Timeline for Do we actually take random line in first step of linear regression?
Current License: CC BY-SA 4.0
22 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Dec 18, 2021 at 18:02 | comment | added | F.C. Akhi | This algorithm is for giving intuition on linear regression. Practically it will not work. Like in the later video author gradually reduced four different conditions to one. | |
| Dec 17, 2021 at 21:18 | history | edited | Karolis Koncevičius | CC BY-SA 4.0 |
added 19 characters in body
|
| Dec 17, 2021 at 20:06 | answer | added | Karolis Koncevičius | timeline score: 4 | |
| Dec 17, 2021 at 12:54 | answer | added | Roger V. | timeline score: 3 | |
| Dec 17, 2021 at 1:33 | answer | added | Cliff AB | timeline score: 3 | |
| Dec 16, 2021 at 11:58 | comment | added | Niels Holst | We know that the best-fitting line goes through the point (xm, ym), where xm and ym are the averages of all x- and y-values, respectively. You could then find the best line (defined by the angle) through rotation around that point. | |
| S Dec 15, 2021 at 7:08 | vote | accept | F.C. Akhi | ||
| S Dec 15, 2021 at 7:08 | vote | accept | F.C. Akhi | ||
| S Dec 15, 2021 at 7:08 | |||||
| Dec 15, 2021 at 7:08 | vote | accept | F.C. Akhi | ||
| S Dec 15, 2021 at 7:08 | |||||
| Dec 15, 2021 at 2:25 | comment | added | Glen_b | @f-c-akhi There are a number of suitable but simple approaches (starting from 'naive' ways to fit a line), to motivate ordinary linear regression but this one seems to be flawed. Given the issues that arose in your previous question, which related to the same video (or at least the same presenter), I'd urge you to consider that you may be served by some other resource. | |
| Dec 15, 2021 at 0:07 | answer | added | Aksakal | timeline score: 19 | |
| Dec 15, 2021 at 0:00 | history | tweeted | twitter.com/StackStats/status/1470906465544192000 | ||
| Dec 14, 2021 at 23:17 | history | became hot network question | |||
| Dec 14, 2021 at 21:24 | comment | added | whuber♦ | The algorithm actually doesn't work. Consider what happens when all the points happen to lie to the right of the y-axis and above the initial line. The slope and intercept will increase on average until half the points lie above it and half lie below it. From that point on, only small fluctuations in the line will happen, because changes to slope and intercept tend to be balanced out. If the slope of the initial guess was far off, its estimate can never reach a reasonable value. One lesson: the proposer of an algorithm has a duty to show (a) it converges (b) to reasonable values. | |
| Dec 14, 2021 at 20:58 | answer | added | Underminer | timeline score: 6 | |
| Dec 14, 2021 at 18:08 | comment | added | whuber♦ | As a practical matter, solvers often use heuristics to find reasonable starting guesses. For instance, we might split the points into three roughly equal vertical strips (by count). Drop the middle strip. In each of the left and right strips, compute the median $x$ value and median $y$ value, thereby producing a "median point" within each strip. Connecting those points gives a very reasonable estimate. (It is a simple form of "robust regression.") The illustrated regression algorithm, BTW, is extremely poor: it must be considered as a conceptual explanation only. | |
| Dec 14, 2021 at 16:03 | comment | added | Sycorax♦ | FWIW, It's plausible that the instructor is introducing the concept in this way so that when students arrive at advanced models like neural networks, the mechanics of gradient descent are familiar. But, this particular slide seems like a poor way to do so because it’s very far removed from a reasonable algorithm. | |
| Dec 14, 2021 at 15:59 | answer | added | Dave | timeline score: 27 | |
| Dec 14, 2021 at 15:21 | history | edited | F.C. Akhi | CC BY-SA 4.0 |
added 18 characters in body
|
| Dec 14, 2021 at 15:19 | answer | added | mribeirodantas | timeline score: 9 | |
| Dec 14, 2021 at 15:13 | comment | added | Frank Harrell | Linear regression when using sum of squared errors as the optimality criterion has a closed form solution. There is no trial and error. | |
| Dec 14, 2021 at 15:10 | history | asked | F.C. Akhi | CC BY-SA 4.0 |