Need statistics questions answered and spss output file by 10am est

SPSS 3 – Cross-tabulations/Analyzing Data

Problem 1

Using the GSSFT (General Social Security Full Time) data set for this problem you will examine cross tabulated data and use a Chi-Square test to analyze the possible relationship between education levels (degree) and a person’s perception of life (life).

a)  Make a cross-tabulation to examine the relationship between highest degree earned (variable degree) and a person’s perception of life (variable life). How many people without a high school diploma find life exciting?  What is the percentage of this group in relationship to the total sample of 965 people who answered the question?

b)  Note that there are 1500 people in the total sample.  The case processing summary indicated that 35.7% of cases are missing.  How might this be considered as the analyst uses this information?

c)  Of the people who find life exciting, what percentabe do not have a high school diploma? 

d)  Examine the relationship, if any, between perception of life and highest degree earned.  What assumptions must be true about the data in order to use the Chi-Square test to determine if the relationship that might be present is statistically significant? Use the Chi-square analysis if the data fit these assumptions. Briefly summarize your findings. 

Problem 2

Using the Salary data set for this problem you will examine cross tabulated data and use a Chi-Square test to analyze the possible relationship between gender (variable: sex) and category of employment (variable: jobcat).

a)  Using the Salary data set create a cross tab in SPSS with gender and job category.

b)  How many males are employed as clerical workers? What percentage of males are clerical workers? Of clerical workers, what percentage are males?

c)  What patterns do you think you observe across the whole cross tab table regarding gender and job categories?  If there was a completely equal distribution of persons so that gender would not be a possible factor in the type of job one might have, what might you expect the values to be in the cells of this table? 

d)  What hypotheses should you test regarding the relationship between gender and job categories.

e)  What assumptions must be true about the data in order to use the Chi-Square test? Are the assumptions met by the data used to build the cross tab?

f)  Based on a 95% confidence interval can you reject the null hypothesis?

Problem 3

Using the Senate Vote on Corporate Average Fuel Economy (CAFE) Standard data data set for this problem you will run a Chi-Square hypothesis test to analyze the relationship between party affiliation (party) and a senator’s vote (vote) on the Levine Amendment in 2012. 

(a) Create a cross tab in SPSS with party (row variable) and vote. 

(b) Develop a null hypothesis to test the relationship between party and vote. 

(c) Based on a 95% confidence interval can you reject the null hypothesis? 

Problem 4
 The 04cars data set provides information on 428 new cars sold in 2004. Please answer the following questions.
a) You are to determine the association between the number of cylinders and horsepower. Which correlation measure should you use: Spearman’s or Kendall’s Tau? Why? What is the strength of this relationship?
b) Graph Highway Miles per Gallon against the weight of the cars. Is this relationship linear or non-linear. What is the correlation coefficient between these two variables.

After completing the problems:

1.  Copy the relevant SPSS output to a MS Word document. (You can simply copy and paste or you can export the file while in SPSS.)

2.  Add your analytic comments to each problem prior to the SPSS output which it supports.

3.  Clearly number and label each problem in the document.

4.  Submit your assignment by uploading it to this site.

Grading method: SPSS Assignment rubric, SPSS Assignments gradebook category