Explaining XKCD and PhD Comics for Data Evaluation
* Explaining the joke!
Do you know why these are funny?
At the end of the class you should be able to explain the basis for the jokes!
Phdcomics/xkcd:
* The difference (scientist) https://m.xkcd.com/242/
* Convincing (label axes) https://m.xkcd.com/833/
* The actual method http://www.phdcomics.com/comics/archive.php?comicid=761
* Correlation https://m.xkcd.com/552/
* Cancer causes cellphones https://m.xkcd.com/925/
* Blind Trials https://m.xkcd.com/1462/
* Experimentation Lesbian Control Group B https://m.xkcd.com/507/
* Fasters Growing https://m.xkcd.com/1102/
* Decline Graphing Coincidence https://m.xkcd.com/523/
* Linear Regression https://m.xkcd.com/1725/
* Null Hypothesis https://m.xkcd.com/892/
* p-Values https://m.xkcd.com/1478/
* Significance jelly beans https://m.xkcd.com/882/
* Statistically significant boyfriend https://m.xkcd.com/539/
* ANOVA Analysis of Value http://www.phdcomics.com/comics/archive.php?comicid=905
* Frequentist vs. Bayesian https://m.xkcd.com/1132/
* Science Valentine https://m.xkcd.com/701/
* What have you done / used in terms of statistics for research? What for exactly?
* Statistical/quantitative evaluation terms:
* Measurements, variables, random samples and errors
* Independent observations
* Representative observations
* Distributions of observation (normal distribution)
* Average and mean
* Variance and standard deviation
* Standard error of the mean
* Effect size
* Degrees of freedom
* Confidence interval
* Covariance (relative independence of measurement error for derived quantities)
* hypothesis testing
* null hypothesis
* t-test
* ANOVA, ANCOVA
* Regression analysis, model calibration, data fitting, curve fitting
* Priors, prior probability, Bayesian estimates
* Transparent statistics in HCI