Testing the variables
Thinking about possible relationships between the variables in the ICPSR data set you selected, select two qualitative and two quantitative variables. List your variables, giving the following information:
- Variable name
- Variable label
- The scale of measurement (Nominal, Ordinal, Interval, Ratio)
Generate at least 2 to no more than 4 research questions you could use these variables to test. You must use ALL of your selected variables and you can use any selected variable in more than one research question.
From these research questions, generate the null and research hypotheses you would use in a hypothesis test of each question.
List the research question, research hypothesis, and null hypothesis (in that order and labeled) for each research question.
Solution:
The lists below give the list of the variables of interest.
Variable 1
Variable name: HLTINDRG
Variable label: DRUG ABUSE
The scale of measurement: Nominal
Variable 2
Variable name: MARRIED
Variable label: MARRIED
The scale of measurement: Nominal
Variable 3
Variable name: NEWWT_A
Variable label: ADJUSTED ANALWT_C
The scale of measurement: Ratio
Variable 4
Variable name: NEWDEPWT
Variable label: ADJUSTED DEPWT_C
The scale of measurement: Ratio
Research Question
Research Question One:
- Is the respondent's drug abuse history dependent on their marital status?
Research hypothesis: There is a significant association between the respondent's drug abuse history and their marital status.
Null Hypothesis: There is no significant association between the respondent's drug abuse history and their marital status.
Research Question Two:
- Is there a significant relationship between the weight used in analyses that include depression (NEWDEPWT) and weight used in analyses that don’t include drugs or depression (NEWWT_A)?
Research Hypothesis: There is a significant linear relationship between the NEWDEPWT and NEWWT_A
Null Hypothesis: There is no significant linear relationship between the NEWDEPWT and NEWWT_A
Research Question Three:
- Does the weight used in analyses that include depression (NEWDEPWT) differ between the married respondent and not married respondent?
Research Hypothesis: There is a significant difference in the average weight used in analyses that include depression (NEWDEPWT) between the married respondent and not married respondent.
Null Hypothesis: There is no significant difference in the average weight used in analyses that include depression (NEWDEPWT) between the married respondent and the not married respondent.
Research Question Four:
- Does the weight used in analyses that don’t include drugs or depression (NEWWT_A) differ between the married respondent and not married respondent?
Research Hypothesis: There is a significant difference in the average weight used in analyses that don’t include drugs or depression (NEWWT_A) between the married respondent and the not married respondent.
Null Hypothesis: There is no significant difference in the average weight used in analyses that don’t include drugs or depression (NEWWT_A) between the married respondent and not married respondent.