SPSS Assignment Part A Question 1 : (Total of 1 2 Marks) Using the SPSS sample data set (" sampledata
SPSS Assignment
Part A
Question 1 : (Total of 1 2 Marks)
Using the SPSS sample data set (" sampledata 1 .sav ") provided for the assignment, answer the following questions. This data come from a study looking at factors related to workplace empowerment and job satisfaction and job commitment. The empowerment scale is comprised of four sub-components – resources, support, information and opportunity. For all scales, including job satisfaction and job commitment, you can assume that higher scores indicate more of the variable in question (i.e. higher scores for job satisfaction indicates that the nurse is more satisfied with their job than someone with a lower job satisfaction score).
NOTE : Use the content taught in this course; and a s with all parts of this assignment, be sure to clearly state what you did and why before telling us what you found and what it means . It should be clear to anyone reading your answer exactly who was in this sample and what their main characteristics were. Any important information/output etc. missing from your description or incorrect conclusions would result in lost marks .
1a) Test the hypothesis that total Resources scores vary by nurse education level. Be sure to provide all relevant background descriptive analyses, including output that explains the total Resources scores by nurse education level , and discuss any limitations of your analysis . ( 8 marks) . U sing alpha of 0.05, write a concluding statement about the results of this analysis. ( 2 marks)
1b) If one were to increase the sample size of the data file so that it included approximately 500 nurses instead of the approximately 400 included in the file you were given; how do you think this might have impacted the results of the analysis from Part 1a? If there is a difference between your answers to (a) and (b) , c omment on why that might be the case. ( 2 marks)
Question 2 : (Total of 1 2 Marks)
Using the SPSS data file provided for the assignment (in question #1), answer the following questions:
2a) Determine if the years of experience in nursing and affective job commitment variables are correlated with one another. Be sure to comment on all relevant aspects of the relationship seen (if any). From your analysis, determine whether a different test should be used instead, if so, perform the test and comment on the analysis and show your work . ( 7 marks total )
2b) For the years of experience in nursing and affective job commitment variables only, conduct a simple linear regression analysis using the years of experience variable as the predictor and job commitment as the outcome variable. Compare your results with the correlation results found for these variables in part ( a). Based on your results from the regression analysis, what would the predicted job commitment score be for a nurse with 10 years of experience? Show all of your work for this calculation. (5 marks total)
Part B
Question 1 : (Total = 10 marks)
1a ) Using the SPSS data file (" sampledata 2 .sav ") first describe the general characteristics of the study sample you have been provided with. Include a table of your main sample characteristics in a format such as those found in a published research article, study report or student thesis. Prior to creating this table (which should be summarized from your SPSS output – i.e. not raw SPSS output) you should comment on the quality of the demographic data that have been provided – i.e. any concerns with it, anything you would like to modify (but not make these changes), etc. ( 10 marks to tal )
NOTE : Use the content taught in this course; and a s with all parts of this assignment, be sure to clearly state what you did and why before telling us what you found and what it means. It should be clear to anyone reading your answer exactly who was in this sample and what their main characteristics were. Any important information/ output etc. missing from your description or incorrect conclusions would result in lost marks .
Question 2: (Total = 1 8 marks)
Use the above SPSS file to answer the following questions:
2a) For the " place of birth " variable (i.e. "Born in Canada" and "Born outside of Canada"), state a hypothesis regarding an association between this variable and the hours of DDC (double duty care ) provided and then test your hypothesis with the data provided. Be sure to justify your choice of test and explain what your results mean? ( 5 marks total )
2 b ) Test the hypothesis that there is an association between the health status variable and marital status using the original versions of the two variables. Include a table for these two variables as part of your results for this question ( include only relevant information in the table) . (5 marks total )
2c) Recode the health status variable used in ( # 2b) so that you combine the fair/poor/good categories and leave the other two levels as they were. Recode the marital status variable so that it is a new binary variable, married or other, with those preferring not to answer also set as missing. Once you recode these variables, re-test your hypothesis from ( # 2b) about the association between health and marital status using the new variables created here. Contrast your results from these two analyses (i n # 2b and 2c), taking note of any differences you might see and stating which analysis you think is a better test of the hypothesis linking health status and marital status and why. ( 6 marks total)
2d) Please differentiate between logistic regression analysis and linear regression analysis? ( 2 marks total)
APPENDIX
SPSS Syntax
PART A
1a) ONEWAY res BY edcat
/STATISTICS DESCRIPTIVES HOMOGENEITY
/PLOT MEANS
/MISSING ANALYSIS
/POSTHOC=TUKEY ALPHA(0.05).
2a) EXAMINE VARIABLES=yrsnsg committ
/PLOT NPPLOT
/STATISTICS DESCRIPTIVES
/CINTERVAL 95
/MISSING LISTWISE
/NOTOTAL.
CORRELATIONS
/VARIABLES=yrsnsg committ
/PRINT=TWOTAIL NOSIG
/MISSING=PAIRWISE.
2b) REGRESSION
/MISSING LISTWISE
/STATISTICS COEFF OUTS R ANOVA
/CRITERIA=PIN(.05) POUT(.10)
/NOORIGIN
/DEPENDENT committ
/METHOD=ENTER yrsnsg.
PART B
1a) FREQUENCIES VARIABLES=Province female Marital CDN_born healthy income LowestD1 HighestD4 MiddleD2 HighD3 fulltime MeduimD1 HighD2
/ORDER=ANALYSIS.
EXAMINE VARIABLES=age ddchours
/PLOT BOXPLOT STEMLEAF
/COMPARE GROUPS
/STATISTICS DESCRIPTIVES
/CINTERVAL 95
/MISSING LISTWISE
/NOTOTAL.
2a) T-TEST GROUPS=CDN_born(1 2)
/MISSING=ANALYSIS
/VARIABLES=ddchours
/CRITERIA=CI(.95).
2b) CROSSTABS
/TABLES=healthy BY Marital
/FORMAT=AVALUE TABLES
/STATISTICS=CHISQ
/CELLS=COUNT
/COUNT ROUND CELL.
2c) RECODE healthy (MISSING=SYSMIS) (4=2) (5=3) (1 thru 3=1) INTO healthy_rec.
EXECUTE.
RECODE Marital (MISSING=SYSMIS) (1=1) (ELSE=0) INTO Marital_rec.
EXECUTE.
CROSSTABS
/TABLES=healthy_rec BY Marital_rec
/FORMAT=AVALUE TABLES
/STATISTICS=CHISQ
/CELLS=COUNT
/COUNT ROUND CELL.
Deliverable: Word Document
