Econ 101 1st Edition Lecture 9 Outline of Last Lecture I. Review II. Restriction of Range III. Golden RuleIV. Causation V. DeterminationVI. Scales of Measurement Outline of Current Lecture I. Review II. Reliability & ValidityIII. ErrorIV. Fundamental Equation of Classical Test Theory V. Internal Consistencya. Alpha Current LectureI.Review a. Restriction of Range can distort sample correlations b. Outliers can impact correlations c. Correlation does not prove causality – Reverse Causality, Reciprocal Causation, Common Cause (Third Variable) d. Coefficient of Determination (r2) e. Coefficient of Alienation (1 – r2) These notes represent a detailed interpretation of the professor’s lecture. GradeBuddy is best used as a supplement to your own notes, not as a substitute.f. Four Scales of Measurement i. Nominalii. Ordinaliii. Intervaliv. RatioII. Reliability & Validity a. Two Critical Attributes of Measuresi. Reliability1. How consistent is the measure?2. How precise is the measure?3. Technical: How much measurement error is involved?ii. Validity1. How well does a measure assess the underlying construct (i.e. accuracy)?2. Why do we care about reliability and validity?a. Garbage in, Garbage outi. If we don’t have good measurements and measurement tools to begin with, we wont have a good result iii. validity is more conceptual or philosophical while reliability is measured by consistencyb. Reliability coefficients reflect the proportion of true score variance to observed score variancei. Reliability= True Score Variance/ Total Varianceii. Conceptually – coefficientsrange from 0.0 (no true score variance) to 1.0 (all true-score variance)iii. Reliability: The consistency or precision of scores...iv. 4 Types (Source of Inconsistency)1. Internal Consistency (Different Items): for example, multiple items survey2. Test-Retest (Different Times of Measurement): for example, if measuring moods, maybe we asked people at different times, which means the moods change3. Parallel Forms (Different Forms) different forms of a test4. Inter-Rater (Different Observers): different doctors looking at one conditionIII. Errora. Observed vs. True Scores (Exam)• Observed Scores = The score you actually get • True score = What you really knowb. Error Scorei. Basically any discrepancy between the observed and true scoreii. What might cause measurement error on an exam?1.maybe if you were anxious or are sick or the test had bad questionsIV. Fundamental Equation of Classical Test Theory a. X=T+Eb. Where x= observed score c. T= true scored. E= error score V. Internal Consistencya. Making sure the questions appropriately measure what we want to find outb. When we correlate all of our data they should all be positive and above zeroc. The correlations will varyd. One way to summarize all of these would be to get the meane. Consider the Construct of Self-Esteemi. Global self-esteem reflects a person’s overall evaluation of value and worth. ii. William James (1890) argued that self-esteem was the result ofan individual’s perceived successes divided by their pretensions iii. Rosenberg (1965) defined global self-esteem as an individual’s overall judgment of adequacy iv. We can ask people questions that might reflect individual differences in self-esteem. – “I feel that I have a number of good qualitiesO– “I see myself as a person with high self-esteemO 1. We do not want to assume that these items are perfect indicators of an individual’s level of self-esteem 2. Any item has measurement error....f. Alpha i. Alpha is a global index of how strongly the items on a measure are associated with each