[{"data":1,"prerenderedAt":702},["ShallowReactive",2],{"header":3,"footer":321,"glossary-term-sample-ratio-mismatch":661},{"id":4,"createdAt":5,"updatedAt":6,"publishedAt":7,"documentId":8,"buttons":9,"menuItems":23},11,"2022-04-07T11:47:09.609Z","2026-06-03T07:55:53.674Z","2026-06-03T07:55:53.993Z","iv73rrw06i0bjkp9ep6ydw4g",[10,18],{"id":11,"text":12,"color":13,"size":14,"rounded":15,"href":16,"landingPage":17},3994,"Log in","transparent","small",true,"https://app.personizely.net/login",null,{"id":19,"text":20,"color":21,"size":14,"rounded":15,"href":22,"landingPage":17},3995,"Try for free","blue","https://app.personizely.net/register",[24,138,241,256],{"id":25,"text":26,"title":26,"description":27,"button":17,"link":17,"children":28},48,"Product","All the tools you need to make your website convert better.",[29,65,90,115],{"id":30,"text":31,"description":32,"icon":33,"link":45},153,"A/B Testing","Run tests to optimize your store for higher conversions",{"id":34,"name":35,"alternativeText":17,"caption":17,"width":25,"height":25,"formats":17,"hash":36,"ext":37,"mime":38,"size":39,"url":40,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":42,"updatedAt":42,"documentId":43,"publishedAt":44},1084,"a:b testing icon.svg","a_b_testing_icon_a3626cb094",".svg","image/svg+xml",3.18,"/uploads/a_b_testing_icon_a3626cb094.svg","local","2024-11-19T14:47:53.677Z","bm0hfsrxrp6edfry28ybhd8n","2025-02-11T12:58:54.859Z",{"id":46,"text":31,"href":47,"landingPage":48},1131,"/",{"id":49,"slug":50,"title":31,"metaTitle":51,"metaDescription":52,"createdAt":53,"updatedAt":54,"publishedAt":55,"noindex":56,"layout":17,"documentId":57,"category":58},552,"ab-testing","A/B Testing Made Easy with Personizely","Discover how Personizely's A/B testing helps drive growth with data-driven changes. Customize your website and boost conversions with precise testing insights.","2024-11-14T10:25:26.541Z","2025-10-16T14:38:57.158Z","2025-10-16T14:39:01.070Z",false,"a3a3s8oytaomnheyp5zru182",{"id":59,"name":26,"slug":60,"createdAt":61,"updatedAt":62,"publishedAt":63,"documentId":64},3,"product","2022-04-12T16:34:02.373Z","2022-11-18T19:29:47.123Z","2022-04-13T00:51:43.368Z","vw04bsngj9ojpwvqz5cq1zne",{"id":66,"text":67,"description":68,"icon":69,"link":77},154,"Website Personalization","Create unique experiences with website personalization",{"id":70,"name":71,"alternativeText":71,"caption":71,"width":17,"height":17,"formats":17,"hash":72,"ext":37,"mime":38,"size":73,"url":74,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":75,"updatedAt":75,"documentId":76,"publishedAt":44},92,"personalization.svg","personalization_73d769313b",0.59,"/uploads/personalization_73d769313b.svg","2022-05-12T11:02:57.715Z","v1gpscxwrhoh3tksx8kr0d23",{"id":78,"text":79,"href":47,"landingPage":80},1132,"Personalization",{"id":81,"slug":82,"title":67,"metaTitle":83,"metaDescription":84,"createdAt":85,"updatedAt":86,"publishedAt":87,"noindex":17,"layout":17,"documentId":88,"category":89},570,"website-personalization","The best practices for your website personalization strategy","Personalize your website to create customer journeys that will convert visitors and get you the best sales. Make it personal with website personalization. ","2022-04-14T14:05:07.624Z","2025-10-21T06:22:46.195Z","2025-10-21T06:22:47.470Z","ns07ikj1fef5gidz18hbavwf",{"id":59,"name":26,"slug":60,"createdAt":61,"updatedAt":62,"publishedAt":63,"documentId":64},{"id":91,"text":92,"description":93,"icon":94,"link":102},155,"Widgets","Create any kind of widgets to drive conversions and