Substance Abuse Survey

Topic

Substance Abuse Survey

Instructions

Part A:  SPSS Data Entry and Levels of Measurement (1 page Table)

Statistics Canada has hired you as their principal investigator to establish “primary” data on various social issues.  The topics of interest are:

  1. Pick a topic area that interests you:
    1. Dysfunctional Families
    2. Substance Use/Abuse
    3. Media
    4. Crime, Justice and Forensic Psychology
  1. Create a codebook of 4 variables related to your topic in a word processing program (this is best done in WORD Table). Make sure your table is appropriately labeled and has a proper title.  Your codebook table should have the following elements, as well as a Title (i.e., Table 1: Codebook of….):
  • The question created
  • Response attributes with coding starting from [0]
  • Variable Classification and level of measurement
    • You should have one variable for each level of measurement
      • Nominal
      • Ordinal
      • Interval
      • Ratio
  1. Take the information from your codebook and create a data matrix in SPSS. Your data matrix must meet the following requirements:
  • Have a sample size of 10.
  • Have 4 variables (listed above), as well as respondent i.d.
  • Have corresponding values entered in the data matrix (you make these #’s up).
  • Have value labels
  • Have levels of measurement for ALL variables.

PAGE #: This assignment is one page only of tabled codebook.

Part B: SPSS Instructions for Univariate and Bivariate Analyses

Complete this assignment using the GSS93 secondary data set using the variables below.

Respondent’s sex

Number of Brothers and Sisters

Gun Law Favorability

Marital Status

  1. Use your discretion and run the most appropriate Univariate Statistics on all of the above variables.  Accompany your analysis with appropriate visual representations of the data.  Group similar levels of measurement together and then run the stats.
  2. Conceptually and logically recode marital status so it will only have 2 response categories. Remember to properly define and label your new recode and provide new univariate statistics for these variables!
  3. Run a 2 x 2 zero-order crosstabulation to test the relationship between respondent’s sex and gun law favorability.  Then control for Marital Status of the respondents.

For the interpretation be sure to discuss: Is the null hypothesis rejected? Discuss the results and all relevant statistics.

Part B: Interpretation

  1. Interpret your findings using Headings and Subheadings and write up your analysis. Provide both technical and substantive interpretations.

For Univariate Analysis (2 pages):

  • The research purpose?
  • Univariate Statistics for ALL 4 variables:
    • Describe the nature of your results for each variable distribution by discussing the type of variable and level of measurement.
    • For the recoded variable, you need to interpret the results of the original frequency distribution, but you still need to hand in the frequency distribution for the recode.
    • Be sure to discuss measures of central tendencies and dispersion.
    • Also, discuss skewness/kurtosis where applicable.
    • Interpret technically and substantively.

For Bivariate Analysis (3 pages):

  • The research purpose/question?
  • You should have a null and alternate hypothesis stated at the very beginning plus an arrow diagram.
  • Logical discussion of controls and the logic of recoding.
  • Cross-tab results with discussion of Conditional distributions, column percentages, Chi square (statistical dependence or not?), and Measures of Association (strength of relationship).
  • Upon elaboration, has the original relationship modified. What are the observed patterns?    Discuss all relevant statistics from the elaboration.

Conclusion

  • CONCLUSIONS (i.e., make concluding statements about univariate and bivariate analyses)
  • What do these results suggest about the sample? Don’t include #’s-substantively explain your conclusion).  So, if you were to provide a summary of your analysis what exactly would you say?
  • Were these results expected?
  • Why do you think your results are the way they are? Sociologically explain [briefly].
  • Do the results support/refute your research hypotheses? Why?
  1. APPENDIX A (i.e., your original SPSS outputs attached to the write-up; make sure all your SPSS tables have titles).  For this assignment, no redone tables are required.  Refer reader to original SPSS outputs.

Presentation of Work Does Matter: 

Use subheadings to let the reader understand your analysis.  It is important to be organized in your statistical write-ups.  In this assignment you should have the following main headings:  Introduction (should discuss overall assignment, research question(s)/hypotheses, and arrow diagram), Data Modifications (any discussion of recoding of variables needs to go here), Univariate Analysis & Bivariate Analysis, Conclusions.  Use each variable name as a subheading and then write your descriptions underneath. 

Answer preview

ANOVA has been used as the primary univariate Analysis of Variance statistic method on our data. The research sample constituted 983 participants, comprising of 559 female and 509 men (Table 1). Out of these, the majority were married (509), followed by 198 who were not married. Only 146 were divorced, 105 widowed and 25 participants separated. The married had a mean of 1.20, widowed 1.12, divorced 1.18, separated 1.28, never married 1.13. the entire sample had a mean of 1.18 (Table 2).

Word count: 815