Survey Research

The Survey Research This presentation has adapted material from . www.socialresearchmethods.com

Survey Research: Definition A survey is a form of descriptive research that uncovers characteristics of a .population through the study of a sample

They are mostly conducted using .questionnaires, interviews or polls

Survey Research: Purposes Surveys are used to gather demographic information about a population. Ex: A survey may be conducted to reveal if facilitating the bureaucratic process in obtaining an Egyptian voter ID would encourage more people to vote in elections.

Types of Surveys • Questionnaire: mail survey group administered questionnaire household drop-off

• Interview personal interview telephone interview

Sampling Terminology • The group you wish to generalize to is often called the population in your study. • The theoretical population, which includes everyone in your population can be differentiated from your accessible population, which includes the population you can actually study. • A sampling frame is a list of everyone in your accessible population.

Sampling Terminology • A sample is the group of people that you choose to include in your study. • A bias is a systematic error that occurs when conclusions are drawn based upon a non-representative population.

Selecting the Survey Method • Population issues Can the population be enumerated? Is the population literate? Are there language issues? Will the population cooperate? What are the geographic restrictions?

Selecting the Survey Method • Sampling issues What data is available on the sampling frame? Are there lists, directories…etc? Can respondents be found? Who are the respondents? Are they volunteers or not? Is the sample representative of the sampling frame? Are response rates likely to be a problem?

Types of Samples • Probability sampling: A sample in which each element has a known probability of being selected. • Non-probability sampling: The sample differs systematically from the population. • Simple Random Sampling: The sample from which selections are made has the same characteristics as the population.

Types of Samples • Stratified sampling: population is divided into groups and a sample is drawn from each group. • Sample of convenience: persons are selected because of their accessibility. • Volunteer sample: persons volunteer to participate in the study N.B. Both convenience and volunteer samples are nonprobability samples.

Constructing a Survey • Step One: Determining the Type of Questions. Questions may be structured 1. dichotomous (yes/no, true/false, agree/disagree) questions. 2. rank questions where participate order elements according to preference.

Constructing a Survey 3. interval questions where participants choose a degree of response from strongly agree to strongly disagree or rate their response from 1-9. 4. contingency questions where an initial question is asked to determine which other questions participants should answer.

Constructing a Survey .Your questions may be unstructured as well This may be better for content but much .harder to draw simple conclusions from

Assessing Survey Questions Step Two: Assessing your questions. • • • • • • •

Is the Question Necessary/Useful? Are Several Questions Needed? Do Respondents Have the Needed Information? Does the Question Need to be More Specific? Is Question Sufficiently General? Is Question Biased or Loaded? Will Respondent Answer Truthfully?

Data Analyses Step Three: Reporting and analyzing data. Data will be reported using either • Descriptive analysis: results are presented in frequencies, percentages, averages, standard deviations or other statistics. • Correlational analysis: relationships between variables take precedence.

Evaluating a Survey • What is the research question? • In what context was the survey conducted? • How was the population defined? • How representative is the sample?

Evaluating a Survey • How were the variables observed or measured? • Were the results biased? Was there nonresponse bias? • Are generalizations about results appropriate? • What is the significance of this study?