Skip to main content
6 votes
Accepted

I think standard deviation of y is related to size of x. How do I create a model for this / test this?

One way to model this type of relationship is by using generalized least squares (GLS). GLS allows you to specify variables which have a relationship not just with the mean of the response, but also ...
Frans Rodenburg's user avatar
4 votes

Any tips to differentiate zero and non-zero values on a map with a continuous color scale?

One possibility would be to use a black-body or heated body palette (which you should do in any case to indicate any kind of ordered or numerical variable). Assuming your variable is nonnegative, let ...
Stephan Kolassa's user avatar
3 votes

I think standard deviation of y is related to size of x. How do I create a model for this / test this?

You are asking models of the variance function, or something in the same vein. There has to be some sort of smoothing in the variance model, because we don't expect anything useful can be done if each ...
Zack Fisher's user avatar
3 votes

Any tips to differentiate zero and non-zero values on a map with a continuous color scale?

Use a non-linear color scale if you like to stress specific small changes. When you do that, be aware that you do not trick the viewers of your graph by exaggerating the difference when it is not as ...
Sextus Empiricus's user avatar
3 votes

Representing growth in learning outcomes

Honestly, it's just 4 numbers, you can't beat just reporting those. That said, you might also say: Scores were $1.6\times$ better Scores improved by $30$ percentage points Scores improved by $60\%$ (...
Frans Rodenburg's user avatar
2 votes

Any tips to differentiate zero and non-zero values on a map with a continuous color scale?

It sounds like you are coloring points, not areas. If so, you could distinguish exact 0s from near-0s by the plotting character's point shape or border color. For example: Exact 0s are square; near-...
civilstat's user avatar
  • 4,491
2 votes

Most effective use of colour in heat/contour maps

In the time since the other answers were written in 2012, there have been other proposed color schemes. I personally recommend "viridis" and its associated color schemes, designed to be ...
civilstat's user avatar
  • 4,491
2 votes

False Negative vs False Positive for Multiclass classification

To answer your specific question, the first 3 cases are incorrect prediction, and hence should all be colored red, and the 4th one should be colored green (correct prediction). Strictly speaking, past ...
jginestet's user avatar
  • 2,004
2 votes

False Negative vs False Positive for Multiclass classification

This is confusing because calling a classification positive or negative is only really meaningful when there are only two options (positive/negative). If there are more options, there are multiple ...
mkt's user avatar
  • 19k

Only top scored, non community-wiki answers of a minimum length are eligible