 Students, we have studied Pearson R correlation and now we are going to study partial correlation coefficient. Partial correlation coefficient is somehow different from the other types of correlation coefficients because we compute this correlation coefficient for more than two variables. Normally, correlation coefficient computes for two variables but partial correlation coefficient computes for more than two variables because we see the relationship of two variables after controlling the effect of third and fourth variables. We see the relationship of two variables after controlling the effect of one variable. Partial correlation coefficient is when you have Pearson R correlation coefficient. For that, it is necessary to compute Pearson R when you have linear relationships. When you have Pearson R, then you can compute partial correlation coefficient. The value of partial correlation coefficient is also between Pearson R minus 1 to plus 1. The minus sign shows the negative relationship and the positive sign shows the direct and positive relationship. The higher the value of this relationship, the more we consider this relationship as absolute or strong. The higher the value of this relationship, the weaker we consider this relationship. If we talk about its formula, its formula is rxy dot z. We denote this as partial correlation coefficient. Its formula is rxy minus rxz into ryz divided by under root of 1 minus rxz square and 1 minus ryz square. If you have, for example, rxy is 0.63, rxz is 0.57 and ryz is 0.88, then you have rxy after the controlling the effect of z is 0.329. Initially, rxy is 0.63. If we control z, then this value will be 0.329. These are significant degrees in the value of rxy because we have controlled z. So z is a stronger predictor and variable. If we look at the value of rxz and ryz, then the relationship of z is quite strong with x and y. That is why rxy is ruining the relationship. When we have controlled it, then we have the actual value of rxy which is less than the value of 0.329. So apparently, what we can see is that rxy has a significant strong relationship. It is actually moderate in nature. So in this way, you can control the effect of other variables using this partial correlation coefficient. How do we compute this in SPSS? Here, I am giving you an example. You will go to analyze, correlate, correlate, say bivariate. Instead of bivariate, you will come to partial. You will select the main variable and you will keep the controlling variable in this. You will do okay. So this will come to you in the table in which it is telling you that after controlling the relationship maintenance behavior, what is the score of Facebook intensity and online bridging social capital? So this is 0.412 and this is significant because the sig value is less than 0.05. So our h1 has been accepted. There is a statistically significant strong relationship between online bridging social capital and Facebook intensity. We will go ahead and exercise this. This will make it easier for you to understand this.