Week Six - Correlations Exercises

Week Six - Correlations Exercises

Correlations are used to describe the strength and direction of a relationship between two variables. A correlation between two variables is known as a bivariate correlation. In this module the Pearson Product-Moment Correlation will be used when running a correlation matrix. The Pearson correlation coefficient ranges from a value of -1.0 to 1.0. A correlation coefficient is never above 1.0 or below -1.0. A perfect positive correlation is 1.0 and a perfect negative correlation is -1.0. The size of the coefficient determines the strength of the relationship and the sign (i.e., + or -) determines the direction of the relationship. The closer the value is to zero the weaker the relationship and the closer the value is to 1.0 or -1.0 the stronger the relationship. A correlation coefficient of zero indicates no relationship between the variables.

A scatterplot is used to depict the relationship between two variables. The general shape of the collection of points indicates whether the correlation is positive or negative. A positive relationship will have the data points group into a cluster from the lower left hand corner to the upper right hand corner of the graph. A negative relationship will be depicted by points clustering in the lower right hand corner to the upper left hand corner of the graph. When the two variables are not related the points on the scatterplot will be scattered in a random fashion. 

Using Polit2SetB dataset, create a correlation matrix using the following variables: Number of visits to the doctor in the past 12 months (docvisit), body mass index (BMI), Physical Health component subscale (sf12phys) and Mental Health component subscale (sf12ment). Run means and descriptives for each variable as well as the correlation matrix. 

Submit the answers only. You do not need to write a paper, use a reference(s), or APA format. Make sure to save your name with your paper as instructed in the submission section.  

Follow these steps using SPSS:

1. Click Analyze, then correlate, then      bivariate. 


2. Select each variable and move them      into the box labeled “Variables.” 


3. Be sure the Pearson and two-tailed      box is checked.


4. Click on the options tab (upper      right corner) and check “means and standard deviations.” The exclude cases      pairwise should also be checked. Click continue.


5. Click OK


6. Check your answers with the SPSS      output provided.

To run descriptives for docvisit, bmi, sf12phys and sf12ment do the following in SPSS: 

1. Click Analyze then      click Descriptives Statistics, then Descriptives.


2. Click the first      continuous variable you wish to obtain descriptives for (docvisit) and      then click on the arrow button and move it into the Variables box. Then      click bmi and then click on the arrow button and move it into the      Variables box. Then click sf12phys and then click on the arrow button and      move it into the Variables box. Then click sf12ment and then click on the      arrow button and move it into the Variables box.


3. Click the Options      button in the upper right corner. Click mean and standard deviation.


4. Click continue and      then click OK. 


5. Check your answers with the SPSS      output provided.

Assignment: Answer the following questions about the correlation matrix.

1. What is the strongest correlation      in the matrix? (Provide correlation value and names of variables)


2. What is the weakest correlation in      the matrix? (Provide correlation value and names of variables)


3. How many original correlations are      present on the matrix?


4. What does the entry of 1.00      indicate on the diagonal of the matrix?


5. Indicate the strength and direction      of the relationship between body mass index and physical health component      subscale? 


6. Which variable is most strongly      correlated with body mass index? What is the correlational coefficient?      What is the sample size for this relationship? 


7. What is the mean and standard deviation      for BMI and doctor visits?

Part II

Using Polit2SetB dataset, create a scatterplot using the following variables: x-axis = body mass index (BMI) and the y-axis = weight-pounds (weight).

Follow these steps in SPSS:

1. Click Graphs, then click on Legacy      Dialogs, then click “Scatter/Dot”. 


2. Click “Simple Scatter” and then      click “Define.” 


3. Click on weight-pounds and move it      to the Y-axis box and then click on body mass index and move it to the      x-axis box. 


4. Click OK.


5. Check your answers to the SPSS      output provided.


6. So not submit the scatterplots as      answers to the questions. 

To run descriptives for BMI and weight do the following in SPSS: 

1. Click Analyze then      click Descriptives Statistics, then Descriptives.


2. Click the first continuous      variable you wish to obtain descriptives for (body mass index) and then      click on the arrow button and move it into the Variables box. Then click      weight-pounds and then click on the arrow button and move it into the      Variables box.


3. Click the Options button      in the upper right corner. Click mean and standard deviation.


4. Click continue and      then click OK. 


5. Check your answers to the SPSS output      provided.

Assignment:

1. What is the mean and      standard deviation for weight and bmi?


2. Describe the      strength and direction of the relationship between weight and bmi?


3. Describe the      scatterplot? What information does      it provide to a researcher?