Class Notes (1,100,000)
CA (630,000)
U of G (30,000)
SOAN (900)
SOAN 2120 (400)
Lecture

SOAN 2120 Lecture Notes - Collectively Exhaustive Events, Formal Language, Jargon


Department
Sociology and Anthropology
Course Code
SOAN 2120
Professor
Scott Schau

This preview shows pages 1-2. to view the full 7 pages of the document.
Lecture Notes Wed. Mar. 13 2013
Survey Research
Surveys
-used often as a mode of observation
-select a sample of respondents and give them a standardized questionnaire
-used for descriptive, explanatory and exploratory purposes
-best method for collecting original data for describing a population too large to observe
directly
-find an informant to answer he questions you have, that can answer your questions for
you
-surveys are quick, interviews on the phone, web surveys or over the mail whereas an
experiment takes long, you have to set up and do the experiment
-surveys have a lot more data in a time period whereas experiments have less data in the
same time
Surveys ask about:
-behavior
-attitudes/beliefs/opinions e.g. how your Gov. is doing
-characteristics e.g. stuff that describes the individuals
-expectations e.g. child education expectation, expectation of a new vehicle
-self-classification e.g.
-knowledge e.g. who was elected mayor in the last election? Questions you can
ask about people’s knowledge
A few introductory tips:
-make items clear
-concise, precise, and unambiguous language
-closed ended questions should be mutually exclusive and jointly exhaustive
-begin with easy and interesting questions
-save most threatening questions for later
-keep an order of questions that will maintain the respondents interest
-pretest questions ahead of time to protect against errors
-questionnaires should be spread out and uncluttered
-questionnaires should contain clear instructions and introductory comments where
appropriate
Open vs. closed-ended questions
-open-ended: respondent is asked to provide her/his own answer to a question
e.g. by filling in a blank
-ppl may or may not answer the question, you may get information that is not useful to
your study
-closed ended: respondent is asked to select an answer from a list provided by the
researcher
-how you order the questions on the survey can influence how they are snwered

Only pages 1-2 are available for preview. Some parts have been intentionally blurred.

Guidelines for survey questions:
-choose appropriate question forms
-avoid the use of jargon, slang and abbreviations
-use as formal language as possible to be clear
-avoid ambiguity, confusion and vagueness
e.g. Are you a regular coffee drinker? What does regular mean though?
-avoid emotional language and prestige bias
e.g. Are you in favor of doctors killing their patients? Versus assisted suicide
-avoid double-barreled questions
e.g. Are you against abortion AND assisted suicide? if you have AND in your
question really consider why it is there
-avoid leading questions
e.g. did you fulfill you civic duty and vote in the last election?
-respondents must be competent to answer?
e.g. How many times did you smile in the last month? impossible to answer!,
how do we know, also may not be relevant to the respondents
-respondents must be willing to answer
-questions should be relevant
-short items are best
-avoid negative items (double negatives)
e.g. do you disagree with those who oppose marijuana use?
-avoid biased items and terms
-use more than 1 question it necessary
Questionnaire Construction
-general questionnaire format
-one question on one line, you can cause ppl to miss questions if you have more
than one
-formats for respondents
-contingency questions
-questions specific to gender
e.g. if you answered male do not answer questions 2, 3 so that mend o not waste
time answering female questions
-matrix questions
-agree, disagree, a list
-can cause problems b/c ppl will just check the same answer all the way down
-negative question can be useful in making ppl think about their answers better
-ordering items in a questionnaire
-all the boring questions at the beginning? No b/c/ they will stop answering form
boredom
-protest the questionnaire
Contingency Question
e.g. 23. Have you ever smoke maajuauna?
Yes or no?
-if yes then they answer: once, 2-5 times, 6-10 times…etc.
You're Reading a Preview

Unlock to view full version