I am trying to create a coefficient plot that combines two models with the following command:
coefplot estimates_1_FR estimates_2_FR, bylabel(France) || estimates_1_UK estimates_2_UK, bylabel(UK)
Everything works well, except for the fact that the France estimates range between -0.02 and 0.03, while the UK estimates range between -0.2 and 0.3. For some reason Stata is using the x axis range as -0.2 0.3 for both models. I have tried adding xscale(range(-0.02 0.03)) after "bylabel(France)" but it does not work to change the axis range. Does anyone know how to change the axis range of each model?
Thank you!
Related
I need to obtain the 3D plot of the joint probability distribution of two random variables x and y. Whereas this plot can be easily obtained with Mathematica, I wasn't able to find any documentation in Python.
Can you help me out with that?
I have values 1 through 5000 along the x-axis and percentage along the y-axis, however, I only want the values from 1-150 to be visible along the x-axis (in order to make the scale more usable), but I'm having trouble figuring out how to do it.
Originally, I was just excluding the data with values over 150, but that obviously doesn't work with percentages.
You can achieve this by limiting the range of the x-axis (or y-axis) of the plot: plt.xlim(1, 150) or ax.set_xlim(1, 150).
I want to automatically find the "knee" point of the eigenvalue plot. I.e. I have a vector of eigenvalues (sorted from highest to lowest) and I want some heuristic to find the "knee" point.
Is there some heuristic for doing that
I've found the two following proposals so far.
Setting a threshold, say 0.99, or 0.95 and keep m of n eigenvalues when T(m-1) < 0.99 *T(n) <= T(m) where T(m) = sum(i=1:m){lambda(i)}
The knee is located at a point where the radius of curvature is a local minimum. For a curve y = f(x) the curvature is k = y''/(1+(y')^2)^(3/2). Just replace the derivatives with finite differences.
What do you think of these two proposals? How can I implement the second one? I don't understand how to replace the derivatives with the differences
Did you read this paper?
Non-Graphical Solutions for Cattell’s Scree Test
https://ppw.kuleuven.be/okp/_pdf/Raiche2013NGSFC.pdf
I have data of events in time. At the moment they are represented by (black) markers, at y = 1 on a scatter plot where the x-axis is time.
Unfortunately there is uncertainty in x of about 2 hours. So I want to turn my black markers into more like grey sausage shapes - where there is an equal probability of the event occurring at each point in time in that 2 hours, and the shading is not black such that when all the events are plotted I can see the density building up at different points in time.
Any idea how I blur my precise markers over time into differentially-shaded uniform-probability sausages?
Thanks very much and let me know if this is not clearly stated as a question.
I'm on a test project to learn about geolocation tools. But being a neophyte, a few concepts in PostGIS escape me.
Here's my problem:
The SRID used was 4326.
I have three fields: The field "geocenter" in which I store the center of my circles, the field "georadius" in which I store circle radii and the field "geocircle" in which are stored circles that are really just polygons .
By using the ST_Buffer, I notice that some of the tops of my polygons (circles) exceed the range [-180 -90 180 90].
My concern is to calculate the distance from a point outside the circle from the circle. ST_Distance using these polygons of geometry types, I find that the calculated distance is wrong. I thought then used a CAST but I am having this error: Coordinate values are out of range [-180 -90 180 90] for GEOGRAPHY type.
Please, it is there a way to convert these "geometry" data in "geography" data although the points are outside the range [-180 -90 180 90]?
thank you
I found: Well, I knew there was an overload of the ST_Buffer for geographic data types! It was therefore necessary to use
ST_Buffer (geography, double)
instead of
ST_Buffer (geometry, double)