network profile
| bio | website | utsa.academia.edu/CoreySparks |
|---|---|---|
| location | San Antonio, TX | |
| age | ||
| visits | member for | 1 year, 4 months |
| seen | May 21 at 0:49 | |
| stats | profile views | 22 |
I am a biological anthropologist trained in demography and statistics. I'm currently doing work using a lot of spatial statistical methods (point pattern, spatial regression, and some spatial Bayesian methods) and applying them to lots of different problems in population science and public policy. I also maintain a strong interest in evolutionary theory as applied to human behavior. I teach graduate stats courses in linear models, hazard models and spatial statistics.
|
Apr 28 |
comment |
Ripley's K Function and L Function for Point Patterns I would use the simulation (envelope()) function before I put any statements on that, you need to evaluate how many times you could observe similar values of L by chance |
|
Apr 27 |
answered | Ripley's K Function and L Function for Point Patterns |
|
Apr 7 |
answered | Looking for a test for shape comparison |
|
Mar 25 |
comment |
What weights to use actually that's not so bad, sometimes weights are in the thousands, but those are typically population weights. |
|
Mar 23 |
answered | What weights to use |
|
Mar 22 |
comment |
Test to show when diverging linear regression models are statistically different Isn't this just a parallel slopes question? do you want to know if the slope is the same in the two groups? Just put an interaction term in the model, and look at the parameter test for the interaction term |
|
Feb 19 |
awarded | Commentator |
|
Feb 19 |
comment |
spline options in gamm4 don't you just put x in the model, not bs()? |
|
Feb 13 |
comment |
Cox proportional hazard model fit to complex survey data If you use a complex survey design, as the OP said, you must use the correct procedure for estimating the standard errors of the estimates, svycoxph does this, and extractAIC on a survey design object does not work |
|
Feb 13 |
answered | Cox proportional hazard model fit to complex survey data |
|
Feb 5 |
comment |
Using Anselin Local Moran's I Values in Regression I agree with the OP, I don't know what it would mean in a model as an IV, I still stick with my statement that some sort of spatially structured model would be better suited for this kind of thing |
|
Feb 5 |
answered | Using Anselin Local Moran's I Values in Regression |
|
Jan 26 |
awarded | Yearling |
|
Jan 17 |
comment |
Best analysis for count data as response variable But it is not strictly normal |
|
Jan 17 |
awarded | Editor |
|
Jan 17 |
revised |
Best analysis for count data as response variable the family in the glm was wrong |
|
Jan 17 |
answered | Best analysis for count data as response variable |
|
Jan 17 |
suggested | suggested edit on Best analysis for count data as response variable |
|
Jan 11 |
comment |
Does Mahalanobis distances have “significance” associated with them? oh, it's absolutely circular, but if you're wanting to see how well the clusters are distinguished from one another, then DFA or something like it is the way to go. The DFA typically will have a test statistics with it, like a Wilk's lambda or Pillai trace to test for differentiation between the groups, but if you have lots of observations, this can be a little conservative, I like the crossvalidation classification rate. This site may get you started: statmethods.net/advstats/discriminant.html But this is assuming you're using R, I know how to do it in sas too, using proc discrim |
|
Jan 11 |
comment |
Does Mahalanobis distances have “significance” associated with them? so you did a finite mixture model, and that found a mixture of several Gaussian densities, so each observation should now belong to one of these distributions identified in the finite mixture model. What I have done before is make a new variable in the data which is the group each data point is assigned to in the mixture analysis and treat it as a known group, then use that as the input into a discriminant function. A discriminant function works off a distance matrix, you classify each observation to a group if its distance to a particular group mean vector is the minimum of all mean vectors |
