joe.fis...@tanguaylab.com, Michael Black, Marc L. Allen, and Simon Slavin, Our software architect defined data streakedness based upon Chauvenet's criterion. Thank you for all of your help.
In statistical theory, *Chauvenet's criterion* (named for William Chauvenet<http://en.wikipedia.org/wiki/William_Chauvenet> [1] <http://en.wikipedia.org/wiki/Chauvenet%27s_criterion#cite_note-1>) is a means of assessing whether one piece of experimental data — an outlier<http://en.wikipedia.org/wiki/Outlier>— from a set of observations, is likely to be spurious. To apply Chauvenet's criterion, first calculate the mean<http://en.wikipedia.org/wiki/Mean>and standard deviation <http://en.wikipedia.org/wiki/Standard_deviation> of the observed data. Based on how much the suspect datum differs from the mean, use the normal distribution <http://en.wikipedia.org/wiki/Normal_distribution> function (or a table thereof) to determine the probability<http://en.wikipedia.org/wiki/Probability>that a given data point will be at the value of the suspect data point. Multiply this probability by the number of data points taken. If the result is less than 0.5, the suspicious data point may be discarded, i.e., a reading may be rejected if the probability of obtaining the particular deviation from the mean is less than 1/(2*n*). On Tue, Feb 19, 2013 at 11:05 AM, Frank Chang <frankchan...@gmail.com>wrote: > joe.fis...@tanguaylab.com, Michael Black, Marc. L Allen and Simon > Slavin, Thank you for your help in helping me to convince our company's > software architect that it is possible to calculate the streakedness of > numeric data. _______________________________________________ sqlite-users mailing list sqlite-users@sqlite.org http://sqlite.org:8080/cgi-bin/mailman/listinfo/sqlite-users
