Measurement Basics Chapter 13 Measurement rules for assigning

Measurement Basics Chapter 13

Measurement • “rules for assigning numbers to objects in such a way as to represent quantities of attributes” - Bennett (1995), pg, 173 SLIDE 13 -1

Scales of Measurement Interval Ordinal HIGHER Ratio Nominal Higher levels of measurement have all the properties of lower levels of measurement. SLIDE 13 -2

Nominal Scale Basic Comparisons Identity Examples Measures of Average male-female user-nonuser occupations uniform numbers mode Which of the following soft drinks do you like? Check all that apply. � Coca-Cola � Mountain Dew � Seven Up � Dr. Pepper � Pepsi � Sprite SLIDE 13 -3

Ordinal Scale Basic Comparisons Order Examples Measures of Average brand preference median social class hardness of minerals lumber quality grades Rank the following soft drinks from 1 (least liked) to 6 (most liked): ___Coca-Cola ___Mountain Dew ___Seven Up ___Dr. Pepper ___Pepsi ___Sprite SLIDE 13 -4

Interval Scale Basic Comparisons Comparison of intervals Examples Measures of Average temperature grade point avg. brand attitude company image mean What is your overall opinion about each of these brands? Coca-Cola Dr. Pepper Pepsi Sprite unfavorable 1 2 3 4 4 5 5 favorable 6 7 6 7 SLIDE 13 -5

Ratio Scale Basic Comparisons Comparison of absolute magnitudes Examples Measures of Average units sold # of purchases age income geometric or harmonic mean Divide 100 points among these soft drinks according to your likelihood of purchasing each within the next week: ___Coca-Cola ___Mountain Dew ___Seven Up ___Dr. Pepper ___Pepsi ___Sprite SLIDE 13 -6

Hypothetical Construct • A concept used in theoretical models to explain how things work. Hypothetical constructs include such things as attitudes, personality, and intentions, concepts that cannot be seen but that are useful in theoretical explanations. SLIDE 13 -7

The Problem of Measurement C C C Observable Data C SLIDE 13 -8

Potential Sources of Variation in Scores • • True differences in the characteristic being measured. Differences in other relatively stable characteristics of the individual. Differences due to temporary personal factors. Differences due to situational factors. Differences due to variations in administration. Differences due to the sampling of items. Differences due to lack of clarity of the measuring instrument. Differences due to mechanical factors. SLIDE 13 -9

Variation in Obtained Scores XO = X T + X S + X R Where XO = obtained score XT = true score XS = systematic error XR = random error SLIDE 13 -10

Establishing the Validity of Measures • Predictive validity • Content validity • Construct validity • Reliability SLIDE 13 -11

Illustration of Random Error . . . . Old Rifle . . . New Rifle That is Sighted in Accurately SLIDE 13 -12

Illustration of Systematic Error . . . New Rifle That is Sighted in Poorly . . . New Rifle That is Sighted in Accurately SLIDE 13 -13

Developing Measures Specify Domain of the Construct Purify Measure Generate Sample of Items Assess Validity Collect Data SLIDE 13 -14