Zoran Skoda misinterpreting statistics

• Measurement error and bias, Ch. 4 of Epidemiology for the uninitiated, link

• selection bias, measurement error, information bias

• validity analysis: sensitivity (a high proportion of the true cases), specificity (having few false positives), systematic error, predictive value (the proportion of positive test results that are truly positive)

• repeatability

Predictive value Selection bias is “a type of bias caused by choosing non-random data for statistical analysis” (investopedia).

• Selection bias, overviews in sciencedirect, link

“Selection bias is defined as a nonrandom imbalance among treatment groups of the distribution of factors capable of influencing the end points—that is, of subexperimental factors (including prognostic factors).”

From: Handbook of Pharmacogenomics and Stratified Medicine, 2014

Subgroups of (sample) selection bias: referral bias, self-selection bias, prevalence bias, protopathic bias, cherry picking

• rationalwiki/selection bias

• rationalwiki/confirmation bias

• rationalwiki/list of cognitive biases

• Eliezer Yudkowsky, Cognitive biases potentially affecting judgment of global risks, in: Global Catastrophic Risks (edited by N. Bostrom & M. M. Ćirković) 91–119 pdf

• Cochrane hbk, 8.4 Introduction to sources of bias in clinical trials, htm

Performance bias.

Detection bias.

Withdrawals: attrition bias (unavailable data from withdrawn subjects) versus exclusions (dataavailable but excluded)

Publication (reporting) bias…

L.K. Alexander et al. Selection bias, pdf

• John P. A. Ioannidis, Why most published research findings are false, PLOS, August 30, 2005, doi