5] Reliability And Validly Flashcards
What is a variable
It is something you’re trying to measure in some way and can take on different values
What are the categories of variables
1: some are unique like DNA
2: some vary little among the general population like committing a crime
3: some categories of people have different but same variables like height
What is qualitative research
Qualitative research involves collecting and analysing non-numerical data to understand concepts opinions or experiences
What is quantitative research
Quantitive research means collecting and analysing numerical data to describe characteristics find correlations or test hypothesis
Compare qualitative and quantitative research: common purpose
Qualitative: discover Ideas with general research objectives
Quantitative: test hypothesis or specific research questions
Compare qualitative and quantitative research: approach
Qualitative: observe an interpret
Quantitive: measure and test
Compare qualitative and quantitative research: data collection
Qualitative: unstructured free-form
Quantitive: structured response, categories provided
Compare qualitative and quantitative research: research independence
Qualitative: Is intimately involved and results are subject
Quantitive: uninvolved observer and results are objective
Compare qualitative and quantitative research: samples
Qualitative: small samples often in a natural setting
Quantitive: large samples to produce generalisable results
What are mixed methods
They are studies that incorporate both qualitative and quantitive methods
What is a construct
A construct is a theoretical concept theme or idea based on observations and is usually not directly measurable for example self-esteem
What is an operational definition
An operational definition is a description of the procedure for measuring some objective variables to study an underline constructs
Why should you be careful when using an operational definition
1: The things you measure may not be the concepts in which you are interested in, and may not address important aspects of the concept
2: You also need to be aware that the things you are measuring may be influenced by other constructed as well
What is reliability
Reliability in a study is how reproducible or replicable it is and how consistently the method of measuring something is in terms of quality and performance
What is test re-test reliability
It is the degree to which test scores remain unchanged when measuring a stable individual characteristic on different occasions
What is inter rate reliability
This refers to whether separate judges give a participant the same score on an observational measure
What is internal reliability
It refers to how consistently different questions (items) within the same test measure the same concept or construct, so the results across all the questions in the test when produced again share a similar value
E.g: if someone answered agree to “I like riding bikes” and then disagreed with the statement “I hate bikes” then the internal consistency is good
What does validity mean
Refers to how accurately it measures what it has intended to and how well the results among the study participants represent true findings among similar individuals outside of the study.
E.g: if research has high validity it means that it produces results that correspond to real properties, characteristics and variations in the physical and social world
What is face validity
It’s when something looks like it measure what it is suppose to
E.g: sociability test- having no friends
Although it has problems like it’s a subjective measure and sometimes research may be valid but not her face validity
What is content validity
When the measure examines the full range of content associated with the construct
E.g: test measuring ability in science should involve questions in biology chemistry and physics
What is construct validity
When the extent to which your test or measure a concept accurately evaluates what it is supposed to
E.g: If the researcher wants to evaluate respondents happiness levels the instruments construct validity would be the extent to which assesses the respondents levels of energy positivity and smiling as opposed to fretfulness anger and negativity
What is criterion related validity
The extent to which the measure is related to some important behaviour that is external to the measure itself
E.g: you can check if your job performance test correlates with the actual ratings for feedback from supervisors customers or peers
What are the types of criterion related validity
1: concurrent validity
The extent of agreement between two different tests for measurements taken at the same time
E.g: results from a new test of intelligence should be similar to the results on a standard highest IQ test
2: predictive validity
The extent to which a measure or test accurately predict future behaviour performance or outcomes
E.g: we could validate leaving cert points as a measure of academic ability by saying how accurately they predict performance in college
