chp.10 Flashcards
4 steps from data collection to sumamry:
Collect the data
Deal with data errors/omissions
Reduce data to manageable size
Develop summaries
what is data?
collective units of information from a subject or case
measured by a data collector following consistent
procedures
raw and unprocessed
what does consistency make data?
verifiable, but not necessarily truthful
2 types of data
primary
secondary
primary data
data the research collects to address the specific
problem at hand
secondary data
originally collected to address a problem other than the
one which require the manager’s attention at the
moment
6 dimensions of data quality
accuracy
consistency
validity
completeness
uniqueness
integrity
accuracy
the level to which data represents the real-world scenario and confirms with a verifiable source
consistency
represents if the same information stored and used at multiple instances matches.
Expressed as the percent of matched values across various records.
validity
signifies that the value attributes are available for aligning with the specific domain or requirement.
completeness
measures if the data is sufficient to deliver meaningful inferences and decisions
uniqueness
indicates if it is a single recorded instance in the data set used. Ensures no duplication or
overlaps.
integrity
indicates that the attributes are maintained correctly, even as data gets stored and used in
diverse systems. Ensures that all enterprise data can be traced and connected.
measurement
assigning numbers to empirical events, objects or properties, or activities in compliance with a set of rules.
what’s a mapping rule
scheme for assigning numbers to aspects of an empirical event
4 most used classifications of measurement
nominal - male or female
ordinal - low/middle/high income
interval - 13 degrees
ratio - defined 0 point eg lbs or $
4 characteristics of mapping rules
classification
order
distance
origin
classification
numbers are used to group or sort responses.
order
numbers are ordered. One number is greater than, less than, or equal to another number.
distance
differences between numbers can be measured.
origin
the number series has a unique origin indicated by the number zero.
:)
:)
nominal
Mutually Exclusive
Collectively Exhaustive
Categories
Classification Only
ordinal
Nominal Scale
Characteristics
+ Order
Conforms to logical
postulate (> or <)
interval
Ordinal Scale
Characteristics
Equality of interval
Equality of distance
between numbers
ratio
Interval Scale
Characteristics
Absolute Zero
Recoding
Adjust variable after data collection
Apply new mapping rules
Only REDUCE variable power
Less powerful statistical analysis
4 sources of error
participant
situation
measurer
instrument
participant error
Opinion differences that affect measurement come from relatively stable characteristics of
the participant.
situation error
Any condition that places a strain on the interview or measurement session.
measurer error
The interviewer can distort responses by rewording, paraphrasing, or reordering
questions.
Stereotypes in appearance and action.
Careless mechanical processing.
instrument error
A defective instrument can cause distortion by being too confusing and ambiguous and not
all-encompassing.
3 characteristics of good measurement
valid
reliable
practical
validity
the extent to which a test measures what we wish to measure.
reliability
refers to the accuracy and precision of a measurement procedure.
practicality
concerned with a wide range of factors of economy, convenience, and
interpretability.
what does this tell us
WITHOUT RELIABILITY YOU CANNOT HAVE VALIDITY…
you can be reliable and not valid - You can consistently measure the wrong thing
A measure is reliable to the degree that it…
…supplies consistent results
Reliable instruments are…
robust and work well under different times and different conditions
The distinction of time and condition is the basis for three perspectives on reliability…
stability
equivalence
internal consistency
measures: stability
secure consistent results with repeated
measurements of the same person with the same instrument.
how to test for stability
test-retest, a correlation will tell you how stable something is
Internal consistency is a characteristic of an instrument…
…in which the items are homogeneous.
equivalence is concerned with…
…variations at one point in time among observers and samples of
items.
equivalence can be seen if…
…we get a few observers to score or observe one event, and see how similar they all are
scientific requirements
measurements to be reliable and valid
operational requirements
measurements to be practical
practicality means we consider: (3 things)
economy
convenience
interpretability
how does a measuring device pass the convenience test?
if it’s easy to administer
why is interprebility important?
for when people other than the test designer want to assess results/data/info