6,222 reputation
1534
bio website integrativestatistics.com
location Boston, MA
age
visits member for 4 years
seen 12 hours ago

12h
revised Linear regression model mistakenly gives $R^2$ equal to 1
code needs either hard returns or ";"s to run. Plots may help with understanding.
21h
comment Sample size for logistic regression. How to determine the number need for positive and negative cases?
Try Googling "rare event logistic regression." Gary King may have done articles that will be helpful.
Jan
24
comment Does clustering need scalar data?
Re: your 2nd sentence: are you sure? I have not found this to be true.
Jan
23
comment Prediction based on multiple time series - Python
Is it essential that an answer make reference to Python?
Jan
23
revised Prediction based on multiple time series - Python
I have tried to clarify. If I have missed your intended meaning, please roll back those edits.
Jan
23
comment Multiple regression or multivariate regression
I'd be interested in an explanation that uses some narrative in addition to the code.
Jan
23
comment Using seasonality in a model
I find this an interesting question too, but I suspect it'd fit better on an economics or econometrics site.
Jan
23
comment Ideal number of variables for PCA
Certainly the inclusion of a different subset of variables is liable to change the nature of the obtained components and the patterns of relationships within and among components. If you think about it, PCA would be a strange and pretty useless beast otherwise.
Jan
23
comment mediation analysis when mediator is categorical (SPSS)
A better link to a page where you can buy the article ($40 US) is tandfonline.com/doi/pdf/10.1080/03637750903310360#.VMGS6Y10x7Q (I have not read the article).
Jan
20
comment Significance of differences between two scenarios
Suggest you think in simpler terms: how might time differences be analyzed in some routine situation where there are two conditions to be compared and where an independent variable can take on 4 values in each condition?
Jan
20
answered How to rearrange 2D data to get given correlation?
Jan
18
answered Does triple interaction need to include all main effect variables?
Jan
17
comment Why including some observations twice changes the coefficients of logistic regression?
"[...] having two instances of some points that are already on the scatterplot should not change anything" - it wouldn't change the appearance of the points, but think about the fitline and how it is weighted by the number of points in each location.
Jan
15
comment Very large odds ratio (558) in logit regressions
Since logistic regression requires listwise deletion (complete case analysis), chances are your inclusion of control variables has markedly reduced the sample size, in a way that biases the iv's coefficient upwards.
Jan
4
comment Which Regression do I have to use when my DV is log R&D expenditures and my IV variables are some Blau Index lagged?
What makes you lean toward some type of regression as opposed to analyzing using, say, a scatterplot and a test of association? Do you have other variables that you need to control?
Jan
4
comment three-way-interaction between two continuous and one binary variable using OLS stata
Could you show your obtained results -- N, standardized and unstandardized coefficients, standard errors, and p-values. Also, have you checked your predictors for collinearity?
Jan
4
awarded  Yearling
Jan
4
comment Departure from normality assumption in ANOVA: is kurtosis or skewness more important?
I'd find the question most productive if it could be resolved into a statement such as "Skewness is so much more important to inferences than kurtosis that skewness at the level of ___ would typically distort results as much as would kurtosis at the level of ___." Without some such quantification, merely to say one or the other is more important doesn't help us much.
Jan
4
comment Find whether one mean is very different from all others in multiple measurements
Could you clarify: "...whether each individual with one measure per group varies a lot by one group more than the others, some kind of across individual variability."
Jan
4
comment Conjoint Analysis Simulation SPSS - excluded subjects
I'm afraid this is off-topic for this site because the question is solely about how to get this or that software to accomplish a certain task.