Correlations Weightlb Heightin HoursofTVper...

Correlations Weightlb Heightin HoursofTVper week Weightlb Pearson Correlation 1 .315 .424* Sig. (2-tailed) .090 .019 N 30 30 30 Heightin Pearson Correlation .315 1 -.146 Sig. (2-tailed) .090 .441 N 30 30 30 HoursofTVperweek Pearson Correlation .424* -.146 1 Sig. (2-tailed) .019 .441 N 30 30 30 *. Correlation is significant at the 0.05 level (2-tailed).

Transcript

00:01 All right, so we're given a correlation table here, and we want to talk about the direction and magnitude of each correlation coefficient.

00:08 So we can have direction and magnitude.

00:18 So let's go ahead and break this down.

00:21 So we have three variables, weight in pounds, height in inches, and hours of tv per week.

00:28 And if we notice, the pearson correlation coefficient is one for the diagonal because weight is directly correlated with weight.

00:36 So that's what that means.

00:38 But if we look at the variable weight and height, actually, before we get into that, just note the symmetry here of this array here.

00:49 So this set of values for height and weight are the same as these values here because weight and height is correlated whether it's weight and height or height and weight, whether you switch them around.

01:04 Same thing can be said with hours of tv per week.

01:09 These values are up here, hours a week and weight, weight hours a week.

01:15 Those are the same.

01:15 And then the other one, the green, is the hours per week.

01:19 These values here are the same as these values here because hours of tv per week and height, height hours of tv per week.

01:27 So no matter which way you look at it, these are the correlation values.

01:29 So we can really only need to look at the upper diagonal or the bottom diagonal here, the upper part of the matrix or the bottom part of the matrix.

01:39 So we're only needing to look at the direction of magnitude.

01:43 So let's just look here.

01:45 So let's look at height and weight, this one.

01:48 So 0 .315.

01:51 This tells us it's positive.

01:53 So height and weight.

01:57 It's positive, so it goes up.

02:03 What that means, if you were to plot these, here's your height and weight, your data would be going up like this.

02:11 And strength would be like, you could call that the magnitude.

02:21 It's moderately correlated, kind of weak.

02:24 It's not significant.

02:25 There's no star here.

02:26 And we're told the stars mean significant at 0 .05 level of significance.

02:33 So these are not significant.

02:35 So this is not a significant relationship or not a significant linear relationship, i should say.

02:47 Because there might be a relationship there, but if there is, it's not linear.

02:59 All right, so now let's look at, that was height and weight.

03:04 Let's do height and hours of tv per week.

03:07 So height and hours of tv.

03:13 So we noticed the correlation coefficient, 0 .424, has a star next to it...

Question

Please give Ace some feedback