Pearson Product Moment Correlation ( Pearson r)

Pearson’s r measures the strength, direction and probability of the linear association between two
interval or ratio variables.

Pearson’s r, semipartial and partial correlation can be employed in order to estimate the relationship
between an outcome and predictor variable after controlling for the effects of additional predictors in
the equation.

Pearson’s r is that it is a simple way to assess the association between two variables; whether they share
variance (covary), if the relationship is positive or negative, and the degree to which they correlation.

A Pearson correlation is appropriate only when a linear relationship exists between the two variables.

Che, J. (2015). Pearson's Product-Moment Correlation: Sample Analysis. DOI:

10.13140/RG.2.1.1856.2726.

Pearson’s r is a measure of the linear relationship between two interval or ratio variables, and can have
a value between -1 and 1. It is the same measure as the point-biserial correlation; a measure of the
relationship between a dichotomous (yes or no, male or female) and an interval/ratio variable (Cramer,
1998)

“Pearson’s correlation is the ratio of the variance shared by two variables” (Cramer, 1998, p. 137).

Cramer, D. (1998). Fundamental Statistics for Social Research. London: Routledge

The Pearson product-moment correlation coefficient is employed extensively in social science research
(Smithson, 2000) as a correlational technique between two variables (X and Y) and also in concurrence
with numerous univariate and multivariate methods “…to analyze the underlying relationship between
the variables of interest prior to or following the main analysis” (Padilla & Veprinsky, 2014, p. 824).

Smithson, M. J. (2000). Statistics with confidence: An introduction for psychologists. Thousand Oaks, CA:
Sage Publications

Padilla, M. A., & Veprinsky, A. (2014). Bootstrapped deattenuated correlation: Nonormal distributions.
Educational and PsychologicalMeasurement, 74(5), 823-830. doi: 10.1177/0013164414531780

Pearson's r is called the “product-moment correlation” because it is calculated by multiplying

the z scores of two variables (i.e., the product of two variables) and then calculating the average (i.e.,
the moment) of these products based on a group of n cases.

Chen, P. & Popovich, P. (2002). The Pearson Product-Moment Correlation. Doi

https://dx.doi.org/10.4135/9781412983808

Pearson’s r requires that interval data be used to determine a linear relationship. Further assumptions
must be met in order to establish statistical significance, “…for the test statistic to be valid the sample
distribution has to be normally distributed” (Filed, 2009, p. 177).

Field, A. (2009) Discovering Statistics Using SPSS. 3rd Edition, Sage Publications Ltd., London.
The Pearson product-moment correlation coefficient, better known as the correlation coefficient, or as r,
is the most widely used correlation coefficient.

Pearson’s r summarizes the relationship between two variables that have a straight line or linear
relationship with each other

If the two variables have a straight line relationship in the positive direction, then r will be positive and
considerably above 0. If the linear relationship is in the negative direction, so that increases in one
variable, are associated with decreases in the other, then r < 0. The possible values of r range from -1 to
+1, with values close to 0 signifying little relationship between the two variables.

(sir, wala ni siyay author huhuhu)

Medgraph using Sobel z-test

The Sobel test is used to determine whether a variable carries (or mediates) the effect of an
independent variable to the dependent variable—the outcome of interest. A significant test statistic
offers evidence that an independent variable has an indirect effect (i.e., an effect that is mediated in
whole or in part through another variable) on the dependent variable. This is done by testing the
hypothesis that there is no statistical difference between the total effect (i.e., the effect of a specified
independent variable on the dependent variable) and the direct effect (i.e., the effect of that same
independent variable on the dependent variable) after taking into account the influence of a potential
mediator.

Allen, M. (2017).  The SAGE Encyclopedia of Communication Research Methods.

doi: https://dx.doi.org/10.4135/9781483381411.n570

The development of Sobel's standard error allowed for testing the significance of this effect using
commonly accepted statistical approaches(LeBreton, Wu, & Bing, 2009)

LeBreton, J. M., Wu, J., & Bing, M. N. (2009). The truth(s) on testing for mediation in the social and
organizational sciences. In C. E. Lance & R. J. Vandenberg (Eds.), Statistical and methodological myths
and urban legends: Doctrine, verity and fable in the organizational and social sciences (pp. 107-141).
New York: Routledge/Psychology Press.

The Sobel test involves the multiplication of a and b coefficient estimates and determining the ratio of
the resulting value to standard error. Numerous formulas have been proposed to estimate this standard
error; however, the differences between them do not often have a significant effect on the test results
(MacKinnon et al., 2002; Preacher & Hayes, 2004, 2008).

MacKinnon, D. P., Lockwood, C. M., Hoffman, J. M., West, S. G., & Sheets, V. (2002). A comparison of
methods to test mediation and other intervening variable effects. Psychological Methods, 7, 83-104.
Preacher, K. J., & Hayes, A. F. (2008). Asymptotic and resampling strategies for assessing and comparing
indirect effects in multiple mediator models. Behavior Research Methods, 40, 879-891.

Sobel test examines whether the entire pathway from X to Y via M is reliable, as a package.

