Ch 5 The process of measurement Flashcards
measurement
refers to the process of describing abstract concepts in terms of specific indicators by assigning numbers or other symbols to these indicators in accordance with rules
measurement is the process of moving from ____ to the ____
abstract (theoretical level)
concrete
measurement is essentially the process of ____ concepts
operationalizing
Indicator
An observation that we assume is evidence of the attributes or properties of some phenomenon - ex, childs broken leg is an indicator that maybe there is child abuse
Item
Used to refer to a single indicator of a variable
Index or scale
a composite of multiple items
scales allow us to measure variables in a more precise and accurate fashion
3 techniques of measuring
verbal reports - most common. answering questions, interviews, etc
observation - watching people
archival records - using recorded information already done
logic of measurement equation
positivist view of science
X = T + E
x = observation/measurement t = true phenomenon e = error
we strive for measurement with no error so that x = t
ex. reading on a weight scale = your actual weight + clothing you are wearing; heavy things in pocket
non positivist view argue what 2 things?
argue that we haven’t examined a huge assumption which is that T exists objectively in the world and our measurement device is merely discovering it and its properties
argue that many social science concepts do not have such clear and objective referents in the world
level of measurement
the rules that define permissible mathematical operations that can be performed on a set of numbers produced by a measure
4 types (levels) of measurement
nominal
ordinal
interval
ratio
nominal measures (1st type)
classify observations into mutually exclusive and exhaustive categories
they are discrete variables
ex - variables like sex, ethnicity, religion, political preference
if we use religion and categorize them into one religion, they don’t go in the other religious groups, therefore are mutually exclusive.
exhaustive categories mean there is a category for every case, meaning you have other as an option AND no religion as an option too
ordinal measures (2nd type)
are of a higher level than nominal measures because in addition to having mutually exclusive and exhaustive categories, the categories have a fixed order, but not always equal spacing
they are discrete variables
ex. socioeconomic status - ranking the statuses
interval measures (3rd type)
share the characteristics of ordinal scales - mutually exclusive and exhaustive categories and an inherent order - but have equal spacing between categories
variables are often continuous
ex. Difference of 70 degrees and 80 degrees is the same as 30 degrees and 40 degrees difference
ratio measures (4th type)
has all the characteristics of interval measures, but the 0 point is absolute and meaningful rather than arbitrary
variables are often continuous
ex - no income at all is 0$
discrete variables
have a specific number of distinct and separate values
ex- sex, household size, number of days absent, number of arrests
continuous variables
can take on an infinite number of values
ex - age because we can measure by years, months, weeks, days, minutes, seconds
a variable is either ____ or ____
discrete or continuous
validity
refers to the accuracy of a measure
face validity
involves assessing whether a logical relationship exists between the variable and the proposed measure
it is subjective in nature
its the weakest demonstration of validity therefore should only be used as a starting point
content validity or sampling validity
has to do with whether a measuring device covers the full range of meanings or forms that are included in a variable to measure
somewhat subjective
contains a detailed analysis of the breadth of the measured concept and its relationship to the measuring device
- determine full range or domain of the content of a variable
- determine whether all those remains are represented among the items that constitute the measuring device
jury opinion
gather opinions of other investigators regarding whether particular operational definitions are logical measures of the variable
criterion validity
establishes validity by showing a correlation between a measurement device and some other criterion or standard that we know or believe accurately measures the variable under consideration
provides more objective evidence
concurrent validity
a type of criterion validity
compares the instrument under evaluation to some already existing criterion, such as the results of another measuring device
a weakness is the validity of the existing measure that is used for comparison
predictive validity
a form of criterion validity
An instrument predicts some future state of affairs
construct validity
The most complex types of validity
Involves relating an instrument to an overall theoretical framework to determine whether the instrument is correlated with all the concepts and propositions that comprise the theory
multitrait-multimethod approach
One form of construct validity
- Two instruments that are valid measures of the same concept should correlate rather highly with each other even though they are different instruments
- Two instruments, even if similar to each other, should not correlate highly if they measure different concepts
reliability
refers to a measure’s ability to yield consistent results each time it is applied
reliable measures only fluctuate because of variations in the variable being measured
test-retest
the first and most generally applicable assessment of reliability
this technique involves applying a measure to a sample of people and then, somewhat later, applying the same measure to the same people again
divide test group randomly into experimental group and test twice, and a control group and test once
a correlation coefficient of _____ or better normally is necessary for a measure to be considered reliable
0.80
a correlation of ___ means highly reliable
0.98
advantage of test-retest
we can use it with many measures
disadvantage of test-retest
slow and cumbersome to use with two required testing sessions and the desirability of a control group
outcome may not be clear
cannot use it on measures of variables whose value might have changed during the intervals between tests
multiple forms
type of reliability
create 2 separate but equivalent versions made up of different items, like different questions. Administer the two forms to the same people during a single testing session. If the correlation is sufficiently high, we can assume that each scale is reliable
advantages to multiple forms
requiring only one testing session or a control group is impractical
don’t need to worry about variables changing over time
disadvantages to multiple forms
the items on both forms will be quite similar, that people may realize they are responding to the same items twice
the difficulty of developing two measures with different items that really are equivalent
internal consistency approaches (split half approach)
type of reliability
use a single scale that is administered to one group of people to develop an estimate of reliability
spearman-brown formula
r = 2ri/1+ri
ri = uncorrected correlation coefficient
r = corrected correlation coefficient (reliability coefficient)
advantages to internal consistency approach
require only one testing session and no control group
give the clearest indication of reliability
disadvantage to internal consistency approach
we cannot always use them
it is important to refine measuring instruments to assure they are valid and reliable measuring among ___
minorities
there is no such thing as ____ measurement
exact
random errors are essentially ____ errors that in the long run, tend to cancel themselves out
chance
____ error is consistent and patterned. errors do not cancel out
systematic
6 ways to improve validity and reliability
develop concepts more extensively
improve training of those who will be applying the measuring devices
interview subjects of research about measurement devices
use higher level of measurement
use more indicators of a variable
conduct an item by item analysis
5 ways to choosing a measurement device
consider theoretical relevance to research
emphasize proven reliability and validity
opt for higher level of measurement
minimize systematic and random error
consider feasibility issues