8 votes

Is most of Kahneman's 'Thinking fast and slow' not supported by evidence/non replicable?

This is complicated. There's no easy answer, but the outlook for replicability/reproducibility of a lot of the empirical evidence is not great. The R-index (that the blog authors use to rank the ...
pep's user avatar
  • 569
7 votes

Can I use data taken in a 5-point Likert Scale, and convert it as if it were taken as a 4-point Likert?

In general, from my extensive experience, using a four or a five point response scale is not going to change much the psychometric properties of a typical psychological self-report scale (e.g., ...
Jeromy Anglim's user avatar
7 votes

What is the rationale for the normal distribution of intelligence?

Short answer IQ scores are distributed normally, because they follow the central limit theorem. Background When we measure IQ scores in sufficiently large populations, they will be normally ...
AliceD's user avatar
  • 20.6k
5 votes
Accepted

What variables allow one to empirically and scientifically quantify trends for learning curves?

Short answer In psychophysical tests, often %correct rates are determined. Hence, training effects are often measured by determining correct rates. The ultimate outcome measures can be wildly variable,...
AliceD's user avatar
  • 20.6k
5 votes
Accepted

Should I look at the data of an experiment before the dataset is complete?

Short answer From an ethical standpoint, not including interim evaluations may be bad practice. Background I will start off with a more extreme case than in your question example, just for ...
AliceD's user avatar
  • 20.6k
5 votes

Should I look at the data of an experiment before the dataset is complete?

gjacob is correct that optional stopping is a common research degree of freedom, and one that has a considerable and unfortunate intuitive basis. Yet, depending on the context of your research, AliceD'...
jsakaluk's user avatar
  • 286
5 votes
Accepted

What are the benefits of using all 30 personality facets in multiple regressions compared to just including hypothesised facets?

I wrote a paper that focuses on this question (Anglim & Grant, 2014; pre-print is https://osf.io/g8kbj/download). In short, if you're interested in estimating how well facets predict an outcome, ...
Jeromy Anglim's user avatar
5 votes
Accepted

Recommended resources (journals, blogs, etc) for nurturing a background of statistical/methodological rigour in behavioural science research?

There are various loosely-defined 'camps' among reform-minded methodologists, so you probably want to try to follow a representative of each. Andrew Gelman is a prominent landmark in this area, and ...
steveLangsford's user avatar
5 votes
Accepted

Recent Peer Review Studies on How Many Have Narcissistic Personality Disorder

While not a peer-reviewed study per se, but the DSM-5 says that the prevalence of Narcissistic Personality Disorder in the population is 6.2%, or approximately one out of sixteen members of the ...
Tyler Mc's user avatar
  • 280
4 votes

Why so few subjects in psychophysics?

It is partly as you already guessed, because the phenomena that are studied don't vary as much between individuals. This doesn't necessarily mean that individual differences in perception are smaller, ...
Ana's user avatar
  • 2,553
4 votes

in R : How to check RT's for ex-gaussian fit with the fitdistrplus package

To answer the question relating to start values for the parameters for use with fitdist: I would like to check for an ex-gaussian distribution fit (GAMLSS ...
Glen_b's user avatar
  • 141
4 votes
Accepted

How do scientists/psychologists deal with conflicting experiment results?

Meta-analysis is the statistical practice of combining results across studies in a principled way. Meta-analyses weight the relative strength of evidence from different studies to generate an overall ...
Bryan Krause's user avatar
  • 7,376
3 votes
Accepted

in R : How to check RT's for ex-gaussian fit with the fitdistrplus package

I did a quick google and found the mesgauss function in the retimes package. I give a simple example of estimatinat ex-gaussian ...
Jeromy Anglim's user avatar
3 votes

Which is a better statistical option to compare differences across groups?

If you have single-trial data, the drift-diffusion model/DDM and related models, originating with Roger Ratcliff (1976/1978), can simultaneously fit the whole response distribution, both RTs and ...
jona's user avatar
  • 2,414
3 votes
Accepted

In SPSS, should you change the significance level for One way ANOVA post-hocs?

