{"id":246,"date":"2011-08-31T10:15:10","date_gmt":"2011-08-31T14:15:10","guid":{"rendered":"http:\/\/www.reliabilityanalytics.com\/blog\/?p=246"},"modified":"2012-09-21T09:46:56","modified_gmt":"2012-09-21T13:46:56","slug":"gamma-distribution","status":"publish","type":"post","link":"https:\/\/reliabilityanalytics.com\/blog\/2011\/08\/31\/gamma-distribution\/","title":{"rendered":"Gamma Distribution"},"content":{"rendered":"<p>The gamma distribution is used in reliability analysis for cases where partial failures can exist, i.e., when a given number of partial failures must occur before an item fails (e.g., redundant systems) or the time to second failure when the time to failure is exponentially distributed. The failure density function is<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_f_of_t.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-247\" title=\"gamma_f_of_t\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_f_of_t.png\" alt=\"\" width=\"269\" height=\"61\" \/><\/a><\/p>\n<p>for t&gt;0<\/p>\n<p><!--more-->where<\/p>\n<p>mean = \u03bc = \u03b1\/\u03bb<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_sd.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-248\" title=\"gamma_sd\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_sd.png\" alt=\"\" width=\"288\" height=\"74\" \/><\/a><\/p>\n<p>\u03bb is the failure rate (complete failure) and a the number of partial failures for complete failure or events to generate a failure. \u0393(\u03b1) is the gamma function<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/tau_gamma_function.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-249\" title=\"tau_gamma_function\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/tau_gamma_function.png\" alt=\"\" width=\"237\" height=\"65\" \/><\/a><\/p>\n<p>which can be evaluated by means of standard tables. When \u03b1 &#8211; 1 is a positive integer, \u0393(\u03b1) = (\u03b1 &#8211; 1)!, which is usually the case for most reliability analysis, e.g., partial failure situation. For this case the failure density function is<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_f_of_t_partial_failure_case.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-250\" title=\"gamma_f_of_t_partial_failure_case\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_f_of_t_partial_failure_case.png\" alt=\"\" width=\"306\" height=\"60\" srcset=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_f_of_t_partial_failure_case.png 306w, https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_f_of_t_partial_failure_case-300x58.png 300w\" sizes=\"auto, (max-width: 306px) 100vw, 306px\" \/><\/a><\/p>\n<p>which, for the case of \u03b1 = 1 becomes the exponential <a title=\"Exponential Distribution\" href=\"https:\/\/reliabilityanalytics.com\/blog\/2011\/08\/30\/exponential-distribution\/\">density function<\/a>.<\/p>\n<p>The gamma distribution can also be used to describe an increasing or decreasing hazard (failure) rate. When \u03b1 &gt;1, h(t) increases; when \u03b1 &lt;1, h (t) decreases, as shown below, plotted in time multiples of standard deviation (SD) .<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_distribution_hazard_rate_plot1.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-254\" title=\"gamma_distribution_hazard_rate_plot\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_distribution_hazard_rate_plot1.png\" alt=\"\" width=\"376\" height=\"276\" srcset=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_distribution_hazard_rate_plot1.png 376w, https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_distribution_hazard_rate_plot1-300x220.png 300w\" sizes=\"auto, (max-width: 376px) 100vw, 376px\" \/><\/a><\/p>\n<p>&nbsp;<\/p>\n<p><strong><strong>Example Calculation<\/strong><\/strong><\/p>\n<p>An antiaircraft missile system has demonstrated a gamma failure distribution with \u03b1 = 3 and \u03bb= 0.05. Determine the reliability for a 24 hour mission time and the hazard rate at the end of 24 hours.<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_r_of_t_example.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-255\" title=\"gamma_r_of_t_example\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_r_of_t_example.png\" alt=\"\" width=\"297\" height=\"65\" \/><\/a><\/p>\n<p>Ordinarily, special tables of the Incomplete Gamma Function are required to evaluate the above integral. However, it can be shown that if \u03b1 is an integer<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_r_of_t_example_alpha_is_integer.