8,414 reputation
1236
bio website
location San Jose, CA
age 35
visits member for 3 years
seen 42 mins ago

Mad data scientist.


41m
revised Testing equality of two X values in quadratic regression
added 60 characters in body
57m
revised What is the best way to remember the difference between sensitivity, specificity, precision, accuracy, and recall?
deleted 1 character in body
1h
revised What is the best way to remember the difference between sensitivity, specificity, precision, accuracy, and recall?
added 188 characters in body
2h
revised What is the best way to remember the difference between sensitivity, specificity, precision, accuracy, and recall?
added 215 characters in body
2h
answered What is the best way to remember the difference between sensitivity, specificity, precision, accuracy, and recall?
2h
comment Sample size calculation for non-normal data (possibly lognormal)
Why don't you post your data, describe what it measures, and describe the test that you want to perform?
1d
comment RCT baseline controls that do not match outcome measures
@Tina If you like the answer, please accept it.
1d
comment Marginal effects of a logistic model, and their standard errors
"Not well-defined" seems like a stretch to me. There are various marginal effects like average marginal effects, marginal effects at the mean/median, or at representative values. In non-linear models, they are all functions of covariates. Some are arguably better than others for a given purpose. Often, they are all quite close in practice.
1d
comment Which p-value to report in a comparison of different logistic regression models using marginal effects?
@non-numeric_argument I answered this on SO.
2d
answered Which p-value to report in a comparison of different logistic regression models using marginal effects?
2d
comment Fuzzy RDD issue
@Luisa If you are asking about IV estimation, I would do both. There are cases where using all the data is more efficient. There will also be cases where that is a bad idea. It is hard to know which case your problem lies in, especially without knowing the details. Ideally, you try all kinds of sensible approaches (vary the kernel, bandwidth, etc.) and they all more or less agree. That is the most convincing approach.
2d
comment Fuzzy RDD issue
@Luisa Let me try to be clearer. I would still use the all the data for the LWIV or the RD. But if I had 1000 men and 1000 women, but only 200 men near the male cutoff and 500 women near the female cutoff, the overall treatment effect should put more weight on the women.
Oct
28
awarded  Cleanup
Oct
28
revised Fuzzy RDD issue
rolled back to a previous revision
Oct
28
revised Fuzzy RDD issue
added 94 characters in body
Oct
28
revised Fuzzy RDD issue
added 151 characters in body
Oct
28
revised Fuzzy RDD issue
added 45 characters in body
Oct
28
revised Fuzzy RDD issue
added 117 characters in body
Oct
28
answered Fuzzy RDD issue
Oct
28
revised Fuzzy RDD issue
added 32 characters in body; edited tags