Typically the likert survey question includes a

  • No School
  • AA 1
  • fahratunnisa
  • 41

This preview shows page 32 - 35 out of 41 pages.

referred to as a satisfaction scale, that ranges from one extreme attitude to another. Typically, the Likert survey question includes a moderate or neutral option in its scale. The choice of answers using the 5-point Likert scale are as follow: 1.) Strongly Agree = 5 2.) Agree = 4 3.) Neutral = 3 4.) Disagree = 2 5.) Strongly Disagree = 1 3.6. Data analysis method The data that has been collected in this research will be analyzed in Structural Equation Modeling (SEM). According to Ghazali (2008) explained that Structural Equation Modeling (SEM) is a model of structural equation which is a simultaneous equation focusing on the predictions which is capable of describing latent variables (indirect measurable) and indirectly measured based on indicators (manifest variables). SEM analysis has a higher flexibility for researchers to link existing theory. Analyzed in SEM is the relationship between the latent variable (unobserved variable) and not between the manifest variable or between the indicator variables (observed variable). Hox and Bechger (2002) stated that SEM is a combination of corfirmatory factor analysis, regression analysis and path analysis. SEM is suitable for the present study because SEM can directly measure the relationships between latent
Image of page 32
and observed variables (Hair et al ., 2010). While Partial least squares are a method for construct preductive models when the factors are many and highly collinear. Partial least squares (PLS) regression is a technique reducing the predictors to a smaller set of uncorrelated components and performs least squares regression on these components, instead of on the original data. The rationale of the use of SEMPLS in this research is similar to the definition by Ghozali (2006), which is PLS is a soft modeling analysis method because it is not assume data that must be measured on a certain scale, which means the sample size can be small. 3.6.1. Evaluation of Measurement Model (outer model) The outer model is the part of the model that describes the relationships among the latent variables and their indicators. In this research author conduct measurement test as below: 3.6.1.1 Validity Test The research will be valid if able to be measured what should be measure as the researcher want. Several types of validity test are used to test the goodness of measures. (Sekaran, 2009). Validity is the extent to which the scores from a measure represent the variable they are intended to. By checking how well the results correspond to established theories and other measures of the same concept. A valid measurement is generally reliable: if a test produces accurate results, they should be reproducible. 3.6.1.2 Convergent Validity According to Bagozzi (1998) Convergent validity is the assessment to measure the level of correlation of multiple indicators of the same construct in agreement. 3.6.1.3 Discriminant Test
Image of page 33
Discriminant validity occurs where constructs that are expected not to relate do not, such that it is possible to discriminate between these constructs.
Image of page 34
Image of page 35

You've reached the end of your free preview.

Want to read all 41 pages?

  • Fall '19

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture