A Concise Guide to Market Research by Marko Sarstedt & Erik Mooi

Author:Marko Sarstedt & Erik Mooi
Language: eng
Format: epub
ISBN: 9783662567074
Publisher: Springer Berlin Heidelberg

6.6.1.2 Choose the Significant Level

Next, we decide to use a significance level (α) of 0.05, which means that we allow a maximum chance of 5 % of mistakenly rejecting a true null hypothesis.

6.6.1.3 Select the Appropriate Test

We move to the next step to determine the type of test, which involves assessing the testing situation, the nature of the measurements, checking the assumptions, and selecting the region of rejection. We start by defining the testing situation of our analysis, which is to compare the mean overall price/performance satisfaction scores (measured on a ratio scale) of male and female travelers. In our example, we know that the sample is a random subset of the population and we also know that they are independent. Next, we need to check if the dependent variable overall_sat is normally distributed. To do this go to ► Analyze ► Descriptive Statistics ► Explore. Then put the test variable overall_sat into the Dependent list box. Under Factor List: enter the gender variable as you want to assess normality within each of the two groups. For the ANOVA example that follows, we also need the status variable so please add this as well as it avoids having to redo the analysis later. All of this is shown in Fig. 6.7. Next, click on Plots, which will open a dialog box similar to Fig. 6.8, uncheck Stem-and-leaf, check Normality plots with tests and click on Continue and then OK.

Fig. 6.7Testing for normality

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.