sales",{"id":95,"name":96,"alternativeText":96,"caption":96,"width":17,"height":17,"formats":17,"hash":97,"ext":37,"mime":38,"size":98,"url":99,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":100,"updatedAt":100,"documentId":101,"publishedAt":44},91,"widgets.svg","widgets_ef79dfe1ac",0.39,"/uploads/widgets_ef79dfe1ac.svg","2022-05-12T11:02:08.438Z","sv14xds0ow4fn1pajxrdf7uc",{"id":103,"text":92,"href":47,"landingPage":104},1133,{"id":105,"slug":106,"title":107,"metaTitle":108,"metaDescription":109,"createdAt":110,"updatedAt":111,"publishedAt":112,"noindex":56,"layout":17,"documentId":113,"category":114},575,"website-widgets","Website Widgets","Website Widgets | Personizely","There is nothing better than increasing profits with less effort. Let Personizely help you create the best widgets for your website without HTML or coding.","2022-04-12T21:49:58.039Z","2025-10-21T16:45:53.095Z","2025-10-21T16:45:54.330Z","nq4mztyzs1x22dy2qemz3hbw",{"id":59,"name":26,"slug":60,"createdAt":61,"updatedAt":62,"publishedAt":63,"documentId":64},{"id":116,"text":117,"description":118,"icon":119,"link":127},156,"Integrations","Connect Personizely into your marketing activities and flows",{"id":120,"name":121,"alternativeText":121,"caption":121,"width":17,"height":17,"formats":17,"hash":122,"ext":37,"mime":38,"size":123,"url":124,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":125,"updatedAt":125,"documentId":126,"publishedAt":44},90,"integrations.svg","integrations_3d7ba01c69",1.81,"/uploads/integrations_3d7ba01c69.svg","2022-05-12T11:00:57.559Z","t9yw02tch43uhe3zi4ykk9ct",{"id":128,"text":117,"href":47,"landingPage":129},1134,{"id":130,"slug":131,"title":117,"metaTitle":132,"metaDescription":133,"createdAt":134,"updatedAt":135,"publishedAt":136,"noindex":17,"layout":17,"documentId":137,"category":17},492,"integrations","Personizely offers you integrations that will enhance your efficiency","Take full advantage of the integrations offered by Personizely. Create a workflow that will enhance your productivity and marketing strategy.","2022-04-11T10:19:34.888Z","2025-06-18T06:01:46.188Z","2025-06-18T06:01:46.800Z","gjd8qtuxgbm429v1gwn4i8g0",{"id":139,"text":140,"title":140,"description":141,"button":17,"link":17,"children":142},49,"Partners","Explore our partner programs, find the one that's right for you, and let's start growing better together.",[143,167,192,217],{"id":144,"text":145,"description":146,"icon":147,"link":155},157,"Become a Partner","Unlock new and profitable growth opportunities for your agency",{"id":148,"name":149,"alternativeText":17,"caption":17,"width":25,"height":25,"formats":17,"hash":150,"ext":37,"mime":38,"size":151,"url":152,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":153,"updatedAt":153,"documentId":154,"publishedAt":44},910,"become a partner.svg","become_a_partner_634fc1b581",17.03,"/uploads/become_a_partner_634fc1b581.svg","2023-08-17T05:01:34.904Z","r6g5nnezp7ghu5sbycxtoue8",{"id":156,"text":145,"href":47,"landingPage":157},1135,{"id":158,"slug":159,"title":160,"metaTitle":161,"metaDescription":162,"createdAt":163,"updatedAt":164,"publishedAt":165,"noindex":56,"layout":17,"documentId":166,"category":17},680,"partner-program","Personizely Partner Program","The Partner Program you were looking for","Discover the Personizely Program and start earning today. There has never been a better time and will take you seconds to get started.","2023-07-31T14:13:11.968Z","2026-01-27T18:28:41.989Z","2026-01-27T18:28:42.805Z","geqd8yxbcjhhbdbh55se37d6",{"id":168,"text":169,"description":170,"icon":171,"link":179},158,"Partner Directory","Connect with Personizely agency