PO217 Lecture Notes - Lecture 5: Convergent Validity, Predictive Validity, Face Validity
Document Summary
Overview: spurious, intervening, and conditional (reinforcing) variables, what are indicators, converting a proposition into a testable form, what is measurement, rules and levels of measurement, nominal-level measurement, ordinal-level measurement. Interval-level measurement: ratio-level measurement, validity vs. reliability, systematic vs. random errors, face validity, convergent validity, discriminant (divergent) validity, predictive validity, test-retest reliability, parallel-form reliability, sub-sample reliability, formulating hypotheses, common errors in formulating hypotheses, key terms. If cv = 1 then: independent variable dependent variable. If cv = 2 then: independent variable dependent variable i. e. individuals who support affirmative action will be more likely to vote for social democratic parties compared to those who oppose to affirmative action. If cv1 = well informed then: affirmative action vote choice. If cv2= not well informed then: affirmative action vote choice the focus is always on how the hypothesized relationship is affected by different values of the conditional variable.