The research will be valid if able to be measured

  • No School
  • AA 1
  • fahratunnisa
  • 42

This preview shows page 34 - 36 out of 42 pages.

The research will be valid if able to be measured what should be measure asthe researcher want. Several types of validity test are used to test the goodness ofmeasures. (Sekaran, 2009). Validity is the extent to which the scores from ameasure represent the variable they are intended to. By checking how well theresults correspond to established theories and other measures of the same concept.A valid measurement is generally reliable: if a test produces accurate results, theyshould be reproducible.3.6.1.2 Convergent ValidityAccording to Bagozzi (1998) Convergent validity is the assessment tomeasure the level of correlation of multiple indicators of the same construct inagreement. 3.6.1.3 Discriminant TestDiscriminant validity occurs where constructs that are expected not torelate do not, such that it is possible to discriminate between these constructs.(ChangingMinds.org,).3.6.2 Reliability TestReliability test is how consistent a measure is of a particular element over aperiod of time, and between different participants. For example, a test measuringpersonality trait should yield the same answers for a subject after several timescompleting the test, and with a short period of time between (so long as theindividual has not inherently changed personality traits). By checking theconsistency of results across time, across different observers, and across parts ofthe test itself. A reliable measurement is not always valid: the results might bereproducible, but they’re not necessarily correct.
Background image
3.6.2.1 Cronbach AlphaAs a reliability coefficient, Cronbach’s alpha estimates the reliability of thescale by determining the internal consistency of the test or the average of all thecorrelations between each item and the total score (Fink, 2003). According to(Sekaran, 2009) Alpha Cronbach is reliable coefficients that can indicate howgood items in asset have positive correlation one another.3.6.2.2. Composite ReliabilityComposite reliability (sometimes called construct reliability) is a measure ofinternal consistency in scale items, much like Cronbach’s alpha (Netemeyer,2003). According to (Ghozali, 2013) reliability of composite result will indicate ifa satisfactory score above 0.7. 3.6.3 Evaluation Model3.6.3.1. R-SquareR squared also name as coefficient of determination. The coefficient ofdetermination (R Square or R squared) or symbolized by "R2" which ismeaningful as a contribution of influence given independent variables orindependent variables (X) to the dependent variable or dependent variable (Y), orin other words, the value of the coefficient of determination or R Square is usefulfor predicting and seeing how much the contribution of the influence of variableX simultaneously (together) to the variable Y. Formula coefficient ofdetermination can be shown as follows:KP = r2 x 100%Information :KP: Coefficient determinant or the coefficient of determinationr2: Correlation Coefficient3.6.4. Hypothesis TestingHypothesis testing is a procedure based on sample evidence used todetermine whether the hypothesis is a reasonable statement and therefore not
Background image
Image of page 36

You've reached the end of your free preview.

Want to read all 42 pages?

  • Fall '19

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture

  • Left Quote Icon

    Student Picture