landroni
  • Member for 8 years, 1 month
  • Last seen more than a month ago
Statistics Jokes
16 votes

Taken from xkcd.com: Cell Phones

View answer
Box-Cox like transformation for independent variables?
11 votes

Take a look at these slides on "Regression diagnostics" by John Fox (available from here, complete with references), which briefly discuss the issue of transforming nonlinearity. It covers Tukey's "...

View answer
Which is the best visualization for contingency tables?
9 votes

To complement @gung's and @xan's answers, here's an example of mosaic and association plots using vcd in R. > tab period activity morning noon afternoon evening feed 28 4 ...

View answer
Back-transformation and interpretation of $\log(X+1)$ estimates in multiple linear regression
4 votes

According to Wooldridge 2009 (p. 192), the log(1 + x) transformation may retain the usual interpretation of log(x): In cases where a variable $y$ is nonnegative but can take on the value 0, $log(1+...

View answer
How to cope with serial correlation and time effects in a panel data model in R
3 votes

Your question is not very clear, and the link to the data is no longer working... For the time fixed effects, your call should look like this: fixed <- plm(Price ~ Income + Housing_units + ...

View answer
Does it make sense to add a quadratic term but not the linear term to a model?
3 votes

Brambor, Clark and Golder (2006) (which comes with an internet appendix) have a very clear take on how to understand interaction models and how to avoid the common pitfalls, including why you should (...

View answer
How to replicate Stata's robust binomial GLM for proportion data in R?
2 votes

You can replicate the UCLA FAQ on proportions (with a percentage as a dependent variable) as follows: require(foreign);require(lmtest);require(sandwich) meals <- read.dta("http://www.ats.ucla.edu/...

View answer
Removing interaction term from repeated measures two-way ANOVA in R: Anova() function in car package
2 votes

While I'm no expert in repeated measures ANOVA, I have some familiarity with the Anova() function in car. Type I or sequential Anova estimates a sequence of models in an effectively arbitrary order, ...

View answer
How to interpret a two-dimensional contingency table?
2 votes

In addition to @gung's answer, I discovered that mosaic plots are very useful in assessing the relative relationships with categorical data. Once we establish (actually, we assume here) departure from ...

View answer
Presenting marginal effects of logit with fixed effects
2 votes

In R the effects package can easily help with interpreting such coefficients by producing the appropriate graphs. From CRAN: effects: Effect Displays for Linear, Generalized Linear, and Other Models ...

View answer
Standard error clustering in R (either manually or in plm)
1 votes

If you don't have a time index, you don't need one: plm will add a fictitious one by itself, and it won't be used unless you ask for it. So this call should work: > x <- plm(price ~ carat, ...

View answer
Type of inference to use with log-linear Poisson glm on contingency table frequency counts
0 votes

The approach recommended in CAR for this type of analysis is to use Anova Type II tests, which conform to the principle of marginality. Fit saturated model: library(COUNT) data(titanic) titanic=...

View answer
Log Linear Models: Interpretation when None Fit
0 votes

Here's the contingency table used in this question: surv.gss <- structure(list(A = c(1L, 1L, 1L, 1L, 0L, 0L, 0L, 0L), E = c(1L, 1L , 0L, 0L, 1L, 1L, 0L, 0L), P = c(1L, 0L, 1L, 0L, 1L, 0L, 1L, 0L)...

View answer