Editing Parapsychology (section)

====Psychokinesis on random number generators====
{{Main|Psychokinesis}}
The advent of powerful and inexpensive electronic and computer technologies has allowed the development of fully automated experiments studying possible interactions between [[Mind-body dichotomy|mind and matter]]. In the most common experiment of this type, a [[Random number generation|random number generator]] (RNG), based on electronic or [[radioactive]] noise, produces a data stream that is recorded and analyzed by computer [[software]]. A subject attempts to mentally alter the distribution of the random numbers, usually in an experimental design that is functionally equivalent to getting more "heads" than "tails" while [[flipping a coin]]. In the RNG experiment, design flexibility can be combined with rigorous controls while collecting a large amount of data quickly. This technique has been used both to test individuals for psychokinesis and to test the possible influence on RNGs of large groups of people.<ref name=Dunne85>{{Cite journal|last=Dunne |first=Brenda J. |author2=Jahn, Robert G. |title=On the quantum mechanics of consciousness, with application to anomalous phenomena |journal=Foundations of Physics |volume=16 |issue=8 |pages=721–772 |year=1985 |doi=10.1007/BF00735378|bibcode=1986FoPh...16..721J|s2cid=123188076 }}</ref>

Major meta-analyses of the RNG database have been published every few years since appearing in the journal ''[[Foundations of Physics]]'' in 1986.<ref name="Dunne85"/> PEAR founder [[Robert G. Jahn]] and his colleague Brenda Dunne say that the experiments produced "a very small effect" not significant enough to be observed over a brief experiment but over a large number of trials resulted in a tiny statistical deviation from chance.<ref name="Park 2000"/> According to [[Massimo Pigliucci]], the results from PEAR can be explained without invoking the paranormal because of two problems with the experiment:  "the difficulty of designing machines capable of generating truly random events and the fact that statistical "significance" is not at all a good measure of the importance or genuineness of a phenomenon."<ref name="Pigliucci2010">[[Massimo Pigliucci]]. (2010). ''Nonsense on Stilts: How to Tell Science from Bunk''. University of Chicago Press. pp. 77–80. {{ISBN|978-0226667867}}</ref> Pigluicci has written that the statistical analysis used by the Jahn and the PEAR group relied on a quantity called a "[[p-value]]", but a problem with p-values is that if the sample size (number of trials) is very large, like the PEAR tests, then one is guaranteed to find artificially low p-values indicating a statistically significant result even though nothing was occurring other than small biases in the experimental apparatus.<ref name="Pigliucci2010"/>

Two German independent scientific groups have failed to replicate the PEAR results.<ref name="Pigliucci2010"/> Pigliucci has written this was "yet another indication that the simplest hypothesis is likely to be true: there was nothing to replicate."<ref name="Pigliucci2010"/> The most recent meta-analysis on [[psychokinesis]] was published in ''[[Psychological Bulletin]]'', along with several critical commentaries. It analyzed the results of 380 studies; the authors reported an overall positive effect size that was statistically significant but very small relative to the sample size and could, in principle, be explained by [[publication bias]].<ref name="pmid16822162">{{Cite journal|vauthors=Bösch H, Steinkamp F, Boller E |title=Examining psychokinesis: the interaction of human intention with random number generators – a meta-analysis |journal=Psychological Bulletin |volume=132 |issue=4 |pages=497–523 |year=2006 |pmid=16822162 |doi=10.1037/0033-2909.132.4.497|quote=The study effect sizes were strongly and inversely related to sample size and were extremely heterogeneous. A Monte Carlo simulation showed that the very small effect size relative to the large, heterogenous sample size could in principle be a result of publication bias.}}</ref><ref name="pmid16822164">{{Cite journal|author1=Radin, D. |author2=Nelson, R. |author3=Dobyns, Y. |author4=Houtkooper, J. |title=Reexamining psychokinesis: comment on Bösch, Steinkamp, and Boller |journal=Psychological Bulletin |volume=132 |issue=4 |pages=529–532; discussion 533–537 |year=2006 |pmid=16822164 |doi=10.1037/0033-2909.132.4.529}}</ref><ref>{{cite journal | last1 = Wilson | first1 = David B. | last2 = Shadish | first2 = William R. | year = 2006 | title = On blowing trumpets to the tulips: To prove or not to prove the null hypothesis – Comment on Bösch, Steinkamp, and Boller | journal = Psychological Bulletin | volume = 132 | issue = 4| pages = 524–528 | doi=10.1037/0033-2909.132.4.524| pmid = 16822163 | url = https://zenodo.org/record/996283 }}</ref>