THE MEANING OF STATISTICAL TERMS

As you are working with SPSS, you will notice that there is a large number of statistical techniques that can be used to analyze data. I went through your textbook and found definitions of some important statistical analysis concepts.

1. Statistical Significance: "The basic motive for making statistical inferences is to be able to generalize from sample results to population characteristics…. If a particular difference is large enough to be unlikely to have occurred because of chance or sampling error the difference is statistically significant" (p. 513). Statistically significant differences are not necessarily meaningful in terms of marketing planning.

2. Type I error "rejecting the null hypothesis when it is, in fact, true" (p. 518). The null hypothesis states that there is no relationship between the variables we are examining or that there is no difference in the group means. In our case, we are willing to take a 5% chance that we are rejecting the null hypothesis even though it is true.

3. Independent samples do not necessarily involve different surveys. Rather, these are "samples in which measurement of a variable in one population has no effect on the measurement of the variable in the other" (p. 523).

4. Chi Square can be applied to a single sample whenever we want to find if responses to one question are different than what we would have expected. Chi Square can also be applied to two samples (or two independent groups) whenever we want to find if these groups differ with regard to a variable. For example, are men or women more satisfied with Outlook? Chi Square can be applied to nominal as well as ordinal data.

5. Komolgorov – Smirnov Test: It is similar to the Chi Square test, but can utilize the distinct characteristics of ordinal data. It is not used as frequently as the Chi Square because most researchers do not want to deal differently with cross-tabulations of nominal and ordinal data.

6. Z-tests examines if a sample mean is different from another mean. It assumes that the sample size is greater than 30.

7. T-test is similar to the Z-test, but it is used when we have a small sample size. T-tests can also be used to compare two means to find if differences between groups (such as men and women) are significantly different. When a sample is large enough, the value of T-test become identical to the Z-test. Often researchers use a T-test to compare means, even if their sample size is large. SPSS only lists T-tests as options.

8. Analysis of variance (ANOVA) allows us to examine differences between the samples of two or more independent samples. In our World95 database, the different religious groups were viewed as independent samples.

9. Bivariate regression analysis allows us to examine the relationship between two variables which have been measured at the interval or ratio level. The Coefficient of Determination, R², examines the percent of variation in the dependent variable that is explained by the independent variable.