CHAPTER 6 MEASUREMENT SCALES (Disarikan dari berbagai sumber)
MEASUREMENT • Selecting observable empirical events. • Using numbers or symbols to represent aspects of the events. • Applying a mapping rule to connect the observation to the symbol.
WHAT IS MEASURED? • Objects: – Things of ordinary experience, e.g. table, person, book, car. – Some things not concrete, e.g. gen, attitude, neutron.
• Properties: characteristics of objects – Character of the object, e.g. physical: weight, height, posture. – Psychological: attitude, intelligence. – Social: leadership, team affiliation, status.
WHAT IS DATA? • Is a set of values of qualitative or quantitative variables. • As s general concept refers to the fact that some existing information or knowledge is represented or coded in some form suitable for better usage or processing.
DATA TYPES
Discrete
Ordinal
Quantitative Types of Data
Continue
Interval
Qualitative Ratio
DATA TYPES • Classification: – Nominal Scale (has number), e.g. 1. Male and 2. Female.
• Order: – Ordinal Scale, e.g. 1. STS, 2. TS, 3. CS, 4. S, 5. SS.
• Distance (interval between numbers): – Interval, e.g. temperature.
• Origin of number series: – Ratio, e.g. Production, Sales, Credit, DPK)
DATA TYPES Order
Interval
Origin
Nominal
None
None
None
Ordinal
Yes
Unequal
None
Interval
Yes
Un/equal
None
Ratio
yes
equal
zero
SOURCES OF MEASUREMENT DIFFERENCES • • • •
Respondent. Situational factors. Measurer or researcher. Data collection instrument.
WHAT IS SCALING?
Scaling is assigning numbers to indicants of the properties of objects
SCALE SELECTION • Depend on: – Study Objective Apa sasaran dari penelitian? Apakah kita mengukur ciri-ciri respondent atau objek stimulus? – Response Form Rating, Ranking, atau Kategorisasi? – Degree of Preference Apakah kita mengukur preferensi atau penilaian nonpreferensi?
SCALE SELECTION • Depend on: – Data Properties Apakah dengan skala nominal, ordinal, interval, atau rasio? – Number of Dimension Apakah mengukur dengan skala satu dimensi atau multi dimensi? – Scale Construction Apakah mengembangkan skala melalui keputusan arbitrer, konsensus, analisis butir, skala kumulatif, atau analisis faktor?
TYPES OF DATA MEASUREMENT SCALES • Rating Scales Penilai menandai jawabannya pada suatu titik sepanjang suatu rangkaian kesatuan (continuum).
• Ranking Scales Subjek secara langsung membandingkan dua atau lebih objek dan melakukan pemilihan terhadap berbagai objek tersebut.
• Categorization
TYPES OF RATING SCALES • Simple category • Multiple choice, single response • Multiple choice, multiple response • Likert scale • Semantic differential
• • • • •
Numerical Multiple rating Fixed sum Stapel Graphic rating
TYPES OF RANKING SCALES • Paired-comparison – Responden menyatakan sikapnya secara tidak rancu dengan memilih di antara dua objek.
• Forced Ranking – Responden diminta untuk membuat urutan peringkat dari pilihan mereka.
• Comparative
SCALING TECHNIQUES • Thurstone Scale – a.k.a. equal-appearing interval scale an expensive, time-consuming type of consensus scaling that results in an interval rating scale for attitude measurement. – Dibuat dalam sejumlah pernyataan (40 – 50) yang relevan dengan variabel yang hendak diukur kemudian sejumlah ahli (20 – 40) orang menilai relevansi pernyataan. Dengan skor 1 – 11, dimana skor 1 menyatakan sangat tidak relevan.
SCALING TECHNIQUES • Likert Scale – Developed by Rensis Likert (pronounced Lick-ert) – This scale is designed to examine how strongly subjects agree or disagree with statements on a 5-point scale with following anchors:
SCALING TECHNIQUES • Guttman Scale – Pada skala ini akan di dapat jawaban yang tegas. Hanya ada dua interval yaitu “setuju atau tidak setuju”. – Penelitian ini dilakukan bila ingin mendapatkan jawaban yang tegas terhadap suatu permasalahan yang ditanyakan.
SCALING TECHNIQUES • Bogardus Scale – A.k.a. Bogardus Social Distance mengukur “jarak sosial” antar individu (kelompok) atau sikap penerimaan terhadap individu (kelompok) lain. – Berbentuk 5 – 7 pernyataan dengan skor 1 – 7, dimana skor 1 menunjukkan tidak ada jarak sosial.
SCALING TECHNIQUES • Semantic Diffrential Scale Measures the psychological meanings of an attitude object using bipolar adjectives. The semantic differential scale is used to assess respondents’ attitudes toward a particular brand, advertisement, object, or individual. The responses can be plotted to obtain a good idea of their perceptions.