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-256\" title=\"gamma_r_of_t_example_alpha_is_integer\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_r_of_t_example_alpha_is_integer.png\" alt=\"\" width=\"194\" height=\"83\" \/><\/a><\/p>\n<p>which is the Poisson distribution. Using this equation<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_r_of_t_example_alpha_is_integer2.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-257\" title=\"gamma_r_of_t_example_alpha_is_integer2\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_r_of_t_example_alpha_is_integer2.png\" alt=\"\" width=\"363\" height=\"83\" srcset=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_r_of_t_example_alpha_is_integer2.png 363w, https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_r_of_t_example_alpha_is_integer2-300x68.png 300w\" sizes=\"auto, (max-width: 363px) 100vw, 363px\" \/><\/a><\/p>\n<p>R(24) = 0.301 +0.362 +0.216 =0.88<\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/h_of_t31.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-258\" title=\"h_of_t3\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/h_of_t31.png\" alt=\"\" width=\"120\" height=\"56\" \/><\/a><\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_f_of_t_partial_failure_case.png\"><img loading=\"lazy\" decoding=\"async\" title=\"gamma_f_of_t_partial_failure_case\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_f_of_t_partial_failure_case.png\" alt=\"\" width=\"306\" height=\"60\" \/><\/a><\/p>\n<p><a href=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_h_of_t_example1.png\"><img loading=\"lazy\" decoding=\"async\" class=\"alignnone size-full wp-image-260\" title=\"gamma_h_of_t_example\" src=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_h_of_t_example1.png\" alt=\"\" width=\"492\" height=\"60\" srcset=\"https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_h_of_t_example1.png 492w, https:\/\/reliabilityanalytics.com\/blog\/wp-content\/uploads\/2011\/08\/gamma_h_of_t_example1-300x36.png 300w\" sizes=\"auto, (max-width: 492px) 100vw, 492px\" \/><\/a><\/p>\n<p>&nbsp;<\/p>\n<p>References:<\/p>\n<p style=\"padding-left: 30px;\">1. MIL-HDBK-338, <a href=\"https:\/\/assist.daps.dla.mil\/quicksearch\/basic_profile.cfm?ident_number=54022\">Electronic Reliability Design Handbook<\/a>, 15 Oct 84<br \/>\n2. Bazovsky, Igor, <a href=\"http:\/\/www.amazon.com\/gp\/product\/0486438678?ie=UTF8&amp;tag=reliabilityan-20&amp;linkCode=as2&amp;camp=1789&amp;creative=9325&amp;creativeASIN=0486438678\">Reliability Theory and Practice<\/a><br \/>\n3. O\u2019Connor, Patrick, D. T., <a href=\"http:\/\/www.amazon.com\/gp\/product\/0470844620?ie=UTF8&amp;tag=reliabilityan-20&amp;linkCode=as2&amp;camp=1789&amp;creative=9325&amp;creativeASIN=0470844620\">Practical Reliability Engineering<\/a><br \/>\n4. Birolini, Alessandro, <a href=\"http:\/\/www.amazon.com\/gp\/product\/3540493883?ie=UTF8&amp;tag=reliabilityan-20&amp;linkCode=as2&amp;camp=1789&amp;creative=9325&amp;creativeASIN=3540493883\">Reliability Engineering: Theory and Practice<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p>The gamma distribution is used in reliability analysis for cases where partial failures can exist, i.e., when a given number of partial failures must occur before an item fails (e.g., redundant systems) or the time to second failure when the &hellip; <a href=\"https:\/\/reliabilityanalytics.com\/blog\/2011\/08\/31\/gamma-distribution\/\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[47],"tags":[48],"class_list":["post-246","post","type-post","status-publish","format-standard","hentry","category-gamma","tag-gamma-distrinution"],"_links":{"self":[{"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/posts\/246","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/comments?post=246"}],"version-history":[{"count":11,"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/posts\/246\/revisions"}],"predecessor-version":[{"id":731,"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/posts\/246\/revisions\/731"}],"wp:attachment":[{"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/media?parent=246"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/categories?post=246"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/reliabilityanalytics.com\/blog\/wp-json\/wp\/v2\/tags?post=246"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}