7,545 reputation
1033
bio website
location San Jose, CA
age 34
visits member for 2 years, 10 months
seen 19 hours ago

Mad data scientist.


Aug
22
comment It it possible in R to specify a regression formula for the hazard rate for a survival analysis model?
Did you mean $S(t)$ and not $f(t)$, which is usually reserved for the density?
Aug
21
comment Leverage - influential points
@sufeipopo No need to thank me. You can just click the check to the left of the response to select it.
Aug
21
comment Leverage - influential points
Let's say you have $m$ continuous variables and one categorical variable with $l$ levels. If you are including the latter as a set of $l-1$ binary indicators to avoid the dummy variable trap, then you would have $k=l + m$, counting the constant as one variable.
Aug
21
revised Leverage - influential points
added 116 characters in body
Aug
21
revised Leverage - influential points
deleted 1 character in body
Aug
21
answered Leverage - influential points
Aug
21
revised Two stage GMM estimator in Matlab
added 81 characters in body
Aug
20
revised What’s wrong with this way of fitting time-dependent coefficients in a Cox regression?
added 3 characters in body
Aug
20
revised What’s wrong with this way of fitting time-dependent coefficients in a Cox regression?
added 2 characters in body
Aug
20
revised What’s wrong with this way of fitting time-dependent coefficients in a Cox regression?
added 136 characters in body
Aug
20
revised What’s wrong with this way of fitting time-dependent coefficients in a Cox regression?
added 136 characters in body
Aug
20
revised What’s wrong with this way of fitting time-dependent coefficients in a Cox regression?
added 175 characters in body
Aug
20
revised What’s wrong with this way of fitting time-dependent coefficients in a Cox regression?
added 175 characters in body
Aug
20
answered What’s wrong with this way of fitting time-dependent coefficients in a Cox regression?
Aug
18
revised Relationship between the latent variable as a function of regressors and the logit model?
added 7 characters in body
Aug
18
comment Proxy variable approach to deal with endogeneity due to reverse causality
Criminologists have tried using the number of DUI and disorderly conduct arrests made per police officer as a proxy for proactive policing intensity in regression where more serious crimes were the outcome. I don't think this identifications strategy would placate most economists these days.
Aug
18
comment Relationship between the latent variable as a function of regressors and the logit model?
Both are used by applied economists. In practice, the average marginal effects and predictions from the two are often quite similar, so the choice usually does not matter very much, except in cases where a lot of observations have probabilities near zero or one.
Aug
17
awarded  Nice Answer
Aug
16
revised Relationship between the latent variable as a function of regressors and the logit model?
added 3 characters in body
Aug
15
revised Relationship between the latent variable as a function of regressors and the logit model?
deleted 28 characters in body