Reference no: EM132271192
Assignment -
To complete this assignment must use SPSS software. Interpret your results when directed, and round all calculations to a minimum of four decimal places. Must show the calculations.
1. Explain, using your own terms, what an independent and dependent variable is.
2. Provide a specific and complete answer to the following questions:
a. Why is it impossible for a categorical variable to be truly normally distributed? (Answer within the context of mean and standard deviation)
b. What do we need to do in order to determine whether a categorical variable can be treated as a normally distributed variable?
c. How do we determine whether a continuous variable is normally distributed?
d. When determining whether we need to perform a parametric or nonparametric method, do we identify the normality of the independent variable or dependent variable?
3. Given the following data and using Excel (do not submit work using paper-and-pencil): Present the Excel sheet separate
X = # of incidents of unwanted contact in past week (females)
|
6
|
12
|
13
|
11
|
7
|
9
|
11
|
8
|
10
|
9
|
a. What proportion of females within the population would we anticipate to report seven (7) or more incidents of unwanted contact in the past week?
b. What percentage of females in the population would we anticipate to report between ten (10) and fourteen (14) incidents of unwanted contact?
i. Interpret the previous answer in a manner that is accessible to the general population.
4. When is it appropriate to perform a single sample analysis?
5. Given the following data regarding whether the respondent experienced domestic sexual violence (DSV) and whether the respondent has been homeless within the past three years:
|
Homeless +
|
Homeless -
|
Domestic sexual violence +
|
489
|
572
|
Domestic sexual violence -
|
191
|
4136
|
a. What is the probability of identifying an individual who has experienced DSV (DSV+) or has been homeless in the past three years?
b. What is the probability of randomly selecting someone who has been homeless?
c. What is the probability of selecting someone who has been homeless given that they experienced DSV?
i. Interpret the result in sentence form.
d. What is the probability of randomly identifying an individual from our sample who has not experienced DSV and has been homeless?
e. Given our data, what proportion of our sample has not experienced DSV given that they have not been homeless?
6. When is it appropriate to perform a non-parametric analysis? Using SPSS, how do you determine whether it is appropriate to perform a parametric or non-parametric test? Explain for a continuous and categorical dependent variable.
SPSS Portion -
Be sure to perform the appropriate analysis and to copy the relevant table(s) from SPSS to the word document directly below the corresponding question. Failure to include the table will result in zero points for that question. Briefly explain why you chose the method of analysis that you did. Indicate which value you are interpreting within the relevant table(s), and provide a complete interpretation of the results, answering all parts of the question.
1. Create a frequency table for General Health Condition (NHANES dataset).
a. What proportion indicated that their health was better than fair?
b. What percentage reported their health as excellent?
2. Using the following document (MONITORING THE FUTURE NATIONAL SURVEY RESULTS ON DRUG USE, 1975-2016), identify the proportion of college age individuals in the United States in 2016 who used any illicit substances (hint: I would consider this statistic to be a 'key finding' of a survey focused on drug use in college students and adults). Using this information, and the 'Class Data' dataset, determine whether drug use among undergraduate biostatistics students at WKU ('Q11') is different from college students in the United States.
3. A score of 16 or higher on the CES-D scale suggests a high level of depressive symptoms. Using the 'Homeless Persons' dataset, determine whether the CES-D score among the homeless differs from the cut-off for high level depressive symptoms.
4. Using the NHANES dataset, calculate the mean, mode, standard deviation, and the minimum and maximum values for Total Cholesterol (mg/dl).
5. Using the NHANES dataset, create a graph that conveys the frequency of responses regarding how the respondent perceives their weight (WHQ030E).
Attachment:- Assignment Files.rar