Probability & Statistics Codexery

Sample mean and covariance

Last updated

The sample mean and sample covariance matrix are unbiased estimates of the population mean and covariance matrix for a random vector.[1] They are not robust statistics, meaning outliers can heavily influence them.[2] Robust alternatives include quantile-based statistics like the sample median and interquartile range.[2]

Quick Facts

Field
Statistics

Facts from the source article.

Key facts and history

The sample covariance matrix uses N-1 in the denominator instead of N due to a variant of Bessel's correction.[1] This correction is needed because the sample mean is slightly correlated with each observation, as it is defined from all observations.[1] The sample mean and sample covariance are sensitive to outliers, which is a key criticism in real-world applications.[2] Bart Kosko discussed the sample mean in "The World Question Center 2006".[2]

The GNU Scientific Library reference manual, Version 2.6, describes the elements of the weighted covariance matrix Q.[3] The 2007 book "Applied Multivariate Statistical Analysis" by Pearson Prentice Hall covers the unbiasedness of these estimates.[1][4] That book was published by Prentice Hall on March 23, 2007, with 800 pages.[4]

What the research sources say

The GNU Scientific Library reference manual, Version 2.6, provides formulas for the weighted covariance matrix elements q_{jk}.[3] The Open Library record for ISBN 9780131877153 lists the book "Applied Multivariate Statistical Analysis (6th Edition)" as published by Prentice Hall on March 23, 2007, with 800 pages.[4]

References

  1. Wikipedia, "Sample mean and covariance" (CC BY-SA 4.0), which cites: "Applied Multivariate Statistical Analysis", Pearson Prentice Hall, 2007 (we also read that source) en.wikipedia.org
  2. Wikipedia, "Sample mean and covariance" (CC BY-SA 4.0), which cites: The World Question Center 2006: The Sample Mean , Bart Kosko (original not read by us) en.wikipedia.org
  3. Wikipedia, "Sample mean and covariance" (CC BY-SA 4.0), which cites: Mark Galassi, Jim Davies, James Theiler, Brian Gough, Gerard Jungman, Michael Booth, and Fabrice Rossi. GNU Scientific Library - Reference manual, Version 2.6, (original not read by us) en.wikipedia.org
  4. Open Library record, ISBN 9780131877153 ("Applied Multivariate Statistical Analysis (6th Edition)"). CC0 (metadata); book content not read. openlibrary.org

Each numbered sentence above was checked against the source it cites before publication. Sentences citing Wikipedia adapt text from the English Wikipedia article Sample mean and covariance (contributors), used under CC BY-SA 4.0; this entry is available under the same licence. Other sources were used for facts only; no text or images are copied from them.

More in Probability & Statistics

Sources

Compiled from Wikipedia and the sources listed below. Text from Wikipedia is available under CC BY-SA 4.0; this entry is adapted from it.

Spotted an error? Know more?

Reader corrections go straight into our review queue. Suggest an edit · How this site is sourced

Comments

Loading…
Open in the interactive codex →