Coefficient of determination (r-squared)

[nozy03]

I have r^2= 0.37. Would you say 37% is good?? I'm not sure what to write.

[bionicturtledotcom]

@nozy03 Ideally, you would test the significance of the R^2 (akin to t test of slope coefficient). While some have a high standard, i think high R^2 are can be unrealistic (most variables are informed by many variables). In my humble opinion, 0.37 conditional on significance, is quite meaningful

[nozy03]

@bionicturtledotcom Wow thank you for your quick reply. I am an undergrad 1st year psychology student and haven't yet been told to test the significance of R^2 (although, now I have seen your video I may just shove it in there!). Was just nice to find a second opinion on 37%.

Enjoying your videos, just subscribed. Thanks very much!

[whkrause]

Um, independent and dependent variables only exist in an experiment. Are you saying you ran an experiment where you manipulated Yahoo stock prices to see its effect on Google stock prices?

[bionicturtledotcom]

@whkrause No, no "effect" implied. The prices are observed as samples drawn from a (theoretical and unobserved) population. Variables don't require, to my knowledge, an experiment: they merely reference the formula which can be used on any dataset

[thehiral84]

thank you.

[macdean]

thanks. What kills me is my Wooldrige book (p 41) calls SSE the explained sum of squares and SSR the residual sum of squares. Your tutorial calls is the Sum Squared Regression (at 5:32) which is slightly different than Sum Square of residuals.It makes it all the harder to understand when statisticians don't agree on the convention.

[ongolos]

yahoo suxs , google should be x, not y.

[unit45x]

Thank you so much! Very helpful!!!

[tufstuf22]

THANK YOU FOR POSTING THIS! my AP stats book does a really horrible job of explaining this so thank you!

[citizenwangpeng]

I appreciate you putting in the time to do the explanation. I thought it was well explained.

[QBhooter]

So you are talking about 70's or 80's.

[QBhooter]

So, you are talking about 70's or 80's.

This is common.

[cosmorocksmyworld]

hey, thanks for posting these videos.  i'm taking a stats class in grad school and even though we work with a program called R, your videos are very helpful in making sense of some of the topics my professor attempts to teach us (he's not very concise or organized)

[zenshinify]

You could have made this video 4 minutes long, and you mixed up your variables at around 8:00. Comparing two variables only means something, when their relationship means something to you. So, unless you're a portfolio manager, this example is meaningless.

[lukewarmpotatoes]

Yer a wank M8

[lukewarmpotatoes]

yer a wank

[657823g]

There are several wrong things here. This is a model I regression which does not apply to this data. Also the correlation coefficient is not the square root of the coefficient of determination. The model is not taken into account when the correlation coefficient is made. So they are not comparable measures of goodness.

[riastrad]

Excellent explanation. Lets hope I can do the same in my presentation!

[missedagain]

If i put a trendline on my scatter plot, i get an R^2 of 0.5, the same as if i calculate it myself, but using RSQ(array1,array2) i get 0.70 based on the same data. What am i doing wrong?

[adeeleo]

On what basis Google is chosen as dependent variable on y-axis and Yahoo on x-axis as independent variable?

[ThreadStone64]

Is the sum of squared residuals the same thing as the sum of squared regression?

No. Sum of squared residuals are sum of squared values of the difference between the actual y which was obtained from the observation and the explained/predicted/estimated/­computed y. The sum of squared regression however is the portion of the sum of squared total minus the sum of squared residuals. Or, it is the portion of the total that was explained by the linear model.

[ThreadStone64]

This video is so good, though shouldn't it be that the interpretation for R-Squared is "the variations in google returns can be explained by the variations in the yahoo returns"? Also from the function he used in the excel, referring to the y and x variable input in his functions, it seems that the dependent variable is still the google periodic returns and the independent variable is the yahoo periodic returns, consistent to the illustrative graph he shown earlier.

Its' quite helpful though.

[slipknotpsychoman]

Is the sum of squared residuals the same thing as the sum of squared regression? Also, if Yahoo! is the independent variable, and Google is the dependent variable, and an R squared value of 32.2%, shouldn't that mean that 32.2% of Google's variation can be explained by the variation in Yahoo!'s return? It seems to me that we are trying to explain the variation in the Google, which depends on the changes in Yahoo!.

[newdoki]

Is it matter if I use reverse range to calculate the number? I mean the range order of Independent and Dependent variables in the Excell function matters? ex. RQG(range of dependent, range of independent) or RSQ(range of independent, range of independent) same?

[openuniverse2003]

Excuse me, at time mark 8:00 to 8:06, GOOG s/b the DEpendent variable, no?

[exom]

Thank! Very helpful to gain insight b4 exams :D keep em coming

[rhettintaipei]

Thanks!!! This is ver helpful!!

[gnigged68]

Best, video, evarrrr!!!!11!11!