the nature of quantitative research Flashcards
main features of quantitative research
measurement, causality, generalization, and replication.
quantitative research
- theory -> drives the research
- preference for the natural science approach+positivism
- social phenomena and their meanings have an existence that is independent of social actors.
quantitative research
epistemological position+ontological position
main methods of data collection associated with quantitative research
questionnaires and surveys, evaluation of documents and texts, evaluation of data already collected by others, systematically observing and recording behavior.
multi-method research
studies using more than one method.
Big Data
new possibilities for secondary data analysis
the process of quantitative research
- theory
- formulate a research question/questions
- hypothesis
- research design
- devise measures of concepts
- select research site(s)
- select research subject/respondents
- administer research instruments/collect data
- process data
- analyse date
- findings/conclusions
- write up findings/conclusions
operationalization
devising measures of the concepts we want to study
hypothesis
informed speculation.
based on knowledge of the existing research literature.
null or alternative hypothesis.
coding of the information
transforming it into numbers to enable the quantitative analysis of the data
concept
the building blocks of theory and the points around which social research is conducted.
three main reasons for the focus on measurement in quantitative research
- measurement allows us to identify fine differences between people’s characteristics
- measurement gives us a consistent device for identifying such differences
- measurement provides the basis for a more precise estimation of the degree of relationship between concepts
how do we measure?
- devising indicators (they represent the concepts): we may use a question, we may record individuals’ behavior using a structured observation schedule, we may use official statistics, or we may examine media content using content analysis.
- using multiple-indicator measures: use a number of indicators that tap into a certain concept (most famous: likert scale)
why use mutiple-indicator measure
a single inicator may incorrectly classify individuals, a single question may be too general or too limited in scope, or multiple question questions allow researchers to make much finer distinctions
likert scale
a multiple-indicator or mutiple-item measure of a set of attitudes relating to a particular area, used to measure intensity of feelings.
dimensions of concepts
the researcher seeks to develop a measure of a concept, the different aspects or components of that concept should be considered. the dimensions are identified with reference to the theory and research associated with it.
reliability
the consistency of measures
its about the stability of measurement over a variety of conditions in which the same results should be obtained
internal reliability
applies to mutiple-indicator measures
we need to make sure that all our indicators are related to each other.
inter-rater reliability
the consistency of observations and ways of recording data across the people who are involved , in studies where there is more than one
measurement validity
whether a measurement of a concept really measures that concept
face validity
that the measure apparently reflects the content of the concept explored.
concurrent validity of the measure
existing at the same time, or overlapping
criterion validity
cases that are known to differ and that is relevant to the concept in question
predictive validity
the researcher uses a future crterion measure, rather than a current one as in the case for concurrent validity.