The data file consists of 43 variables and 1500 cases available for analysis. Expand the Label column to read the entire question for a variable or use the tab “Utilities” to see how the variable is categorized and coded. Note which variables are nominal, ordinal, or scale (interval-ratio) in the Measure column, modify to set the appropriate level of measurement if necessary. 1.Four Frequency distributions and four Graphs (8 marks, 1 marks each) Choose four variables (one – nominal, two ordinal, and one scale (interval/ratio) from the data file. Click on Analyze and select Descriptive Statistics and within it Frequencies. In the box that opens, select four variables of your choice in the left open window with a list of variables. Highlight them (one at a time) and click on the arrow button between the right and left open windows to pull it into the right window. When you are done click the OK button. You should have produced the frequency distribution tables for the four variables of your choice. For each of the four chosen variables create the most appropriate chart from the options provided (“Chart Builder or Legacy dialogue”). Label the charts correctly, including the appropriate title and number. Provide a brief discussion of the results for each variable of your choice from the frequency distribution and the chart. 2.Two Cross-tabulations (12 marks, 6 marks each) State and explain two hypothesis involving an independent and dependent variable of your choice from the provided data set. Identify the independent and dependent variables in your hypothesis. Run crosstabs with column percentages to test each of your two hypothesis. Remember to define the appropriate values as “missing” for both variables if necessary. Analyze and discuss the results of the cross-tabulation analysis. In particular, consider whether the results are consistent with your hypothesis and whether there appears to be an association between the variables. Based on your analysis, discuss if this association is worth investigating further. Why or why not? Support your answer with your results (relevant percentages). Part II Cross-tabulations, Chi-Square and statistical significance (30 marks – 10 marks for each hypothesis and its analysis) Create three bivariate hypotheses that you can test with the data set. For each hypothesis choose two appropriate for the test variables that you think may be related. List the variables and explain briefly how you think they may be related. Test your hypothesis by exploring the relationship between the variables using cross-tabulations and chi-square test. Discuss your findings, focusing in particular on whether the relationship between the variables you chose is statistically significant. Using the information from your data analysis explain why the relationship between the variables in your hypothesis can or cannot be generalized to the US population. The cross-tabulations will include the Pearson Chi-Square value and its df (degrees of freedom). These are always reported for Chi-Square tests. In the same row is something called Asymp. Sig. (2-sided). This is the probability for a test of statistical significance. Information from it is always reported, but usually as a level of statistical significance. Save the output for each hypothesis being analysed. A simple rule to use when reporting levels of significance. .001 level if significance probability is .000-.001 .01 level if significance probability is .002-.010 .05 level if significance probability is .011-.-050 Not significant if significance probability is .051 or larger. View Less >>
Part 1 1. Four Frequency distributions and four Graphs The four variables selected for this analysis are: ABORTION IF WOMAN WANTS FOR ANY REASON– Nominal HOW OFTEN R ATTENDS RELIGIOUS SERVICES– Ordinal SUBJECTIVE CLASS IDENTIFICATION– Ordinal AGE OF RESPONDENT– Scale Get solution

Place a new order
Pages (550 words)
Approximate price: -