Fr.
  • Member for 10 years, 9 months
  • Last seen more than a month ago
4 answers
37 votes
17k views
Why does logistic regression become unstable when classes are well-separated?
7 votes

What you are calling "separation" (not 'seperation') covers two different situations that end up causing the same issue – which I would not call, however, an issue of "instability" as you do. An ...

View answer
5 answers
44 votes
55k views
What is the significance of logistic regression coefficients?
6 votes

Let me just stress the importance of what rolando2 and dmk38 both noted: significance is commonly misread, and there is a high risk of that happening with that tabular presentation of results. Paul ...

View answer
4 answers
8 votes
4k views
What should I be aware of when using multiple regression to find "causal" relationships in my data?
Accepted answer
5 votes

You cannot "systemically avoid this problem in the future", because it should not be called a "problem". If the reality of the material world features strong covariates, then we should accept it as ...

View answer
4 answers
5 votes
5k views
2x2 chi-square test vs. binomial proportion statistic
4 votes

Shouldn't you favour Fisher's exact test on a 2x2 contingency table? The advantages of the Chi-squared test would be preserved, with the additional advantages of an exact test. Based on a few handbook ...

View answer
1 answers
1 votes
6k views
How to calculate confidence interval of the mean age of a sample?
3 votes

Obtain the five-number summary for your sample. Calculate the standard error for your sample. Select a level of confidence, based on the z-score. Calculate the lower and upper bound of the interval. ...

View answer
1 answers
5 votes
1k views
Visualising generalized linear model
Accepted answer
3 votes

From StatSoft, without links: Diagnostics in the generalized linear model. The two basic types of residuals are the so-called Pearson residuals and deviance residuals. Pearson residuals are based on ...

View answer
8 answers
9 votes
2k views
Resources for learning Stata
3 votes

I have listed some resources on my Stata page. It includes links to the UCLA and Princeton tutorials, as well as a few more resources in several formats. The "Stata Guide" document, which is very much ...

View answer
4 answers
16 votes
16k views
Assumptions of cluster analysis
3 votes

There is a very wide variety of clustering methods, which are exploratory by nature, and I do not think that any of them, whether hierarchical or partition-based, relies on the kind of assumptions ...

View answer
2 answers
8 votes
8k views
How to perform text mining, sentiment mining, and business category identification, and where to obtain a categorization library
2 votes

One solution mentioned by Jeffrey Breen is to use Lu and Hiu's lexicon. He also gives a cool tutorial for sentiment mining on Twitter.

View answer
2 answers
33 votes
31k views
Raw residuals versus standardised residuals versus studentised residuals - what to use when?
2 votes

Re: plots, There is such a thing as overfitting, but overplotting cannot really do much harm, especially at diagnostics stage. A standardized normal probability plot cannot hurt next to your QQ-plot. ...

View answer
2 answers
4 votes
1k views
General advice on forming an index of attitude to the environment from a set of Likert items
2 votes

You need to check how others have built indexes with similar questions. My guess is that Inglehart and Norris, in Rising Tide, have built their Gender Equality/Empowerment index in a way that you can ...

View answer
5 answers
11 votes
3k views
References for how to plan a study
2 votes

Answering with an aphorism, I believe that your study design will be successful as soon as it actually exists in its full-fledged form. The game of reviewing as it is played in academia is primarily a ...

View answer
3 answers
3 votes
448 views
How to assess effect of intervention in one state versus another using annual death rate data?
2 votes

I might have wrongly understood the data (see my comment above), but what would be so wrong in simply t-testing the difference in means of the deaths-to-cases ratios between the two series, assuming ...

View answer
25 answers
103 votes
42k views
Locating freely available data samples
1 votes

Here's a list of quantitative social science data: https://f.briatte.org/teaching/quanti I update it every 3-4 months or so. At the very end, I cite the "Data is Plural" newsletter, which has tons ...

View answer
2 answers
4 votes
470 views
What are the Fundamentals of Applied Statistics?
1 votes

The targeted audience are those with little or no exposure to statistics. My favourite audience! It should also serve as a start for those who are interested in the subject but don't know where to ...

View answer
3 answers
0 votes
78 views
Data sources related to Federal regulation
1 votes

There's an API in development on your topic.

View answer
1 answers
8 votes
316 views
What is the right name for the variant of the Kolmogorov-Smirnov statistic that retains the sign of the difference?
1 votes

It looks like a variant of Kuiper's test to me, although Kuiper's V = D+ + D− ≠ D'.

View answer
3 answers
4 votes
436 views
Simple introduction to linear models in R
0 votes

Hamilton, "Low-Tech Causal Modeling", 2008 Diez et al., "Introduction to linear regression" ch. 11 in OpenIntro Stats, 2nd ed., 2012 Gelman and Hill, ch. 3-4 in Data Analysis Using Regression and ...

View answer
5 answers
6 votes
1k views
Textbook with list of hypothesis tests and practical guidance on use
0 votes

Could this help? The following table shows general guidelines for choosing a statistical analysis. We emphasize that these are general guidelines and should not be construed as hard and fast rules. ...

View answer
2 answers
5 votes
34k views
Advantages and disadvantages of parametric and non-parametric models
0 votes

The question is too vague as such, but any answer will depend on your object of study (example). You will find tons on the topic over at Andrew Gelman's blog, with an April's Fool somewhere in the ...

View answer
2 answers
1 votes
2k views
How to perform a regression model with a mix of binary, nominal, ordinal, and continuous predictors?
0 votes

As the comments suggest, it is only by fully understanding and specifying your research design that you will establish what regression method best corresponds to your data. In the case where your DV ...

View answer