Datsgeer, G., Rehman, A. & Sadhu, M. (2020).Selection and use of mediation testing methods;
application in management sciences. Business & Economic Review.doi:10.22547/BER/12.3.1

It also involves the use of hierarchical regression method (Da Silveira and Arkader, 2007).

Why is Sobel test needed? Sobel

(1982) argues that
“Thus sociologists (and
researchers in many other
disciplines as well) typically
treat the indirect effects they
calculate as parameter values and
formulate inferences
without asking whether the effect
itself is statistically significant.”
(p. 291)
Da Silveira, G. J. C. & Arkader, R. (2007). The direct and mediated relationships between supply chain

coordination investments and delivery performance. International Journal of Operations and Production

Management, 27(2), 140-158.

Why is Sobel test needed? Sobel (1982) argues that “Thus sociologists (and researchers in many other
disciplines as well) typically treat the indirect effects they calculate as parameter values and formulate
inferences without asking whether the effect itself is statistically significant.” (p. 291) his test works well
in a situation when full data are not available, and the researcher has only results of regression analysis
(M ← X; and Y ← M).

Sobel, M. E. (1982). Asymptotic

confidence intervals for indirect effects in
structural equations models.
In S. Leinhardt (Ed.), Sociological
methodology. (pp. 290-312). San
Francisco, CA: Jossey-Bass.
Sobel, M. E. (1982). Asymptotic confidence intervals for indirect effects in structural equations models.

In S. Leinhardt (Ed.), Sociological methodology. (pp. 290-312). San Francisco, CA: Jossey-Bass.

Sobel test works well only in case where there is a large sample size and the sampling of indirect effect
holds the properties of normal distribution (Rucker, Preacher, Tormala & Petty, 2011).

Rucker, D. D., Preacher, K. J., Tormala, Z.

L., & Petty, R. E. (2011). Mediation
analysis in social psychology:
Current practices and new
recommendations. Social and Personality
Psychology Compass, 5(6), 359–371.
Rucker, D. D., Preacher, K. J., Tormala, Z.
L., & Petty, R. E. (2011). Mediation
analysis in social psychology:
Current practices and new
recommendations. Social and Personality
Psychology Compass, 5(6), 359–371.
Rucker, D. D., Preacher, K. J., Tormala, Z.
L., & Petty, R. E. (2011). Mediation
analysis in social psychology:
Current practices and new
recommendations. Social and Personality
Psychology Compass, 5(6), 359–371.
Rucker, D. D., Preacher, K. J., Tormala, Z.
L., & Petty, R. E. (2011). Mediation
analysis in social psychology:
Current practices and new
recommendations. Social and Personality
Psychology Compass, 5(6), 359–371.
Rucker, D. D., Preacher, K. J., Tormala, Z.
L., & Petty, R. E. (2011). Mediation
analysis in social psychology:
Current practices and new
recommendations. Social and Personality
Psychology Compass, 5(6), 359–371.
Rucker, D. D., Preacher, K. J., Tormala, Z.
L., & Petty, R. E. (2011). Mediation
analysis in social psychology:
Current practices and new
recommendations. Social and Personality
Psychology Compass, 5(6), 359–371.
Rucker, D. D., Preacher, K. J., Tormala, Z. L., & Petty, R. E. (2011). Mediation analysis in social psychology:

Current practices and new recommendations. Social and Personality Psychology Compass, 5(6), 359–
371.

The Sobel test inclines to produce an incorrect approximation to the true confidence interval of the
mediated effect (MacKinnon, Warsi & Dwyer, 1995).

MacKinnon, D. P., Warsi, G., & Dwyer, J. H. (1995). A simulation study of mediated effect measures. Mul-

tivariate Behavioral Research, 30(1), 41-62.

The Sobel test is inadequate to show that the effect of X on Y is reduced in size when M is added to the
model (Preacher & Hayes, 2008).

Preacher, K. J., Rucker, D. D., & Hayes, A. F. (2007). Addressing moderated mediation hypotheses:

Theory, methods, and prescriptions. Multivariate Behavioral Research, 42(1), 185-227.

Sobel test is low in power compared to a bootstrap test (Zhao et al., 2010)

Zhao, X., Lynch Jr, J. G., & Chen, Q.

(2010). Reconsidering Baron and Kenny:
Myths and truths about
mediation analysis. Journal of Consumer
Research, 37(2), 197-206.
Zhao, X., Lynch Jr, J. G., & Chen, Q. (2010). Reconsidering Baron and Kenny: Myths and truths about

mediation analysis. Journal of Consumer Research, 37(2), 197-206.

Sobel (1982) firstorder test is the most common product of coefficient test using multivariate delta
method.

Sobel, M. E. (1982). Asymptotic confidence intervals for indirect effects in structural equations models.

In S. Leinhardt (Ed.), Sociological methodology. (pp. 290-312). San Francisco, CA: Jossey-Bass.

The Sobel test works well only in large samples. We recommend using this test only if the user has no
access to raw data.

Preacher, K. J., & Hayes, A. F. (2008). Asymptotic and resampling strategies for assessing and comparing
indirect effects in multiple mediator models. Behavior Research Methods, 40, 879-891.

It also
involves the use of hierarchical
regression method (Da Silveira and
Arkader, 2007).