File

advertisement
•
Bias is a form of systematic
error that can affect scientific
investigations and distort the
measurement process.
•
A biased study loses validity
in relation to the degree of
the bias.
•
While some study designs are
more prone to bias (such as
qualitative research), its
presence is universal.
•
It is difficult or even
impossible to completely
eliminate bias.
•
In qualitative research, bias
affects the validity and
reliability of findings, and
consequently affects public
perception.
•
In qualitative research, bias
is inevitable. The goal of
qualitative research is to
recognize and reduce it, or
at least be aware of how it
impacts data.
In qualitative research, there
are two major categories of
bias:
•
Researcher bias
•
•
•
•
Biased questions
Biased samples
Biased reporting
Participant Expectations
•
•
Biased actions
Biased answers
•Researcher bias, also called
experimenter bias, is a process
where the researcher performing a
study consciously or subconsciously
influences the results, in order to
portray a certain outcome.
•Participant expectation or the
Hawthorne effect is the process
where subjects of an experiment
change their behavior, simply
because they are being studied.
•
In qualitative research researcher
bias is a problematic concept, since
by definition the qualitative
researcher is part of the process,
and all researchers are different.
•
This human factor has been said to
be both the greatest strength and
the greatest weakness of
qualitative method.
A trip down memory lane to support our claim: Principles
that Define the Socio-cultural level of analysis
Principle 1: Human behavior occurs
within a social or cultural context. The
social situation can impact our behavior
(i.e. the presence of a researcher)
Principle 2: Humans have a tendency
to comply or conform to group
norms. Group interviews can be
impacted by the presence of others.
People in a position of “authority” can
impact ones response.
•
The researcher collects the
data and has a major impact on
the quality of the data.
•
During data collection, the
researcher’s facial expressions,
body language, tone, manner
of dress, and style of language
may introduce bias.
•
Similarly, the moderator’s age,
social status, race, and gender
can produce bias.
•
The bias of the researcher can
create certain “expectations”
for the participant.
•
These expectations can lead to
answers that reflect the bias of
the researcher as opposed to
the perspective of the
participant.
•
This causes a study to lose its
credibility.
•
•
•
Sampling bias is consistent error
that arises due to the sample
selection.
For example, a survey of high
school students to measure
teenage use of illegal drugs will
be a biased sample because it
does not include home schooled
students or dropouts.
A sample is also biased if certain
members are underrepresented
or overrepresented relative to
others in the population.
•
Both underrepresentation and
overrepresentation can lead to
skewed qualitative data and
cause research to lose
credibility.
•
Research that claims to
“represent the voice of a
specific group” does not do so if
some portion of the group is not
represented in the sample.
•
Sampling bias is usually the
result of a poor or subjective
sampling plan.
•
The most notable is the bias of
non response when for some
reason some units have no
chance of appearing in the
sample.
•
This can be briefly explained in
your response.
•
Design bias (leading questions
or selective probing in
interviews)
•
Content analysis bias
(misinterpreting or omitting a
response from data analysis)
•
In some cases, an experimenter
might give off hints or cues that
might make the participant believe
that a particular outcome or
behavior is expected, this is
considered participant bias.
•
It is important to note that the
participant may or may not be right
in their guess.
•
Even if the individual is wrong
about the experimenter's intentions,
it can have a profound influence on
how the participant behaves.
•
For example, the subject might
take it upon themselves to play
the role of the "good participant."
•
Instead of behaving as they
normally would, these individuals
strive to figure out what the
experimenter wants and then live
up to these expectations.
•
This is especially true with case
studies, focus groups, and
observations.
•
Demand characteristics might
also motivate participants to
behave in ways that they think
are socially desirable (to make
themselves look better than
they really are)
•
Or in ways that are antagonistic
to the experimenter (an
attempt to throw off the results
or mess up the experiment).
•
This is also known as the
Hawthorn effect.
Classwork
•Read and outline pp. 36-44
•Define all terms
•Summarize the following sub-sections
•Experimentation (Skip Obj. 13)
•Cause and Effect
•IV/DV
•Statistical Reasoning (Skip Obj. 19&20)
•Describing Data
Download