Ch 6 - Measurement Flashcards
3 distinctions between qualitative and quantitative measurement techniques
- TIMING - think about variables and convert them into specific actions during a planning stage that occurs before and is separate from gathering and analyzing data
QUAN - measurement occurs before data collected
QUAL - occurs during data collection - DATA THEMSELVES - quantitative - numbers - represents abstract ideas, qualitative - sometimes numbers more often spoken words, actions, sounds, symbols, physical objects, images - develop flexible ongoing processes to measure the data that leave those data in various shapes sizes and forms.
- HOW STYLES MAKE LINKAGES between data and concepts -
QUAN - reflect on concepts before gathering data, measurement techniques that bridge concepts and data.
QUAL - reflect on ideas before data collection - develop most of concepts during data collection - reexamines and reflects simultaneously and interactively
conceptualization
is the process of taking a concept and refining it by giving it a conceptual or a theoretical definition
conceptual definition
is a definition in abstract, theoretical terms
operationalization
links a conceptual definition to a specific set of measurement techniques or procedures, the concepts operational definition
Guidelines for Coming Up with a Measure
- Remember the conceptual definition
- Keep an open mind
- Borrow from other
- Anticipate difficulties
- Do not forget your units of analysis
Measurement process for QUAN
First conceptualization
Operationalization
Application of operational definition or measuring to collect the data
abstract ot concrete
conceptual hypothesis QUAN
A type of hypothesis in which researcher expresses variables in abstract, conceptual terms, and expresses the relationship among variables in a theoretical way
empirical hypothesis QUAN
a type of hypothesis in which the researcher expresses variables in specific terms and expresses the association among the measured indicators of observable
Conceptualization QUAL
QUAL - refine rudimentary working ideas during the data collection and analysis process - develop new concepts, formulate definitions for concepts, consider relationships among concepts, clear explicit definitions abstract - determined BY THE DATA
OPERATIONALIZATION QUAL
forms conceptual definitions out of rudimentary working ideas that they used while making observations or gathering data
instead of going from conceptual def to measurement operations - describe how specific observations and thoughts about the data contributed to working ideas that are the basis of conceptual definitions and theoretical concepts
operationalization - after the fact description
How to improve reliability
Conceptualize clearly
Increase level of measurement - more precise
Use multiple indicators of a variable
Pretests, pilot studies, replication
measurement validity
how well the conceptual and operational definitions mesh with each other
Content validity
is the full content of a definition represented in a measure
Criterion Validity
measurement validity that relies on some independent outside verification
Criterion validity > concurrent validity
relies on a pre-existing and already accepted measure to verify the indicator of a concept
criterion validity > predictive validity
measurement validity that relies on the occurrence of a future event or behavior that is logically consistent to verify the indicator of a concept
Qualitative researchers more interested in BLANK than validity
authenticity - fair honest and balanced account of social life from the POV of someone who lives it everyday
Credibility and transferability- external validity
internal validity
no errors internal to the design - eliminating alternative explanations
external validity
generalize from experimental research to settings or people that differ from the specific conditions of the study
statistical validity
achieved when an appropriate statistical procedure is selected and the assumptions of the procedure are fully met
Levels of measurement
an abstract but important and widely used idea.
Some ways in which a researcher measures a concept are at a higher more refined level and others are crude or less precisely specified
Continuous variables
Infinite number of values or attributes that flow along a continuum - can be divided into smaller increments
Discrete variables
relatively fixed set of separate values or variable attributes - contain distinct categories - religious affiliation
Nomial
Difference among categories
discrete
religion
ordinal
difference plus the categories can be ordered or ranked - likert
discrete
Interval
Everything the first two do and can specify the amount of distance between categories - celsius
arbitrary 0s
continuous
Ratio
everything all the other levels do plus there is a true 0
continuous
Mutually exclusive attributes
individual or case fits into one and only one attribute of a variable
religion - can only only fit into one category
exhaustive attributes
all cases fit into one of the attributes of a variable - every possible situation is covered - listing all religions
Index/scales
both produce ordinal or interval level measures of a variable
information about variables and possible to assess the quality of measurement
Index
summing or combining of many separate measures of a construct or variable
Scale
Like an index is an ordinal interval or ratio measure of a variable expressed as a numerical score. most are ordinal
two purposes of scales
- help in the conceptualization and operationalization processes - shows fit between indicators and construct
- scaling produces quantitative measures and can be used with other variables to test hypotheses
standardization
the procedure to statistically adjust measures to permit making an honest comparison by giving a common basis to measures of different units
concepts
the things studied
measurement * the process moves from the general to the specific:
conceptual definition
* operational definition
* identify indicators (variables) related to the operational
definition
* we first arrive at a conceptual definition and then identify
measures of those concepts; e.g. MBM vs before and after-tax
low income
quantitative data is more prone to _________ problems
validity
qual data is more prone to _________ problems
reliability
regardless of the level of measurement, every variable must
have two qualities:
the attributes must be exhaustive
- the attributes must be mutually exclusive
- Index:
typically just adds/averages items
- e.g. a political participation index would just add together
how many these things a person did - vote
- attend candidate debates
- donate money to political party
- sign on lawn during election
problem? Not all of the items in this index should be treated
equally
- Scales:
a technique for properly measuring the intensity of
items in relation to each other; most are ordinal level
