GREAT, CLEAR , CONCISE, COHERENT explanation. The speed of the deliverance was a bit intimidating, like Tennis ball thrown from a pitching machine. I played the video at .75 speed and it became even enjoyable. Above all your lesson is SPOT ON helpful.
S² is the mean square error....its the sum of the square of the difference in the known values of y and predicted values of y divided by the no of variable pairs all square rooted s²=sqrt((Σ(yᵢ-ŷ)²/(n))
Hi Katie, I hope you do not mind me asking, but after watching dozens of videos, it seems that you are the only person who can help me. I am performing Total Least Squares / Orthogonal Distance regression with a non-linear model Ln(P) = a + b / (T + c), where a, b, and c are the adjustable parameters. I am also treating the function as an implicit function F = Ln(P) - a - b / (T+c) =0. After convergence, how do I calculate the Standard Error (SE) for each of the adjustable parameters ? And, can you please say something about K (or Kappa?) ? In the mean time, I'll add subroutines to calculate the averages for T and P, t-distribution, etc. I Really hope to hear from you. A link to a CLEAR paper will suffice.
GREAT, CLEAR , CONCISE, COHERENT explanation. The speed of the deliverance was a bit intimidating, like Tennis ball thrown from a pitching machine. I played the video at .75 speed and it became even enjoyable. Above all your lesson is SPOT ON helpful.
This was very helpful! Thank you for posting.
pls help me why k=1
i like how you used an easy to digest small dataset
pls help me why k=1
beautiful
How do you define s or s^2.
Exactly my question as well.
S² is the mean square error....its the sum of the square of the difference in the known values of y and predicted values of y divided by the no of variable pairs all square rooted
s²=sqrt((Σ(yᵢ-ŷ)²/(n))
you'll use the regression line to get the predicted values of y
Hi Katie, I hope you do not mind me asking, but after watching dozens of videos, it seems that you are the only person who can help me. I am performing Total Least Squares / Orthogonal Distance regression with a non-linear model Ln(P) = a + b / (T + c), where a, b, and c are the adjustable parameters. I am also treating the function as an implicit function F = Ln(P) - a - b / (T+c) =0. After convergence, how do I calculate the Standard Error (SE) for each of the adjustable parameters ? And, can you please say something about K (or Kappa?) ? In the mean time, I'll add subroutines to calculate the averages for T and P, t-distribution, etc. I Really hope to hear from you. A link to a CLEAR paper will suffice.
please help me why k=1
k, means a numbe of independent variables in the equation, the equation is simple linear regression and there is only one value of x