Basic Statistics- Part III
Correlations
Definition:
- Measures the strength of the relationship between two variables
- Correlation coefficient (r) are values that can range from –1 to +1, and reflects the absolute value of the strength of the relationship
- If the absolute value is close to 1, the relationship is considered to be strong; if it is close to 0, it is considered weak
Steps in SPSS
- 1.Click on the statistics option on the top row. Then move your cursor to Correlate, and then click on Bivariate.
- 2.This brings you to the Bivariate Correlations window. Move the relevant variables over to the variable pane.
- 3.Click on Options on the bottom right hand corner of the window. This will bring you to the Bivariate Correlations: Options Window.
- 4.Click on means and standard deviations to provide these statistics, and then click on Continue. This brings you back to the Bivariate Correlations Window.
- 5.Click on OK to run Correlations.
Output
- There will be two tables of output.
- In the first table, you will find the descriptive statistics for the variables (i.e., mean, standard deviation, and sample size)
- The second table will be the correlational matrix.
- This table is symmetric, in that the values above the diagonal are the same as the values below the diagonal
- The first section of the table presents the correlation coefficients (r). The asterisk (*) following this correlation indicates that the correlation is significant at the .05 level (** indicates a significant correlation at the .01 level).
- The second section of the table presents the actual probabilities associated with each correlation
- The third section of the table shows the sample size on which each correlation is based.
Example
- The following output is for a study that examined the relationship between cognitive specific imagery and the amount of physical and technical preparation used in the off-season.
PHYSICAL / TECHNICAL
CS
Pearson Correlation
Sig. (2-tailed)
N / .426**
.00
329 / .463**
.00
327
- In the paper, these results would be report as followed.
“ Bivariate correlations were calculated to examine whether imagery use was related to the amount of physical and technical preparation that athletes engage in during the off-season. These correlations are presented in Table 1, and indicate that a positive, significant relationship existed between cognitive specific imagery and physical preparation (r = .43, p = .00) and between cognitive specific imagery and technical preparation (r = .46, p = .00).”