Upgrade to remove ads
Only $2.99/month

Quiz 1

Terms in this set (52)

statistic
summarize the characteristics of groups of persons
inference
formal logic that permits description of unobserved phenomena based on observed phenomena
error
deviations of what is desired in the survey process from what is attained
measurement error/ error of observation
deviations from answers given to survey question and the underlying attribute being measured
error of non-observation
deviations of a statistic estimated on a sample from that on the full population
observational unit
what is the survey about?
construct
elements of information that are sought by the researcher
measurement
ways to gather information about constructs
response
information provided through the survey measurements
outlier detection
lead to more careful examination of a particular completed questionnaire
target population
the set of units to be studied
sampling frame
a listing of all units in the target population
respondents
those successfully measured
non-respondents/ unit non-response
those that were not successfully measured
item missing data
the absence of information on individual data items for a sample case successfully measured on other items
weighting
a way of improving survey estimates
imputation
a process when data is missing and are replaced with estimated responses
postsurvey adjustments
different weighting and imputation procedures
mode of data collection
the way in which the data is collected
total survey error
a way to look at the error that may occur within a survey
construct validity
the extent to which the measure is related to the underlying construct
true value
the actual value
validity
the correlation of the measurement and the true ale measured over all possible trials and persons
expected value
average value
measurement error
a departure from the true value of the measurement as applied to a sample unit and the value provided; the observational gap between the ideal measurement and the response obtained
response bias
if there is a consistent direction of the response deviations over trials
bias
the difference between the expected value (over all conceptual trials) and the true value being estimated
reliability
if the value can be trusted
response variance
leads to instability in the value of estimated over trials
processing error
when a question may seem different to a different person; the observational gap between the variable used in estimation and that provided by the respondent
coding
text answers are categorized into numbered classes
finite population
target population
undercoverage
those in the target population that are not included in the frame population
ineligible units/ overcoverage/ foreign elements
those in the frame population that are not included in the target population
coverage bias
the proportion of the target population not covered by the sampling frame, and the difference between the covered and noncovered population
coverage error
a property of a frame and a target population on a specific statistic; the nonobservational gap between the target population and the sampling frame
sampling error
the nonobservational gap between the sampling frame and the sample
sampling variance
given the design for the sample, by chance many different sets of frame elements could be drawn
sampling bias
when some members of the sampling frame are given no chance (or reduced chance) of selection
realization
different sets of frame elements
sampling distribution
a plotting of the frequency of specific different values of the sample mean
probability sampling
whether all sampling frame elements have known, nonzero chances of selection into the sample
stratification
whether the sample is designed to control the representation of key subpopulations in the sample
element sample/ cluster sample
whether individual elements are drawn directly and independently or in groups
sampling variance
measures how variable the y-s are over all sample realizations
nonresponse error
when the values of statistics computed based only on respondent data differ from those based on the entire sample data
nonresponse bias
the product of the nonresponse rate (the proportion of eligible sample elements for which data are not collected) and the difference between the respondent and nonrespondent mean
fitness for use
acknowledges that different users of the same estimate may have different purposed for the information
credibility
the extent to which the producer of the information is judged by the user to be free of any particular point of view, a perspective on the phenomena being measured that may influence an outcome of the survey in a known direction
relevance
if a survey estimate measures a construct quite similar in meaning to the user's main concern
timeliness
available at a time needed for the decision based on the information
unit response
individuals who were successfully measured
YOU MIGHT ALSO LIKE...