Activities : You will submit one Word document for this activity. You will create this Word document by
Activities :
You will submit one Word document for this activity. You will create this Word document by cutting and pasting SPSS output into word. Please answer the questions first and include all output at the end of the activity in an Appendix.
Part A.
SPSS
Activity
Using the data set: Chamorro-Premuzic.sav you will focus on the variables related to Extroversion and Agreeableness (student and lecturer).
Do the following:
- Exploratory Data Analysis.
- Perform Exploratory Data Analysis on all variables in the data set. Because you are going to focus on Extroversion and Agreeableness, be sure to include scatterplots for these combinations of variables (Student Agreeableness/Lecture Agreeableness; Student Extroversion/Lecture Extroversion; Student Agreeableness/Lecture Extroversion; Student Extroversion/Lecture Agreeableness) and include the regression line on the chart.
- Give a one to two paragraph write up of the data once you have done this.
- Create an APA style table that presents descriptive statistics for the sample.
2. Make a decision about the missing data. How are you going to handle it and why?
3. Correlation. Perform a correlational analysis on the following variables: Student Extroversion, Lecture Extroversion, Student Agreeableness, Lecture Agreeableness.
- Ensure you handle missing data as you decided above.
- State if you are using one or two-tailed test and why.
- Write up the results in APA style and interpret them.
4. Regression. Calculate a regression that examines whether or not you can predict if a student wants a lecturer to be extroverted using the student’s extroversion score.
- Ensure you handle missing data as you decided above.
- State if you are using one or two-tailed test and why.
- Include diagnostics
- Discuss assumptions; are they met?
- Write the results in APA style and interpret them.
- Do these results differ from the correlation results above?
5. Multiple Regression. Calculate a multiple regression that examines whether age, gender, and student’s extroversion predict if a student wants the lecturer to be extroverted.
- Ensure you handle missing data as you decided above.
- State if you are using one or two-tailed test and why.
- Include diagnostics
- Discuss assumptions; are they met?
- Write the results in APA style and interpret it.
- Do these results differ from the correlation results above?
Part B. Applying Analytical Strategies to an Area of Research Interest
- Briefly restate your research area of interest.
- Pearson Correlation. Identify two variables for which you could calculate a Pearson correlation coefficient. Describe the variables and their scale of measurement. Now, assume you conducted a Pearson correlation and came up with a significant positive or negative value. Create a mock r value (for example, .3 or -.2). Report your mock finding in APA style (note the text does not use APA style) and interpret the statistic in terms of effect size and R 2 while also taking into account the third variable problem and well as direction of causality.
- Spearman’s Correlation. Identify two variables for which you could calculate a Spearman’s correlation coefficient. Describe the variables and their scale of measurement. Now, assume you conducted a correlation and came up with a significant positive or negative value. Create a mock r value (for example, .3 or -.2). Report your mock finding in APA style (note the text does not use APA style) and interpret the statistic in terms of effect size and R 2 while also taking into account the third variable problem and well as direction of causality.
- Partial Correlation vs. Semi-Partial Correlation. Identify three variables for which you may be interested calculating either a partial or semi-partial correlation coefficient. Compare/contrast these two types of analyses using your variables and research example. Which would you use and why?
- Simple Regression. Identify two variables for which you could calculate a simple regression. Describe the variables and their scale of measurement. Which variable would you include as the predictor variable and which as the outcome variable? Why? What would R 2 tell you about the relationship between the two variables?
- Multiple Regression. Identify at least 3 variables for which you could calculate a multiple regression. Describe the variables and their scale of measurement. Which variables would you include as the predictor variables and which as the outcome variable? Why? Which regression method would you use and why? What would R 2 and adjusted R 2 tell you about the relationship between the variables?
- Logistic Regression . Identify at least 3 variables for which you could calculate a logistic regression. Describe the variables and their scale of measurement. Which variables would you include as the predictor variables and which as the outcome variable? Why? Which regression method would you use and why? What would the output tell you about the relationship between the variables?
Answer :
Research Hypothesis
My area of research is focused on computer networks and their use in electronic commerce.
The following variables could be interest:
- Type of platform (Unix, Windows) (Nominal)
- Type of webserver used (Apache, IIS) (Nominal)
- Type of CPU (Two-core, Quad-core) (Nominal)
- E-commerce platform (OSCommerce, ZenCart, Virtue Mart) (Nominal)
- Type of goods sold (Physical goods, digital goods) (Nominal)
- Volume of sales ( Ratio)
- Number of transactions during the year 2009 ( ratio)
- Type payment (Paypal, Credit card, bank transfer) (Nominal)
- Number of fraudulent transactions during the year 2009 ( ratio)
- Percentage of fraudulent transactions during the year 2009 ( ratio)
- Quality of Service (from 1 to 5, 1 = very bad, 5 = excellent) (ordinal)
- Will continue in business for 1 more year at least? (Yes or no) (Nominal)
(a) Pearson Correlation :
We use the variables Volume of Sales and Number of Transactions . These two variables are scale variables so it makes sense to perform a correlational analysis. Using a sample of 35 students, it was found that the correlation between these two variables is not significant, r(33) = 0.11, p = 0.5293. The amount of variation in Math GPA explained by IQ is 1.21%. No confounder seems to be acting in this case.
(b) Spearman Correlation :
We might be interested in analyzing the association between Volume of Sales and Quality of Service . Since one of the variables is ordinal, we need to use Spearman’s correlation. For a sample of 35 eight graders, it was found that the correlation between these two variables is significant, r S (33) = 0.945, p < 0.001.
(c) Partial Correlation vs. Semi-partial correlation
In this case we use
- Volume of Sales
- Number of Transactions
-
Percentage of Fraudulent Transaction
In this case we are interested in assessing whether the Percentage of Fraudulent Transactions can be significantly predicted from the Number of Transactions , after controlling for Volume of Sales .
(d) Simple Regression
We will use the variables Number of Transactions and Percentage of fraudulent transactions . In this case, we will use Number of Transactions as the predictor, and Percentage of fraudulent transactions is the response variable. The value of R 2 indicates the amount of variation in the Percentage of fraudulent transactions explained by Number of Transactions .
(e) Multiple Regression
The following variables will be considered: - Volume of Sales
- Number of Transactions
-
Percentage of Fraudulent Transactions
In this case, Percentage of Fraudulent Transaction s will be the response variable, and Volume of Sales and Number of Transactions will be the predictors. Using a Multiple Regression, we would use R 2 as a measure of effect size. But the best measure of effect size in this case would be Adj. R 2 , which indicates the amount of explained variation in Percentage of Fraudulent Transaction s by this model.
(f) Logistic Regression - Volume of Sales
- Number of Transactions
- Will continue in business for 1 more year at least?
In this case, Will continue in business for 1 more year at least would be the response variable, and Volume of Sales and Number of Transactions would be the predictors. In this case a logistic regression should be used, which would allow us to find the corresponding odd ratios.
Deliverable: Word Document
