Before completing the Tasks, please work through each of the sub-pages for Tutorial 3 as these will help complete the task below.

For the task below we will be using the following dataset:

Skoczylis, Joshua, 2021, "Extremism, Life Experiences and the Internet", https://doi.org/10.7910/DVN/ICTI8T, Harvard Dataverse, Version 3.

You will also use the Twitter dataset you have created.

Come up with a number of Hypotheses and alternative Hypotheses that looks at the following variables:

Age, Political Engagement, Confidence_inSelf, and Household_Income.

Now use a correlations matrix to test your hypotheses:

• Select the correct Correlation Coefficient.

• Interpret the results (which correlations are/are not significant)? 

We know that 50.59% of the UK population are females. Using the appropriate One Sample proportion test check the following hypothesis:

H0: There is no difference between the proportion of females in the sample and the UK population. 

Ha: There is a significant difference between the proportion of females in the sample and the UK population. 

Do we accept/reject the Null hypothesis? Why? 

Come up with some relevant hypotheses using the following three variables: Gender, Highest Qualification, and Violence_effective_respect.

Test your hypotheses using a Contingency Table. 

• Make sure you select the correct Measures of Association

• Where are the significant relationships?

• Try to interpret the table using column/row percentages

Convert Social Media Use into a Nominal variable with the following three categories: 

• Low Social Media Use

• Average Social Media Use

• High Social Media Use

Use the transform function to create this new variable (Hint: use the percentiles to divide the Social Media variable into the three categories - get the Quartiles using descriptive statistics)

Now come up with a hypothesis that uses this new variable, gender, and Violence_Effective_respect. Test your hypothesis using a Contingency Table

• Make sure to select the correct Measures of Associations

• Try to interpret the table using column/row percentages