Surveys
may be used for descriptive, explanatory and exploratory purposes
Respondents
a person who provides data for analysis by responding to a survey questionnaire
Careful probability sampling
provides a group of respondents whose characteristics may be taken to reflect those of the larger population, and carefully constructed standardized questionnaires provide data in the same form from all respondents
Survey Research
best method available to the social scientist s interested in collecting original data for describing a population too large to observe directly
Questionnaire
a document containing questions and other types of items designed to solicit information appropriate to analysis. Used primarily in survey research
Open ended questions
questions to which respondents are asked to provide their own answers. Qualitative in depth interviewing heavily relies on these, but they are sometimes used in other forms of data collections such as telephone surveys and self administered questionnaires
Close ended questions
questions to which the respondent is asked to select an answer from among a list provided by the researcher. These are popular in research because they provide greater uniformity of responses and are more easily processed than open ended questions
Open ended questions must
must be coded before they can be processed for computer analysis
Open ended question responses
must be interpreted by the researcher, opening the possibility of misunderstanding and researcher bias, another danger is that some respondents will give answers irrelevant to the researchers intent
Close ended responses
can be directly transmitted into a computer format
Chief shortcoming of close ended questions
lies in researchers structuring of responses. When the relevant answer to a given question are relatively clear, there should be no problem. In other case, however, the researchers structuring of responses may overlook some important responses
Structural Requirements for close ended questions
response categories provided should be exhaustive: they should include all possible responses that might be expected (ensured by other: please specify). The answer categories must be mutually exclusive: the respondent should not be compelled to select mor
Avoid Double Barreled Questions
researchers must not ask for a single answer to a question that has multiple parts
Respondent Requirements
must answer reliably, must be willing to answer
Questions
should be relevant, ideally we would like respondents to simply report that they do not know, have no opinion or are undecided in instances where that is the case
Short Items are best
long and complicated items should be avoided, should be able to read them quickly, understand the intent and select or provide an answer without full difficulty
Negative Items
the appearance of negation in a questionnaire item paves the way for easy misinterpretation
Loaded Questions or Leading Questions
questions containing bias, the use of certain wording can affect the outcome of responses, the true meaning of ones responses to a question depends in large part on its wording
Bias
refers to any property of questions that encourages respondents to answer in a particular way. The quality of a measurement device that tends to result in a misinterpretation of what is being measured in a particular direction
Social Desirability
answering a question that will make one look good, especially if interviewed face to face
General Questionnaire Format
should be spread out and uncluttered
Inexperienced Researchers
worry that their survey will be too long, as a result, squeeze several questions into a single line, abbreviate questions, and try to use as few pages as possible
Formats for Respondents
boxes adequately spaced apart are the best format
Contingency questions
a survey question, only intended for some respondents, determined by their responses to some other question, arises when researchers wish to ask a series of questions about a specific topic
Advantages of Matrix Questions
it uses space efficiently, respondents will probably find it faster to complete a set of questions presented in this fashion
Ordering Items in a Questionnaire
can affect responses, the appearance of one question can affect the answers given in later ones
Prevented by randomization
the effort is usually futile. Int he first place, a randomized set of items will probably strike respondents to answer because they must continually switch their attention from one topic to another
Questionnaire Instructions
should contain clear instructions and introductory comment where appropriate, useful to begin with basic instructions
Pretesting the questionnaire
pretest the questionnaire in full or in part, give questionnaire to a diverse set of ten people, it is not usually essential that the pretest subjects comprise of representative sample, although you should use people to whom the questionnaire is least rel
Precoding
because the information collected by questionnaires is generally transformed into some sort of computer format, it is usually appropriate to include data processing instructions on the questionnaire itself, these instructions indicate where specific piece
Basic Method of Mail Distribution and Return
send questionnaire accompanied by a letter of explanation and a self-addressed, stamped envelope
Strategy for Easy Return
self mailing questionnaire requires no return envelope: when the questionnaire is folded in a particular way, the return address appears to be on the outside, respondent does not need to worry about losing the envelope
Monitoring Survey Returns
rate return graph: best to compile two graphs, one shows the number returned each day, the second reports the cumulative number or percentage
Returned Questionnaires
opened, scanned and assigned an identification number. Numbers should be assigned serially as the questionnaires are returned.
Serialized ID numbers
can be valuable in estimating nonresponse biases in the survey
Follow Up Mailings: simple
non-respondents are sent a letter of additional encouragement to participate
Follow Up Mailings: better method
send a new copy of the survey questionnaire with a follow up letter
Effects of follow up mailings
seen in the response rate curves recorded during data collection. The initial mailings will be followed by a rise and subsequent subsiding of returns; the follow up mailings will spur a resurgence of returns; and more follow ups will do the same
Response rate
the number of people participating in a survey divided by the number selected in the sample, in the form of percentage. This is also called the completion rate or, in self administered surveys, the return rate: the percentage of questionnaires sent out th
Interview
a data collection encounter in which one person asks questions of another
Advantages of questionnaire administered by Interviewer
interview surveys typically obtain higher response rates than mail surveys, respondents more reluctant to turn down an interviewer, decreases "I don't knows
Interviewer
serves as a guard against confusing questionnaire items, if the respondent misunderstands the intent of the question or indicates that he/she does not understand, the interviewer can clarify matters, obtaining relevant responses