Chapter 4: Measuring Data

Chapter 4: Measuring Data New Vocabulary: Reliability: the consistency or repeatability of the measurement Internal consistency reliability: homogeneity of the measurement instrument Inter-rater reliability: a comparison of the measurements obtained by two different data collectors to make sure they are similar Validity: the accuracy of a measurement Content validity: a determination that an instrument measures what it is designed to measure Convergent validity: test results obtained are similar to test results of a previously validated test of the same thing Divergent validity: the measurement of the opposite variable of a previously validated measurement yields the opposite result Predictive validity: the measurement of how accurately an instrument suggests future outcomes or behaviours Feasibility -​ How practical something is -​ Consider the cost, time, training, and limitations of the study sample Validity -​ Content validity evaluates how well an instrument (like a test) covers all relevant parts of the construct it aims to measure -​ Convergent validity involves comparing your results to a previously validated study that measures the same thing. A correlation of 0.4 or higher strengthens the validity of your study -​ Predictive validity involves how well your test can predict something for the future -​ Divergent validity involves measuring the opposite variable of a previously validated measurement in which you should get the opposite result -​ Construct validity is used to determine how well a construct measures what it is designed to measure, such as a math test for aptitude Reliability -​ Reliability means that your measurement tool is consistent and repeatable. -​ 3 main factors relate to reliability: stability, homogeneity, and equivalence 1.​ Stability is the consistent or enduring quality of the measure a.​ Should not change over time b.​ Should have a high correlation coefficient when administered repeatedly 2.​ Homogeneity is the extent to which items on a multi-item instrument are consistent with one another a.​ Internal consistency reliability involves homogeneity of the measurement instrument b.​ Cronbach's alpha (a) is used for measurement tools that measure a single concept from 0-1. A higher value indicates better internal consistency reliability 3.​ Equivalence is how well multiple forms of an instrument or multiple users of an instrument produce/obtain the same results a.​ You should consider inter-rater reliability to observe if multiple raters come to the same conclusion