EC303: Methods pt.2
Surveys
Statistical surveys are used to collect quantitative information about items in a population. They focus on opinions or factual information depending on their purpose.
Steps in a Survey Project
1. Establish the goals of the project – decide what you want to learn
a. the goals of the project determine whom you will survey and what you will ask
b. if your goals are unclear, the results will probably be unclear.
2. Determine your sample – two main components
a. first is deciding what kind of people to interview – “target population”
b. how many people you need to interview
c. careful of population bias
3. Choose interviewing methodology
a. How you will interview – person, phone, email, computer, etc.; SurveyMonkey.com
b. How you will distribute: web page popup, email, paper and transfer results to online version
4. Create your questionnaire see more Tips – Survey Construction below
a. KISS – keep it short and simple.
b. questions into three groups: must know, useful to know and nice to know. Then discard the last group, unless the previous two groups are very short.
c. Start with an introduction: who you are and why you want the information; it will also encourage people to complete your questionnaire
5. Pre-test the questionnaire
6. Conduct interviews and enter data
7. Analyze the data – Produce the reports
a. open ended questions
b. code or excel display
Note: Human Subjects Permission
Using SurveyMonkey
Go to http://www.surveymonkey.com
Sign up for basic account or see McKinley /ask at Ref. Desk for password for Premium edition.
Example
Select
- “Create Survey at the top of the screen
- “… From Scratch”; Enter Title, and click “Create Survey”
- Select a “Theme” and “Save Theme”
- Edit page
a. add questions – choose a question type
b. save changes
Add question:
- Select type: “Multiple Choice – One Answer – (Vertical)”
- Type the following – Year in School
- Under Answer Choices: First year, Sophomore*, Junior and Senior
- “Add+” to save
Use the SurveyMonkey “<
Tips
Methods used to increase response rates
- brevity
- incentives – financial or non-monetary
- guarantee anonymity
- acknowledge affiliation with universities, research institutions, or charities
- emotional appeals and bids for sympathy
- convince respondent that they can make a difference
- preliminary notification
- foot-in-the-door techniques – start with a small inconsequential request
- personalization of the request – address specific individuals
- follow-up requests – multiple requests
Survey Construction
- Allow a “Don’t Know” or “Not Applicable” response to all questions, except to those in which you are certain that all respondents will have a clear answer
- Include “Other” or “None” if either of these is a logically possible answer
- 3 basic types of questions: multiple choice, numeric open end and text open end
question and answer choice order. - Ideally, the early questions in a survey should be easy and pleasant to answer
- Whenever possible leave difficult or sensitive questions until near the end of your survey
- Leave your demographic questions (age, gender, income, education, etc.) until the end of the questionnaire
- Always present agree-disagree choices in that order
- Reduce habituation
- Randomize the order of related questions
- Present a series of questions in a random order
- Change the “positive” answer (applies mainly to level-of-agreement questions)
- People tend to pick the choices nearest the start of a list when they read the list
- Do not put two questions into one.
- Try to make sure the wording does not favor one answer choice over another.
- Avoid emotionally charged words or leading questions
- Avoid technical terms and acronyms
- Leave a space at the end of a questionnaire entitled “Other Comments.”
Online – take advantage of html and computer technologies
a. maps
b. picture examples
c. required information to continue
d. limit choices