6,173 reputation
1434
bio website integrativestatistics.com
location Boston, MA
age
visits member for 3 years, 11 months
seen 2 days ago

2d
comment What to do after running an exploratory factor analysis?
Unclear what you are asking. Are you asking how to compute a score for each person for each factor? This can be a simple matter of choosing the option for saving factor scores.
Dec
13
comment Linear relationship between explanatory variables in multiple regression
On your 2nd sentence: If independent variables were totally uncorrelated, then much of the rationale for regression would become moot. Each bivariate relationship of a predictor with Y would show up as the same as the relationship when all the other predictors were controlled. In that case, why control?
Dec
12
comment What's a real-world example of “overfitting”?
Interesting discussion. I'll add just that the graph might support the argument better if the lines were labeled.
Dec
11
awarded  Necromancer
Dec
11
comment What is cross-validation?
Helpful answer, and nice use of "ad hocly."
Dec
4
comment What variables explain which PCA components?
Neat idea--thank you.
Dec
4
comment How to find if a difference is statistically significant?
You'll want to get familiar with tests of outliers and control process tests.
Dec
1
comment How to interpret a ROC curve?
In your 2nd-to-last sentence: "need" in order to....? Your last sentence: to estimate it with ___ degree of accuracy?
Nov
27
revised Analysing data on importance ratings
minor wording change
Nov
27
answered Analysing data on importance ratings
Nov
27
revised Analysing data on importance ratings
Ratings are distinct from rankings (this is 1st, this is 2nd, etc.) and need to be treated differently.
Nov
27
comment How to analyze my Likert-scale data
If you have $19 and 2 hours to spend I highly recommend Paul Spector's little book at sagepub.com/books/Book3653 .
Nov
27
comment Cross-Validation: how to choose k for small datasets (n=900)?
For better answers I suggest you say what classification procedure you're conducting. If it's predicting a binary outcome, how high is the incidence rate of that outcome? E.g., 90 cases would be insufficient if that rate is 10%.
Nov
27
comment How to analyze my Likert-scale data
If you truly have no idea, then you must not have read any of the Related links on the right side of this page. That's a place to start. If you are struggling with a choice between two or more alternatives, please say something about that.
Nov
24
comment Testing and reporting interactions in multiple regression
Hint: compute the slope for z and non-z cases. Compare the difference between those slopes to the interaction coefficient you just obtained.
Nov
23
comment machine learning model with 50% chance to be deterministic
I like the first 1/2 of the answer. "looking at all your data to decide what features to include": if this approach were taken, then your point about cross-validation wouldn't apply, because this would not even be cross-validation. It would defeat the purpose of cross-validation.
Nov
22
answered Testing and reporting interactions in multiple regression
Nov
16
answered Factor loading and corrected item to factor correlation
Nov
14
awarded  Popular Question
Nov
12
comment Need Insight on Measuring Variable Effect
Consider the possibility that what you need is not an answer from some knowledgeable person who's at arm's length from the work, but either a consultant or a coach who can get to know in detail the data, your analyses thus far, and your level of understanding and analytic capabilities.