend to use computers. On the other hand, Web surveys may allow effective and economical surveying of the entire population and thereby skirt around the inference problem. Further, they saw a mixed system of Web-based and mailed surveys as promoting a high response rate.

 

One-on-one interviews are a form of survey data collection. In one-on-one interviewing in survey research, investigators conduct an interview with an individual in the sample and record responses to closed-ended questions. The process involves developing or locating an instrument and training the interviewer(s) in good interview procedures. One-on-one interviews are useful for asking sensitive questions and enabling interviewees to ask questions or provide comments that go beyond the initial questions. Interviews lead to a high response rate because researchers schedule the interviews in advance and sample participants typically feel obligated to complete the interview. However, one-on-one interviews do not protect the anonymity of the participant as questionnaires do. Researchers may also prejudice participant answers, knowingly or unknowingly, through either comments or body language. Also, not all interviewees are comfortable disclosing information about themselves during the interview.

An alternative to a one-on-one interview is to administer a survey to a focus group. In quantitative focus group interviews in survey research, the researcher locates or develops a survey instrument, convenes a small group of people (typically a group of 4 to 6) who can answer the questions, and records their comments on the instrument. For example, international students provide views about cultural integration in a Makerere university setting. During processes such as these, researchers ask the group questions on an instrument and record or take notes on the group conversation. Focus groups provide for interaction among interviewees, collection of extensive data, and participation by all individuals in a group (Krueger, 1994). A disadvantage of focus group interviews is that they require the researcher to find consensus on questions so one score can be marked for all individuals in the group. In addition, some individuals may dominate the conversation, leading to responses that do not reflect the consensus of the group.

 In telephone interview surveys, the researcher records the participants’ comments to questions on instruments over the telephone. The researcher develops or locates an instrument, obtains the telephone numbers of participants in the sample, conducts the telephone calls, and asks the participants to answer questions on the instrument. Telephone interviews allow the researcher easy access to interviewees who are geographically dispersed. However, the researcher cannot see any nonverbal communication on the part of the participant, and people often dislike telephone contacts because of their prior personal experiences with calls from survey firms asking for information.

Good survey research questions are specific, relevant, and aligned with the study’s purpose. They should avoid ambiguity and bias, allowing respondents to provide clear and honest answers. Below are examples of effective survey research questions categorized by their purpose:

1. Understanding preferences:

• “Which features of [product/service] do you value most?”

Options: Feature A, Feature B, Feature C, Other (please specify). 

• “What factors are most important to you when choosing [product/service]?

Options: price, quality, availability, brand reputation, other (please specify). 

2. Measuring Satisfaction 

• How satisfied are you with your experience using [product/service]?

Scale: Very dissatisfied to very satisfied. 

• What aspects of our [product/service] do you believe need improvement?

Open-ended response.

3. Behavior and Usage Patterns

• How often do you use [product/service]?

Options: Daily, Weekly, Monthly, Rarely, Never. 

• What challenges, if any, do you encounter when using [product/service]?

Open-ended or multiple-choice options. 

4. Assessing Needs and Expectations

• What additional features or services would you like to see in [product/service]?

Open-ended response.

• How well does [product/service] meet your needs?

Scale: Not Well at All to Extremely Well. 

5. Demographics and Contextual Information

• What is your primary reason for using [product/service]?

Options: Work, Personal Interest, Education, Other (please specify). 

• Which age group do you belong to?

Options: Under 18, 18–24, 25–34, 35–44, 45–54, 55 and Older. 

Tips for Crafting Effective Survey Research Questions: 

• Be Clear: Use simple language and avoid jargon. 
• Stay Neutral: Avoid leading questions that suggest a “correct” answer. 
• Be Specific: Focus on one topic per question to minimize confusion. 
• Use Scales Thoughtfully: Provide balanced scales with clear labels. 
• Pilot Test: Test your survey with a small group to identify any confusing or ineffective questions. 

Effective survey research questions align with the objectives of your study while ensuring that respondents feel comfortable and capable of answering them.

Advantages of Survey Research

Survey research boasts several notable advantages:

a) Ease of Administration: Surveys can be administered with relative simplicity, making them an     attractive option for researchers.

b) Time-Efficient Development: Unlike some qualitative data collection methods, which may require extensive time for participant recruitment and engagement, surveys can often be prepared and distributed swiftly.

c) Cost-Effectiveness: While the cost of survey administration can vary based on methodology (online versus telephone, for example), surveys typically offer an economical way to gather large quantities of data.

d) Remote Accessibility: Surveys can now be easily distributed and completed online or through various digital platforms, enabling researchers to reach participants regardless of geographical barriers.

e) Large Sample Size Potential: Surveys possess the capacity to gather data from extensive respondent groups, significantly increasing the generalizability of the results.

f) Flexibility in Question Design: A wide range of questions can be posed, offering researchers the flexibility to explore different aspects of a topic deeply and thoroughly.

g) Advanced Statistical Analysis Capabilities: Survey software allows researchers to employ complex statistical methods to analyze the data, assessing aspects such as validity, reliability, and statistical significance, including the examination of relationships among multiple variables.

h) Diverse Data Collection Potential: Surveys facilitate the collection of a broad spectrum of data types—such as attitudes, beliefs, values, behaviors, and factual information—yielding a holistic view of the subject matter.

i) Standardization Minimizing Errors: Well-constructed standardized surveys are generally more resilient against various types of biases and errors compared to less structured forms of data collection.

Disadvantages of Survey Research

Despite its numerous advantages, survey research presents its own challenges. These challenges among others include:-

1. Accuracy of Responses: There may be reluctance among respondents to provide truthful answers due to the fear of judgment or privacy concerns, which can compromise data integrity.

2. Comfort Level Issues: Some respondents might feel uncomfortable revealing information that could paint them in a negative light, leading to incomplete or distorted responses.

3. Cognitive Awareness of Responses: Participants may not always have clear insights into their reasons for answering questions a certain way, potentially due to lapses in memory or a lack of engagement with the survey.

4. Validity Concerns with Closed-Ended Questions: Surveys primarily constructed with closed-ended questions can sometimes yield lower validity as they may simplify complex opinions into binary or limited choices.

5. Data Errors from Non-Response: Variability in response rates may lead to bias. For instance, if certain demographic groups are less likely to respond, the results may not accurately reflect the broader population.

6. Interpretation Variations among Answer Options: Answer options can lead to ambiguous data. For example, a phrase like “somewhat agree” could mean different things to different individuals, while binary choices like “yes” or “no” can restrict nuanced responses.

7. Customization Risks: Tailored surveys may inadvertently include biases or errors that arise from subjective question design, making careful planning essential.

In summary, while survey research is a powerful tool for collecting quantitative data across diverse populations, researchers must consider both its strengths and limitations to ensure they design effective studies that yield reliable and meaningful results.