Week 6: Tests of Significance

In Week 3, we used crosstabs to determine if a potential relationship between two variables is worth examining further. During Week 4, we studied tests of significance. In this week's discussion, students will apply these tests of significance to their project variables. As we discussed previously, the level of measurement of our variables determine which test of significance works for the research project.

Complete the following steps:

1. Post a brief explanation of your topic. Include your research question. Next, begin your 5 steps of hypothesis testing by stating your research and null hypotheses. State your alpha level is .05.

2. Run a test of significance on your variables (based on the level of measurement).  Copy and paste the appropriate table into the window.

3. Identify the two-tailed p value and explain your findings. Is p<alpha? Do you reject or fail to reject the null hypothesis? Does your IV affect your DV?

As a reminder, here is the guideline for tests of significance: 

1. IV and DV are BOTH categorical variables (nominal/ordinal): Chi-square

2. IV and DV are both interval/ratio variables: Regression

3. IV is categorical (nominal/ordinal) and DV is interval/ratio:

           a. IV has 2 values/groups: Independent Sample T-test

           b. IV has 3 or more values/groups: ANOVA

Why do we need to run tests of significance?

1. They allow us to see if our relationship is "statistically significant." To be more specific, these tests tell us if a relationship observed in a sample, like our research project based on GSS 2018 data set, is generalizable to the population from which this sample was drawn (US adults).

2. Test results reported under "p" in the SPSS output tell us the probability or likelihood that a relationship observed in the sample is not real, but rather due to factors like a sampling error or chance. We compare this "chance" with alpha (level of significance), commonly set as .05 or .01. If this chance is smaller than level of significance (p<alpha), we can reject the null hypothesis, and keep the research hypothesis. The smaller the p, the lower the possibility for error.