rolando2

5,669 reputation

722

bio	website	integrativestatistics.com
	location	Boston, MA
	age
visits	member for	2 years, 4 months
	seen	2 days ago
stats	profile views	550

	5,669 reputation	bio	website	integrativestatistics.com	visits	member for	2 years, 4 months
722 badges		location	Boston, MA		seen	2 days ago

summary answers questions tags badges favorites bounties reputation activity

1,122 Actions

suggestions reviews revisions comments badges posts accepts all

May 15	comment	ANOVA with 4 factors, 1 covariate & 500 subjects Adjusting (partialling out, holding constant, removing the influence of, accounting for) would mean estimating the group difference in the DV by Factor 1 if each group had the same mean age. (There are causality issues to be addressed here, but statistically it's straightforward.) Whether one calls this ANCOVA or regression or a GLM is a matter of semantics and perhaps of the type of output one chooses to examine. Also, it's not clear to me from the OP that age and Factor 1 are correlated, though it seems a good guess. Cheers ~
May 15	comment	Does this histogram of residuals indicate that the residuals are effectively random? In addition to whuber's helpful comments, one way to try to rule out non-random patterns in residuals is to create a scatterplot of the residuals (on the vertical axis) against either the dependent variable or the predicted values of it (on the horizontal axis). Ideally one would see no systematic increase or decrease in the mean or the variation as one moved from left to right.
May 15	comment	ANOVA with 4 factors, 1 covariate & 500 subjects The OP is interested in the effect of Factor 1 when adjusting for the covariate. What would this adjustment accomplish if the correlation between the covariate and Factor 1 were zero?
May 11	comment	Is it a true main effect if it is significant only when interaction is included? Possible responses for your chair: 1. Should the concepts of parsimony or penalization play any role in this work? 2. At what point would I need to start accounting for the multiple comparison problem? 3. Why stop at about 100?
Apr 18	comment	What factors do I have to consider when deciding if creating a composite score using four t-scores is defensible psychometrically? It may be that the answer to this question would take the form of a book or one or more graduate-level courses.
Mar 23	comment	Plotting confidence intervals for the predicted probabilities from a logistic regression (-1) These CIs are for each for individual cases? If so, for a binary outcome, the only sensible CI for a predicted probability is [0,1]. Even though this may be a technically proficient answer.
Mar 22	comment	How do I interpret a significant interaction effect that has a low effect size? @Glen_b - I think this is a good revision. Cheers ~
Mar 21	awarded	Taxonomist
Mar 20	comment	How to estimate an upperbound for logistic regression by only 5 to 7 data points? The first sentence to your question is very Neo-Platonic.
Mar 20	comment	How do I interpret a significant interaction effect that has a low effect size? I almost upvoted, but if we're going for "canonical answers" (not that many of mine are), either the "large enough" or the footnote will have to go in order for the answer to make sense.
Mar 20	comment	Which regression model to use with ordinal & skewed dependent variable? It's hard to imagine a single population of people giving ratings such that there'd be a large spike at 0, almost no values at 1 or 2, and a near bell curve centering on 5 or so. Is it possible you've got 2 distinct populations?
Mar 14	comment	What's the difference between a component and a factor in parallel analysis? possible duplicate of What are the differences between Factor Analysis and Principal Component Analysis
Mar 11	comment	Sample size calculation for multivariate problems Framing the task as the very general "multivariate investigation" won't be enough: you'll need to narrow things down to a specific procedure and then you'll be able to find specific help on sample size / power analysis.
Mar 11	comment	Use of PCA analysis to selection of variables for a regression analysis The 2012 study reported at r4stats.com/articles/popularity showed 31% of data analysts using R.
Mar 9	comment	Strongest predictor of outcome A nice answer by @Glen_b. Please see the FAQ (frequently asked questions) for information about this site. You can expect well-thought-out answers about specific questions you may ask about statistics, but you shouldn't expect other users to conduct your analyses for you or to teach you how to use your software (at least, not for free). For those things you may need to hire a consultant--but this is not really a place to seek out that kind of help.
Mar 9	comment	How to check the distribution of the given data A nice job with a difficult question to answer constructively.
Mar 9	comment	Estimating the number of Twitter users that drive to work katelyn friedson - Can you say a little about what you've tried so far? @Ross Millikan - I don't see how you get "a factor [of] 3" for 10% compared to 100%. Also, does "±30−50%" mean "about 30-50%"?
Mar 9	revised	Interpreting this regression coefficient edited body
Mar 9	comment	Interpreting this regression coefficient +1 for your last 2 paragraphs. But Y is described by the OP as "the extent to which a candidate mentions other users when he or she tweets." This is not esp. clear, but it doesn't match your number-of-tweets interpretation.
Mar 3	comment	Size of a test and level of significance I don't recognize the meaning of "size of a test." Perhaps you mean "size of a test statistic" such as F or T or Z. In that case the level of significance (p) is not necessarily higher or lower. Are you quoting from a particular source? If so, please include the quote and someone will no doubt help clarify it for you.