Chapter11 Measurement

167 Views

Download Presentation
## Chapter11 Measurement

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -

**授課教授 : 洪新原教授**李彥杰 602556001 鄭玲潔602556027 周敬堯602556025 Chapter11 Measurement**The Nature of Measurement**• Measurement in research consists of assigning numbers to empirical events, objects or properties, or activities in compliance with a set of rules. • This slide illustrates the three-part process of measurement. A mapping rule is a scheme for assigning numbers to aspects of an empirical event.**Empirical**Researchers use an empirical approach to describle，explain，and make predictions by relying on information gained through observation.**Characteristics of Measurement**樣本元素 實證觀察 映射規則 符號**measurement –**• of assigning numbers to empirical events in compliance with a set of rules**An operational definition defines a variable in terms of**specific measurement and testing criteria**What is measured ?**The concepts of ordinary experience • Physical properties • Psychological properties • Social properties P273Exhibit11-2**Measurement Scales**Nominal Classification Classification Ordinal Order interval Classification Distance Order Ratio Classification Distance Order Natural Origin Exhibit11-3**調查問題**10**Nominal Scales 名目尺度**• Just Labels , not have quantitative value • Nominal scales are the least powerful of the four data types . • The number count of cases in each category (the frequency distribution) ,the researcher is retricted to the use of the mode as the measureof central tendency.**The mode (眾數)**• – the most frequently occurring value. • classify a set of properties into a set of equivalent classes. • Valuable • - The objective is to uncover relationships rather than secure precise measurements. • This type of scale is also widely used in survey and other research when data are classified by major subgroups of the population.**Ordinal Scales**• Include the characteristics of nominal scale plus an indication of oder. • Ordinal data require conformity to a logical postulate：if a is greater than b and b is greater than c,then a is greater than . • Ordinal data include attitude and preference scales. • The numbers used with ordinal scales have only a rank meaning,the appropriate measure of central tendency is the median. • Correlational analysis of ordinal data is restricted to various ordinal technique.**Interval Scales**• Have the power of nominal and ordinal data plus one additional strength- the concept of equality of interval. • When a scale is interval and the data are relatively symmetric with one model, you use the arithmetic mean as the measure of central tendency. • The standard deviation is the measure of dispersion. • The product-moment correlation,t-test,F-test,and other parametric tests are the stistical procedures of choice for interval data. • Use the median as the measure of central tendency and the interquartile range as the measure of dispersion.**Ratio Scales**• Incorporate all of the powers of the previous scales plus the provision for absolute zero or origin. • Ratio data represent the actual amounts of a variable. • Measures of physical dimensions such as weight,height…**Sources of Measurement Differences**• Much error is systematic(results from a bias), while the remainder is random(occurs erratically). • Four major error sources may contaminate the results： • The respondent • The situation • The measurer • The data collection instrment**The respondent**• Opinion differences that affect measurement come from relatively stable characteristics of respondent. • Typical of these are employee status, ethnic group membership, social class, and nearness to manufacturing facilities. • Respondent also suffer from temporary factors like fatigue, boredom.**The situation**• Any condition that places a strain on the interview of measurement session can have serious effects on the interviewer-respondent rapport.**The Measurer**• The interviewer can distort response by rewording, paraphrasing, or reordering question. • In the data analysis stage, incorrect coding, careless tabulation, and faulty statistical calculation may introduce further errors.**The Instrument**• A defective instrument can cause distortion in two major ways • It can be too confusing and ambiguous. • Poor selection from the universe of content items.**The Characteristics of Good Measurement**• What are the characteristics of a good measurement tool? A tool should be an accurate indicator of what one needs to measure. It should be easy and efficient to use. • There are three major criteria for evaluating a measurement tool： • Validity is the extent to which a test measures what we actually wish to measure. • Reliability refers to the accuracy and precision of a measurement procedure. • Practicality is concerned with a wide range of factors of economy, convenience, and interpretability.**Validity**• The text features two major forms： • External validity • Internal validity • There are three major forms of validity: • Content • Construct • Criterion**Validity Determinants**Content Criterion Construct**Content validity**Content Criterion Construct**Content validity**• To evaluate content validity • one must first agree on what elements constitute adequate coverage. • To determine content validity • one may use one’s own judgment and the judgment of a panel of experts. • Content validity is primarily concerned with inferences about test construction rather than inferences about test scores**Increasing Content Validity**Content Literature Search Etc. Expert Interviews Question Database Group Interviews**Criterion – related validity**Content Criterion Construct**two types of criterion validity:**Criterion Concurrent predictive**Judging Criterion Validity**Relevance Criterion Freedom from bias Reliability Availability**Construct validity**Content Construct**Increasing Construct ValidityConvergent / discriminant**validity New measure of trust Known measure of trust Empathy Credibility**Reliability Estimates**Stability Internal Consistency Equivalence**Reliability Stability**Stability Internal Consistency Equivalence**Reliability - Stability**• Observation studies • Survey situation • Test-retest • can be used to assess stability. • Cause bias： • 1.Time delay between measurements • 2.Insufficient time between measurements • 3.Respondent’s discernment of a study’s disguised purpose • 4.Topic sensitivity**Reliability - Equivalence**Stability Internal Consistency Equivalence**Reliability Internal Consistency**Stability Internal Consistency Equivalence**Practicality**measurement requirements ： process to be reliable and valid operational requirements ： call for it to be practical. Economy Convenience Interpretability**1.A statement of the functions ;**• 2. Detailed instructions for administration; • 3. Scoring keys and instructions; • 4. Norms for appropriate reference groups; • 5. Evidence of reliability; • 6. Evidence regarding the intercorrelations of subscores; • 7. Evidence regarding the relationship of the test to other measures; and • 8. Guides for test use. Interpretability