Meeting-5 MEASUREMENT 8-1
Measurement Measurement Process: 1. Selecting observable empirical events 2. Using numbers or symbols to represent aspects of the events being measured 3. Applying a mapping rule to connect the observation to the symbol 8-2
8-3 Characteristics of Measurement
What is Measured? Objects: Things of ordinary experience: furniture, people, cars Some things not concrete: genes, attitudes etc. Properties: characteristics of objects: Physical : weight, height and posture Psycological : attitudes, behaviour, intelligence Social : leadership ability, status 8-4
Levels of Measurement Nominal Ordinal interval Ratio Classification Classification Order Classification Order Classification Order Distance Distance Natural Origin 8-5
8-6 Measurement Scales
Data Types Order Distance Origin Nominal none none none Ordinal yes unequal none Interval yes equal or none unequal Ratio yes equal zero 8-7
Sources of Measurement Differences Respondent: employee status, ethnic, social class, fatigue, boredom, hunger, impatience, anxiety Situational factors: the existence of other person Measurer or researcher: rewording, reordering questions, incorrect coding, careless tabulation, faulty statistical calculation Data collection instrument: the use of complex words and syntax, ambigious meaning, mechanical defects 8-8
The Criteria for Evaluating a Measurement Validity: a characteristic of measurement concerned with the extent that a test measures what we actually wish to measure. Reliability: a characteristic of measurement concerned with accuracy, precision and consistency. Practicality is concerned with a wide range of factors of economy, convenience, and interpretability. 8-9
8-10 Understanding Validity and Reliability
Validity and Reliability Test Questionnaire Test Validity Realibility Correlation Analysis (Pearson): Total Variable & Each Variable If Sig. < 0,05 valid If Sig. > 0,05 not valid delete the question Realibility Statistics If Cronbach s Alpha > 0,6 the instrument is reliable. If Cronbach s Alpha < 0,6 the instrument is not reliable 8-11
Validity and Reliability Test 1. Validity Test Using SPSS software to do the correlation analysis Pearson Correlation. Find correlation between each question in the questionnaire and its total value. See the significance value (Sig.): If Sig. < 0.05 the question/instrument is valid If Sig. > 0.05 the question/instrument in not valid deleted/removed 8-12
Validity and Reliability Test Example of validity test: Open SPSS program Open the data: validity&reliability1_original.sav First Step: Making new variable Total 1. Choose Transform Compute variable 2. Type the new name variable. Total in the Target variable box. 3. Entry and suming all variables (from question1 to question15) to Numeric Expression box. 4. Click OK. 5. Then in SPSS - Data View, you can see the new variable (Total) with its values. 8-13
Validity and Reliability Test Second Step: Correlation Analysis 1.Open the data: validity&reliability1_original.sav 2.Choose Analyze Correlation Bivariate 3.Enter all variables to the Variables box 4.Click Pearson s box in the Correlation Coefficient box and click Flag significant correlation s box. 5.Click OK 6.The output as seen below: 8-14
8-15 Validity and Reliability Test
Validity and Reliability Test 2. Realibility Test Using SPSS software to find Realibility Statistics Cronbach s Alpha. If Cronbach s Alpha > 0.6 the instrument is reliable If Cronbach s Alpha < 0.6 not reliable Example of realibility test: The steps: 1.Open SPSS program 2.Open the data: validity&reliability1_original.sav 3.Choose Analyze Scale Reliability Analysis box 4.Entry all variables to the Items box 5.Click Statistics Reliability Analysis box. 6.Click Scale if item deleted in the Decriptive for box 7.Click Continue 8.Click OK. 8-16
Validity and Reliability Test The output of reliability analysis: 8-17