6,083 reputation
1332
bio website integrativestatistics.com
location Boston, MA
age
visits member for 3 years, 9 months
seen 3 hours ago

2d
revised Best practice for visualizing a lift from zero?
edited tags
2d
comment Best practice for visualizing a lift from zero?
I would say that what depends is not the limit of the ratio but one's interpretation of that ratio.
2d
comment Systematic Review (maybe)
This is not really a statistics problem. One might call it a measurement problem or even a research problem. In addition, there is not going to be a single correct answer (though there may be answers or approaches that many commentators would reject).
2d
comment Number of possible statistical test can be used on the observation data.
Please specify what you mean by "show the relationship between the known and unknown factors."
Oct
18
comment How to make a vertical line in R
Question seems on-topic as it is about data visualization. I'd like to see a fuller explanation for the effective code described by @user777.
Oct
14
awarded  Popular Question
Oct
12
comment How to Calculate in Binomial Probability Distribution
You'll also need to decide what x and/or r are going to represent for you. Currently x is in the formula but not defined, and r, the opposite.
Oct
10
comment Prediction when survey subsets create dramatically smaller Ns
Every person has a Y value.
Oct
7
asked Prediction when survey subsets create dramatically smaller Ns
Oct
3
comment What kind of test is this?
The method you describe has a bit in common with what's sometimes called monadic testing. Sources that go into that might also go into your method.
Oct
3
comment How to apply a logistic + an OLS model to the same data set?
Possibly censored regression would apply. I learned a lot from stats.stackexchange.com/questions/49443/…
Oct
1
comment Multiple Linear Regression: Obtaining a Stable Model
Remember that under random sampling a relationship with p=.05 has a 50-50 chance of producing a p>.05 among the next sample chosen. Sound like you've overfitted.
Sep
30
awarded  Explainer
Sep
28
revised Reference for the idea that a simpler model can be used when the range of data values is smaller
deleted 279 characters in body
Sep
27
comment In curvilinear relationship (inverted U shaped), how do we calculate the highest point?
+1 It's valuable to look for an interval instead of just a point estimate.
Sep
27
comment Coefficient changes sign when adding a variable in logistic regression
My point is that, as I'm sure you know, "The effect on the outcome," if ever determined, would be a real-world thing and would never change depending on how we model it. What the model shows is a coefficient, a statistical association,...perhaps "an apparent effect"?
Sep
27
comment Coefficient changes sign when adding a variable in logistic regression
Though I appreciate the thought that went into this, -1 because of "When travel distance is the only variable, the effect on the outcome is positive." The OP, I noticed, was careful to use language that avoided the inappropriate attribution of causality.
Sep
25
comment scale creation - how to know if concept B is part of concept A or seperate concept
You could search for Scale development; Correlated factors; Simple structure; Internal consistency; and Cronbach's alpha. @Conjugateprior's concepts and terms may well be very productive but they are more specialized and advanced and less mainstream than these.
Sep
25
comment Dichotomizing Continuous Variables in Regression: Good or Bad?
Try demonstrating how much better predictive accuracy on a holdout sample will be when using the original continuous variables.
Sep
25
comment How to calculate multicollinearity of binary variable with other predictors in regression model?
You can use binary variables for this. Your assumption to the contrary is, as far as I know, unfounded.