Survey Design and Experiments Flashcards
T or F: sampling is an important part of quantitative research
True: especially important when conducting surveys
what is a survey?
a specific type of field study that involves the collection of data from a sample of elements drawn from a well-defined population through the use of a questionnaire
what is the purpose of surveys?
- allow for data collection from a large number of people
- allow for assessment of self-reported traits, attributes, and behaviors
- are reliable means of information gathering
T or F: surveys do not rely on self-report data
FALSE
what is self-report data?
data provided by a study respondent without inference on the part of the research
what is the process of conducting a survey?
1) specify the research problem
2) select a survey design
3) generate questionnaire
4) generate data
5) analyze data
T or F: survey questions should be easy to read and understandable
True
T or F: it’s important to think about “user experience” when designing surveys
True
T or F” a survey should take participants more than 10-12 minutes to complete
False: should not take more than 10-12 minutes to complete
T or F: personally sensitive questions and demographic questions should appear at the beginning of the survey
False: these questions should appear at the end of the survey
When is it acceptable to have personally sensitive question at the beginning of a survey?
when branching or eligibility questions are necessary
What do experiments do?
1) demonstrates whether something is true
2) examines the validity of a hypothesis or theory
3) attempts to discover new information
T or F: experiments are the means by which we detect cause and effect
True
What is a casual relationship between variables?
refers to the researcher’s attempts to determine that one or more variables (independent) have caused the changes in another variable (dependent)
What conditions allow for one variable to cause an effect in another variable?
1) Correlation
2) Time Order
3) Non-Spuriousness
what is correlation?
when variables A and B are related to one another
what is time order?
when changes to variable A result in changes to variable B
what is non-spuriousness?
the relationship between variable A and B must not be explained by a third variable (C)
what is spuriousness?
a relationship between variables that seems real, but is explained by the presence of another variable
what is causation?
states that A causes B
what is association?
states that A and B are associated (correlated) with one another
T or F: surveys can only point to associations between two variables
True
T or F: independent variables are varied by researchers
True
T or F: dependent variables are presumed to be affected by independent variables
True
what is an independent variable in an experimental research?
a variable that is manipulated/changed by the researcher
what is a dependent variable in an experimental research?
a variable that is measured by the researcher
T or F: independent and dependent variables are something we think about in all forms of qualitative research
False: quantitative research
how is the independent variable used in non-experimental research contexts?
the independent variable is the thing that is presumed/theorized to predict another outcome
T or F: in survey designs, independent and dependent variables are used similarly to experimental research
False: the independent variable is the variable that we expect to come before or be predictive of the dependent variable
T or F: the independent/dependent variable distinction only makes sense if our research context involves two or more variables
True
what are the common question types in survey design?
1) single selection measures
2) multiple selection measures
3) ranking measures
4) rating measures
5) likert-type measure
6) semantic differential measures
what are single selection measures?
requires participants to make a single selection from a list of options
what are multiple selection measures?
allows participants to make more than one selection from a list of options
what are ranking measures?
requires participants to rank a body of elements in terms of preference
what are rating measures?
requires participants to rate (on a numeric scale) thoughts, feelings, or beliefs relative to a researcher-provided prompt
what are likert-type measures?
requires participants to indicate level of agreement relative to a researcher-provided prompts
- ex: strongly disagree - strongly agree
what are semantifc differential measures?
requires participants to indicate feelings/beliefs relative to a researcher-provided prompt
- use bipolar formate where only the poles are labeled
T or F: all true experiments no do require random assignment
False: random assignment is require
what is random assignment?
the research subjects are randomly placed in experimental groups
What is the first thing we do when we’re ready to collect data?
randomly place our participants into the experimental or control group
T or F: randomly assigned people into experimental groups should be similar in terms of demographics features, life experiences, and so on…
True
what is the purpose of random assignment?
placing subjects into different treatment and control groups in a true experiment to ensure that subjects in each group will have similar characteristics and are equal
T or F: if an “experiment” uses random assignment, it is a quasi-experiment
False: experiments that don’t use random assignments are quasi-experiments
T or F: quasi-experiments can provide conclusive evidence of causation
False: quasi-experiments CANNOT provide conclusive evidence of causation
T or F: random assignment and random sampling are the same thing
False: random sampling refers to the random selection of individuals from a larger population
T or F: the most straightforward experiment involves two groups: control and experimental group
True
what is randomized controlled trial?
an experiment involving a controlled and experimental group
- also referred to as RCT
what is a control group?
a group of participants who do everything the experimental group does, but are not given any test, drug, intervention, or manipulation
what is an experimental group?
the group of participants who undergo a form of experimentation
what are the strength of experimental research?
only method that can definitively show causality
- can be replicated