Flashcards
Chapter 5 Survey Research
Flashcards do conjunto (21)
- 1Nature of SurveysA survey is a method of collecting primary data in which information is gathered by communicating with a representative sample of people
A respondent is someone who provide answers to survey questions
A population is the population of interest - 2Survey ObjectivesIdentify characteristics of target markets
Measure consumer attitudes
Describe consumer purchasing patterns - 3Advantages of surveysQuick
Inexpensive
Accurate
Flexible
Extremely valuable to managers - 4Errors in Survey Research1. Random Sampling Error
2. Systematic Error
- Respondent Error (non-response error & response bias)
- Administrative Error - 5Random Sampling ErrorIt is a statistical fluctuation that occurs because of chance variation in the elements selected for a sample
Without increasing sampling size, these statistical problems are unavoidable - 6Systematic Errors - Respondent errors -Administrative errorsIt is an error resulting from some imperfect aspect of the research design that causes respondent error or administrative error
Sample bias exists when the results show a persistent tendency to deviate from the true value of the population parameter - 7Non-response errorIt is the statistical differences between a survey that includes only those who responded and a perfect survey that would also include those who failed to respond
To be able to use results that do not have 100% response rate, researchers need to ensure that those who responded need to be representative of those who didn't response - 8Self-selection BiasIt is a bias that occurs because people who feel strongly about a subject are more likely to respond than those who feel indifferent about it. Eg. Christians over homosexuality.
It can distort survey results because they can over-represent extreme positions while those who felt indifferent can under-represent responses - 9Response BiasIts is a bias where respondents tend to answer questions either consciously or unconsciously that misrepresent the truth.
Deliberate Falsification: Respondents deliberately provide incorrect or the best information they could to appear intelligent, conceal personal information, or to avoid embarrassment, to please interviewer etc
Unconscious misrepresentation: respondents who misunderstood survey questions may unconsciously provide biased answer or are willing to answer but forgotten the exact details - 10Types of Response BiasAcquiescence Bias
Auspices Bias
Extremity Bias
Interviewer Bias
Social Desirability Bias - 11Acquiescence BiasIt is individuals' tendency to agree or disagree all questions, or to concur with a particular position
- 12Extremity BiasIt is the tendency of individuals to use extremes when responding to questions
- 13Interviewer BiasThis occurs when in the presence of interviewers, respondents may give incorrect answers that they believe will please the interviewer or to appear smart and wealthy
- 14Auspices BiasThis is caused by the influence of the organization conducting the study.
- 15Social Desirability BiasIt is caused by respondents' desire, either consciously or unconsciously, to gain prestige or appear in a different social role, in order to either save face or to impress the interviewer
- 16Administrative Error - Data processing error - Sample-selection error - interviewer error - interviewer cheatingThis is caused by careless, neglect, omission, etc of improper administration or execution of the research task.
Data processing error: occurs because of incorrect data entry, computer programming or other procedural errors during data analysis
Sample-selection error: caused by improper sample design or sampling procedure execution
Interviewer error: it is caused by interviewer incorrectly record survey responses due to unable to write quickly or misinterpretations
Interviewer cheating: it is the practice of an interviewer filling in fake answers and falsifying questionnaires - 17Structured and Disguised QuestionsA structured question limits the number of allowable responses. Eg, SA
An unstructured question does not limit the number of allowable responses. Eg. MA or Open-ended
A disguised question is used for sensitive questions and will be 'hidden' from the respondent
An undisguised question are straightforward questions that assume respondents are willing to reveal information and answer
A question may be a hybrid of both categories, eg, structured undisguised question - 18Temporal Classification (time basis study)Cross-sectional study: samples of various segments are sampled and data is collected at a single point of time.
Longitudinal study: a survey of respondents at different times, used to examine continuity of responses and to observe changes that occur over time - 19Personal InterviewsIt is a versatile and flexible two-way conversation between the interviewer and the respondent
- 20Advantages of Personal InterviewsOpportunity for feedbacks
Ability to probe for further explanation
Availability of props and visual ads to assist respondents in answering
Length of interviews can be controlled to allow longer interviews - 21Disadvantages of Personal InterviewsDemographic characteristics, differential interviewing techniques, tone of voice and appearance of interviewers can influence answers
Respondent is not anonymous and may be reluctant to provide confidential information
Expensive
Informações
- Descrição
- MRA FlashCards sobre Chapter 5 Survey Research, criado por IngIng Hon em 28-11-2014.
- Criado por
- IngIng Hon
- Visualizações
- 7
- Avaliação