Normality Test Classical Assumption Test

44 sales promotion and customer satisfaction with 30 samples of respondents.

2. Reliability Test

Reliability is a tool to measure a questionnaire which is an indicator of variables or constructs. A questionnaire said to be reliable or reliable if someone answers to questions are consistent or stable over time. SPSS provides the facility to measure the reliability of the statis tical test Cronbach Alpha α. a construct or variable said to be reliable if it provides value α 0,70 Ghozali, 2011:47-48. In other words able to obtain precise data on the variables studied. Testing of each item used item analysis, the reliability test is a measure of stability and reliability testing instruments used in this study using Cronbachs Alpha formula.

E. Classical Assumption Test

1. Normality Test

Normality test aims to test whether the regression model or residual confounding variables have a normal distribution. Studies that use a more reliable method to test the data have a normal distribution or not by looking at the Normal Probability Plot. A good regression model is to have a normal data distribution or dissemination of statistical data on a diagonal axis of the graph of a normal distribution Ghozali, 2011:160. 45 There are several ways to detect normality to see the spread of the data points on the diagonal axis of the graph. There are two ways to detect whether residual normal distribution or not is by analysis of graphs and statistical tests test Kolmogorov - Smirnov, with the following explanation Ghozali, 2011:147. a. Normality Test in Charts One of the easiest ways to see the residual normality is to look at the histogram graph that compares the distribution of observation data with which to detect the normal distribution. However, just by looking at the histogram this can be misleading, especially to the small sample size. More reliable method is to look at normal probability plots comparing the cumulative distribution of the normal distribution. The normal distribution will form a straight diagonal line and residual plotting the data will be compared with a diagonal line Ghozali, 2011:147. Basis for a decision in the normality test is: 1 If the data is spread around the diagonal line and follow the direction of the diagonal line, the regressions meet the assumption of normality. 2 If the data spread of the diagonal line and did not follow directions or diagonal line, the regression model did not meet the assumption of normality. 46 b. Normality Test in Statistics Normality test graphically can be misleading if not carefully look at it. Therefore it is recommended to complete normality test graphically statistical normality test Ghozali, 2011:163. In addition to seeing the normal curve P-plot, the normality test can also be performed using the Kolmogorov- Smirnov test. In Kolmogorov Smirnov test the hypotheses that apply are: H = Samples derived from data or population v normally distributed. Ha = Samples derived from data or populations that are not normally distributed. In this test if sig. 0,05 then the data is not distributed normally. However, if the value of sig. 0,05 then normally distributed data Santoso, 2011:193-196.

2. Multicollinearity Test