Lecture 8 Flashcards
what is measurement
researcher takes a concept, idea, or construct and develops measure to observe idea empirically
What are the two steps of measurement process
- conceptualization
- Operationalization
What is conceptualization
- refinement of abstract concepts
- conceptual definition
- process of thinking through the various meanings of the concept
What is operationalization
- development of specific research procedures that will result in empirical observations
- operational definition
why are operational definitions important in research
force us to think carefully and specifically in precise terms
- replication
- measurable
what is ethnic identity
- self identification within particular group
What is ethnic origin
Classification based on the ethnic group to which the individuals ancestors belong
Draw the levels of measurement
What are nominal measures
- categorical,
- no clear order
- least precise measurement
- mutually exclusive
- no math
What are ordinal level of measurement
- categories and can be ordered meaningfully
- mutually exclusive
- distances between variables not necessarily equal across range
What is interval level of measurement
- can be ordered
- actual value between has meaning
- numbers have meaning, but no true zero point - temp
What are ratio levels of measurement
- have characteristics of all and
- have an absolute zero point which represents absence of the attribute
- fixed measuring units
ex: body weight
What is reliability
ability of a measuring instrument to produce consistent results under consistent conditions
What is test-retest reliability
reliability across time
What is inter-rater reliability
independent evaluations conducted by different individuals
What is parallel forms reliability
reliability across indicators
What is internal consistency
- whether different items on same test correlate
how to improve reliability
- conceptualization
- increase level of measurement (ratio instead of ordinal)
- multiple indicators
What is validity
“degree of confidence we can place on inferences…. is the scale actually measuring what we think it is”
What is construct validity
theoretical concept, theme, idea based on empirical observations. Variable that is not directly measurable. may consist of multiple dimensions
What are the two types of construct validity
- convergent - used for multiple indicators based on idea that indicators of one construct will act alike or converge
- Discriminant - uses for multiple indicators based on idea that indicators of different constructs diverge
Can a test be valid if its not reliable
no
- not reliable = different results every time..
What does CFA stand for
confirmatory Factor analysis - “standardize measures”
What kind of sampling will you most likely use in qualitative
non-probability
What kind of samples will you most likely use in quantitative
probability
What are non probability sampling
- participants selected based on relevance to research topic than representativeness
- not good with generalizing
Why use non-probability samples
- too costly
- not methodologically viable
What are examples of non-probability sampling
- haphazard = convenience
- Quota
- Purposive - selected for reasons linked to research study
- snowball - identify few key individuals and ask to recruit others
- volunteer sampling
- judgement sampling
What does target population mean
- concretely specified large group of many cases from which a researcher draws a sample and to which results from a sample are generalized
- pop of interest which inferences desired
What does sample mean
Select subset of the target pop
What is a sampling unit
a member of the target pop
What is a sampling frame
list of all available sampling units in the target pop
What is a sampling ratio
The ratio of the size of the sample to the size of the target pop
What is probability sampling and 2 primary criteria
- method of sampling allowing inferences to be made on pop based on observations from sample
- avoid selection bias
- generalizable
1. individuals randomly selected
2. individuals must have a non-zero chance of being selected
What does random mean
- each element in a pop an equal probability of being selected
What is SRS and pros cons
ex: lottery draw
advantages - simple to conduct
disadvantages - requires list prior to sampling, expensive
What is systematic sampling
- gap or interval between each selection
What is stratified sampling
- divide pop into strata
- groups = mutually exclusive and exhaustive
- select random sample from within each group
What is cluster sampling
- divide pop into clusters and random sample of there clusters is selected
- typically= researcher cannot get a complete list of members of the pop
difference between stratification and clustering
stratification - divide groups different from each other
clustering - divide pop into comparable groups
