Social Research Methods: Qualitative and Quantitative Approaches

ANALYSIS OF QUALITATIVE DATA

the operational advantages of their quantitative
cousins in being able to predict their own analytic
processes; consequently, they cannot refine and
order their raw data by operations built initially
into the design of research.”
A second difference is that we do not begin data
analysis in quantitative research until we have col-
lected the data. Only then do we manipulate the
numbers in seeking patterns or relationships. In
qualitative research, we start looking for patterns or
relationships while collecting data. We use results
from early data analysis to guide subsequent data
collection. Thus, analysis is less a distinct final stage
of research than a dimension of research that
stretches across all stages.
Another difference is the relation to social the-
ory. Quantitative research involves manipulating
numbers that represent empirical facts to test abstract
hypotheses comprised of variable constructs. In con-
trast, qualitative research frequently creates new con-
cepts and theory by blending empirical evidence with
abstract concepts. Instead of testing a hypothesis, we
may illustrate or color evidence to show that a theory,
generalization, or interpretation is plausible.
The fourth difference is the degree of abstrac-
tion or distance from the details of social life (see
Summary Review Box 1, Comparing Quantitative
and Qualitative Data Analysis). In all data analysis,
we place specific raw data into broader categories.
We then examine and manipulate categories to iden-
tify patterns. In quantitative analysis, this process is
clothed in statistics, hypotheses, and variables. We
assume that we can capture or measure using num-
bers and then manipulate the numbers with statistics
to reveal key features of social life.
In contrast, data in qualitative analysis are
relatively imprecise, diffuse, and context based
and can have more than one meaning. This is not
always a disadvantage.

Words are not only more fundamental intellectually;

one may also say that they are necessarily superior

to mathematics in the social structure of the disci-

pline. For words are a mode of expression with

greater open-endedness, more capacity for con-

necting various realms of argument and experience,

and more capacity for reaching intellectual audi-

ences. (Collins, 1984:353)

Explanations and Qualitative Data

We do not have to choose between a rigid idio-

graphic/nomothetic dichotomy: that is, between

describing specifics and verifying universal laws.

When analyzing qualitative data, we develop expla-

nations or generalizations that are close to concrete

data and contexts, and we usually use less abstract

theory. We may build new theory to create a realis-

tic picture of social life and stimulate understanding

more than to test causal hypotheses. The explana-

tions tend to be rich in detail, sensitive to context,

and capable of showing the complex processes or

sequences of social life. They may or may not be

causal. Our goal is to organize specific details into

a coherent picture, model, or set of tightly inter-

locked concepts.

Qualitative explanations can be either highly

unlikely or highly plausible. We provide supportive

evidence to eliminate some theoretical explanations

from consideration and to increase the plausibility

of others. Qualitative analysis can eliminate an

explanation by showing that a wide array of evidence

contradicts it. The data might support more than one

SUMMARY REVIEW BOX 1

Comparing Quantitative and Qualitative

Data Analysis

SIMILARITIES DIFFERENCES

Both infer from

empirical data to

abstract ideas

Quantitativeuses a few shared,

standardized techniques.

Qualitativeuses many diverse,

nonstandard techniques.

Both use a public

process and

described in detail

Quantitativeanalyzes after all

data have been collected.

Qualitativebegins data analysis

while still collecting data.

Both make

comparisons

Quantitativetests preexisting

theories and hypotheses.

Qualitativeconceptualizes and

builds a new theory.

Both avoid errors

and false

conclusions

Quantitativeuses precise and

compact abstract data.

Qualitativeuses imprecise,

diffuse, relatively concrete data.