Buy Dideo Subscription
Pearson r Correlation in SPSS - How to Calculate and Interpret Correlation (Part 1). Check out our next text, 'SPSS Cheat Sheet,' here: http://goo.gl/b8sRHa. Prime and 'Unlimited' members, get our text for free! (Only $4.99 otherwise, but will likely increase soon.) For additional SPSS/Statistics videos: SPSS Descriptive Statistics Videos: http://tinyurl.com/lyxnk72 SPSS Inferential Statistics Videos: http://tinyurl.com/lm9hpwc Our four-part YouTube video series on regression: http://youtu.be/ubZT2Fl2UkQ How to calculate the correlation coefficient in SPSS is covered in this video. The correlation is also tested for significance and a scatterplot is constructed. YouTube Channel: https://www.youtube.com/user/statisticsinstructor Video Transcript: In this video we'll take a look at how to calculate the correlation coefficient in SPSS. Now when we talk about calculating correlation what we mean here is Pearson correlation. The Pearson correlation measures the degree of the linear relationship between two variables. When we say linear what we mean is that the relationship can be well characterized by a straight line. So a straight line does a good job of representing the relationship. Correlation ranges from negative 1.0 to positive 1.0. There are 3 types of relationships I'd like to talk about with Pearson correlation. And in this description we have two variables the first variable is X and the second variable is Y. So our first type of relationship is a positive relationship and for a positive relationship or a positive correlation that's saying the same thing higher scores on X are associated with higher scores on Y. And what this means is there's a tendency for if an individual has a high score on X they're also going to tend to have a high score on Y. It's not necessarily perfect in most cases it won't be but if you know someone's score on X it gives you a good idea of where they are on Y. High on X high on Y. For positive it's also true that if you have a lower score on X you would tend to have a lower score on Y. The second type of relationship is a negative relationship or negative correlation. Now here we see the opposite pattern. So here higher scores on X are associated with lower scores on Y and vice versa. Lower scores on X are associated with higher scores on Y. Finally our last type of relationship is no relationship and that means there's no predictable relationship between X and Y. And another way to think about it is where here we had higher on X we had higher on Y for positive and for negative we had higher on X with lower on Y, well for no relationship we have if you have a low X you're going to have some low Ys, some medium Ys, and some high Ys. If you have a high X you're going to once again have some low Ys, medium Ys, and high Ys. There's no relationship; no predictable relationship between X and Y for a correlation that exhibits no relationship at all between the two variables. OK with the background of correlation laid out let's go ahead and take a look at our example. In this example we have the following two variables, hours of media or hours media and college GPA. And what we did here in this hypothetical example is we recorded the number of hours of media during a given week that individuals engaged in. And media could be TV, movies, internet, and so on. So we recorded the number of hours of media that people engaged in, in a given week, and then we also obtained their college GPA and we want to see if there's a relationship between these two variables as measured by Pearson's r our correlation. And if you think about it if somebody watches a lot of media so they're spending let's say an inordinate amount of time watching media whatever form it may take. That's not going to leave them probably sufficient time to attend to their studies. And in that case if we had a lot of hours of media watched that probably would suggest that the GPA may be lower. But if that was true high hours media, low GPA, do you recall kind of correlation coefficient that would be? Well if we use the generic variables X and Y here high on X low on Y so it's an opposite pattern, high on one low on the other, that you may recall is a negative correlation. So it makes sense, at least theoretically speaking, that there could be a negative correlation here. But let's go ahead and run the analysis and see what we find. To run the correlation we go to Analyze, and then Correlate, and then Bivariate Lifetime access to SPSS videos: http://tinyurl.com/m2532td
