Skip to main content

1- Survey

Why Should I Care?

Surveys are very common. However, many are not done well. There are many traps most people don’t know about that reduce their scientific validity.

Definitions

Survey: the act of measuring objects.

Social survey:  a research technique that obtains information from a sample of individuals by asking                                    questions and analyzing the responses.

Questionnaire: a written set of questions organized in a sequence appropriate to the purpose of a                                         survey, or psychological test.

Interview: a loose set of questions, mostly designed to produce an open-ended conversation.

Usefulness

Allows for a “real-time” expression of opinions and attitudes on a particular topic.

In politics, allows to identify shifts in opinions, and relate them to a particular event (speech, riot, etc.)

Business people need them to prepare marketing strategies, advertising campaigns, etc.

Objects of Measurement

Type of Object

Yes

No

Maybe

Example

Personal Characteristic

 X



Eye colour, Height, Accent

Socio-Demographic Characteristic

 X



Religion, Language, Income, Gender, Ethnicity, Marital Status

 zOpinion

 X



I don’t like Rice Krispies Cereal

Motivations



Fear, Hope, Ambition, Greed

Ideology

 X



Right-Wing, Left-Wing

Biases / Prejudice

 X


I trust tall people more than short people

Preferences

 X


Commercial example: pricing, marketing

Personal History / Background

 X


Immigration, Settler, Indigenous, Divorce

Family Dynamics

 X 


Number of siblings, Rank in Family, Class

Cultural History

 X


Military History, Political History, Class

Perception / Self-Perception

 X


Other people are smarter than me

Aptitude /Ability

 X


X

Can hit 3-point shot. Can manipulate others

Behaviour / Actions


 X


Domestic Violence. Narcissist. Kind.

Personality





Moods / Emotions





Performance





Level of Knowledge

 X



School test. Diagnostic quiz.

Sampling

Hopefully _random___ and _large____.

Possible using phonebooks as lists of population, but not so much through _email and internet_ .

With interviews, samples are non-random and tiny.

Types of Surveys
  1. Cross-sectional: compare many independent variables to a dependent variable
  2. Longitudinal: compare a few variables over time
    • Trend: similar samples taken at different time points
    • Panel: same sample followed through time
Instruments
  1. Questionnaire (116): set question list, closed-ended questions, larger sample
    • In-person
    • Telephone
    • Internet
    • Group
  2. Interview: starting question list, open-ended questions, smaller sample
    • Field interview
    • Formal Face-to-face interview
Scientific Power

Exploratory: possible but not likely if the topic is taboo or difficult to discuss.

Mostly descriptive studies, which focus on who, where, how and what.

But may also be used for explanatory studies which validate hypotheses and their causal relationships (why).

Warning – “Surveys” are also used as a commercial ploy to build email mailing lists for advertising.