Questions tagged [scaled]
The scaled tag has no usage guidance.
8
questions
2
votes
0
answers
102
views
How to interpret RMSE with scaled values vs ground truth values
I've trained an LSTM model and am measuring RMSE. I know how RMSE is interpreted normally, but I'm a a little confused on how to interpret the RMSE value when I have scaled my features and target ...
0
votes
1
answer
122
views
Converting scaled parameters to unscaled parameters in exponential regression
I would like to calculate two types of bivariate exponential models on scaled data (therefore both variables are expressed as z-scores):
Model 1:
$$
y=b_{0}*e^{b_{1}x} + \epsilon
$$
Model 2 (is ...
0
votes
1
answer
138
views
Scaling formula (reference required)
I came across a very good scaling formula to scale theta based on Item Response Theory to the scale of 31-68.
The original post is here. The formula looks like this:
$f(x) = \frac{(b-a)(x-min)}{max-...
2
votes
1
answer
477
views
Interpretation of scaled error measures
can someone give me an explanation on how one would interpret the result of a scaled error measure.
For example the Mean Absolute Scaled Measure (MASE). The numerator is the mean absolute error and ...
2
votes
1
answer
160
views
Interpretation of OLS: Scale dependent variable by independent variable instead of including it in the regression model
How does the interpretation on the coefficient of X in this OLS model:
Y(Profit in €) = b0 + b1 X + b2 X2 (Firm Size in €) + e
change if I rewrite the model as
Y(Profit in €) / X2(Firm Size in €) = b0 ...
2
votes
1
answer
119
views
How to interpret a scaled response variable as an unscaled response variable?
I'm new to R and I'm having trouble to interpret the estimates of my scaled response variable.
I used (scale) function to standardize all my variables (1 response ...
0
votes
1
answer
1k
views
Confused about h-step ahead forecasts
I have 12 months of in-sample data and 12 months of out-of-sample data. I'm trying to calculate the scaled error for an h-step ahead forecast where h=1, 6 and 12. Do I just calculate the error at ...
2
votes
1
answer
2k
views
Normalised binomial random variable
Assume $Z$ is a Binomial random variable with a distribution function
$$
f(z)=\binom{n}{z}p^z(1-p)^{n-z}
$$
What is the distribution of the random variable $Z/n$? Does it have a name? Any close form ...