Leave it at 0.05 . SPSS corrects it properly. Only when you want to test with different alpha's (.10 or 0.01 e.g.) you should change it.
Robin Kramer-ten Have's user avatar
3 votes

In a forced-choice task, what proportion of responses is above chance level?

This is a binomial distribution and the answer depends on the total number of Type A and B questions as well as what confidence level you want to use for the cutoff. There is probably a formula for ...
K A's user avatar
  • 981
3 votes

What tools are available for EEG analysis on the R platform?

For the sake of completeness: eegkit, see https://cran.r-project.org/web/packages/eegkit/index.html For "historical purposes" perhaps the following could also be of interest, although development ...
Tiberius's user avatar
  • 131
3 votes

What tools are available for EEG analysis on the R platform?

I was searching for alternative when I fell on this post. Here are a few others eegUtils , the same author has a blog that might be of interest to you for further reading here I also found eegAnalysis ...
Patrick's user avatar
  • 151
3 votes

How should results from linear mixed models (LMMs) be reported?

As an update, this paper may be helpful, though it comes from the medical field. References Monsalves, M.J., Bangdiwala, A.S., Thabane, A. et al. LEVEL (Logical Explanations & Visualizations of ...
NewMoonPalace's user avatar
3 votes
Accepted

How to efficiently use a statistical consultant?

This is a challenging question. As a bit of background, I am a cognitive scientist for the most part (by my highest graduate degree), but in addition to that, I have graduate degrees in both math and ...
Doctorambient's user avatar
3 votes

Examples of interventions that yield large long term effect sizes in psychology

Skill acquisition: If you take a novice on a task and get them to practice that task, performance will tend to improve. See the Power Law of Practice. In many cases that I've seen, the difference ...
Jeromy Anglim's user avatar
3 votes

Should I look at the data of an experiment before the dataset is complete?

This is an important question! This practice ("optional stopping" if you stop collecting data based on your early analyses, or "peeking" if you continue collecting data) is considered a bad idea ...
qjacob's user avatar
  • 328
3 votes

What does it mean statistically for there to be significant differences in average IQ scores between racial groups?

Statistical significance in this context is determined by: the underlying size of the group differences, the group sample sizes, and your threshold for statistical significance (traditionally .05). ...
Jeromy Anglim's user avatar
3 votes
Accepted

In fMRI analyses, what is the t-test actually comparing?

The coefficient is the measure of how strongly the given factor predicts the dependent variable, or in other words how much of the variance in the dependent variable can be explained by that factor. ...
Henry Brice's user avatar
3 votes

How to statistically test whether parents and children share similar humor styles?

Assuming the data are dyadic (i.e., one child per parent), you would probably focus on correlating child scores with parent scores. Hopefully, you have a sense of how the child and parent scales ...
Jeromy Anglim's user avatar
3 votes
Accepted

Which experimental design is this? Factorial vs within groups

Let us see first what it is not: Not a within subjects design. To be an within subjects experiment, you need a repeated measure, something that you would test for each individual multiple times. E.g.:...
OMan's user avatar
  • 409
3 votes
Accepted

Questions on Interpreting Factor Analysis Results and Scores

Is my approach in generating a distribution based on the samples' factor scores flawed? How do they do it in practice? I found this somewhat difficult to follow. But in general, you should be able to ...
Jeromy Anglim's user avatar
3 votes

Do .sav files expire after the trial version expires?

The only difference between trial software and the 'real' thing is that trial software looses some or all functions after the trial period. Any files generated with it will be kept and be functional; ...
AliceD's user avatar
  • 20.6k
3 votes

If a two-tailed test shows significance and the mean is higher, can you infer that one condition is significantly higher?

Yes. A two-tailed test simply corrects for the appropriate probability of observing a difference as large as you observe given the null hypothesis is true. This probability is twice the one-tailed ...
Bryan Krause's user avatar
  • 7,376
3 votes
Accepted

Why does IQ have a truncated normal distribution?

IQ isn't normal, it's normalized to have mean 100 and standard deviation 15, usually via a percentile method. The reason IQ looks roughly normal is because intelligence (however it is defined) is a ...
Bryan Krause's user avatar
  • 7,376

Only top scored, non community-wiki answers of a minimum length are eligible