partners  to achieve your growth goals",{"id":172,"name":173,"alternativeText":17,"caption":17,"width":25,"height":25,"formats":17,"hash":174,"ext":37,"mime":38,"size":175,"url":176,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":177,"updatedAt":177,"documentId":178,"publishedAt":44},909,"find a partner.svg","find_a_partner_2c23d5e8f7",1.01,"/uploads/find_a_partner_2c23d5e8f7.svg","2023-08-17T05:01:34.878Z","iuctcog1y3e7jv447nldbvnw",{"id":180,"text":181,"href":47,"landingPage":182},1136,"Find a Partner",{"id":183,"slug":184,"title":185,"metaTitle":186,"metaDescription":187,"createdAt":188,"updatedAt":189,"publishedAt":190,"noindex":17,"layout":17,"documentId":191,"category":17},108,"partner-directory","Find the right Personizely Service Partner","Personizely Partner Directory","Need expert help? We know the right people. Hire one of our industry-leading partners and reach your goals faster.","2023-08-07T05:34:56.600Z","2024-09-21T07:45:42.755Z","2023-08-08T07:49:07.661Z","s5ooxljmt1sk2q5znf21wvo0",{"id":193,"text":194,"description":195,"icon":196,"link":205},159,"Become a Personizely Affiliate","Grow your revenue with the Personizely affiliate program",{"id":197,"name":198,"alternativeText":17,"caption":17,"width":25,"height":25,"formats":17,"hash":199,"ext":37,"mime":38,"size":200,"url":201,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":202,"updatedAt":203,"documentId":204,"publishedAt":44},908,"become an Personizely affiliate.svg","become_an_Personizely_affiliate_c04f540f92",0.58,"/uploads/become_an_Personizely_affiliate_c04f540f92.svg","2023-08-17T05:01:34.875Z","2023-08-17T05:03:04.937Z","y9tr69ypv6suvc8ndw9opmn9",{"id":206,"text":194,"href":47,"landingPage":207},1137,{"id":208,"slug":209,"title":210,"metaTitle":211,"metaDescription":212,"createdAt":213,"updatedAt":214,"publishedAt":215,"noindex":17,"layout":17,"documentId":216,"category":17},634,"affiliate","Personizely Affiliate Program","The Affiliate Program you were looking for","Discover the Personizely Affiliate Program, and start earning today. There has never been a better time and will take you seconds to get started.","2022-04-14T14:02:18.692Z","2025-12-24T15:47:58.132Z","2025-12-24T15:47:58.947Z","qj23jx3ltidj2hja0nl71zoe",{"id":218,"text":219,"description":220,"icon":221,"link":230},160,"White Label","Expand your services and grow revenue with a fully branded CRO platform",{"id":222,"name":223,"alternativeText":17,"caption":17,"width":25,"height":25,"formats":17,"hash":224,"ext":37,"mime":38,"size":225,"url":226,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":227,"updatedAt":227,"documentId":228,"publishedAt":229},1928,"white-label.svg","white_label_44b6f1cd7c",2.18,"/uploads/white_label_44b6f1cd7c.svg","2025-09-16T05:53:51.020Z","m8y9qjmiiw1vl9mlmnknmnze","2025-09-16T05:53:51.023Z",{"id":231,"text":219,"href":47,"landingPage":232},1138,{"id":233,"slug":234,"title":219,"metaTitle":235,"metaDescription":236,"createdAt":237,"updatedAt":238,"publishedAt":239,"noindex":15,"layout":17,"documentId":240,"category":17},533,"white-label","White Label CRO Platform – Rebrand Personizely as Your Own","Resell Personizely’s A/B testing, personalization, and conversion tools under your own brand. Full control over logos, domains, pricing & client journey.","2025-09-11T04:52:39.698Z","2025-09-16T05:46:57.989Z","2025-09-16T05:47:01.572Z","hg00idtrkc7awcd7kmqhuh9c",{"id":242,"text":243,"title":17,"description":17,"button":17,"link":244,"children":255},47,"Pricing",{"id":245,"text":17,"href":47,"landingPage":246},1130,{"id":247,"slug":248,"title":243,"metaTitle":249,"metaDescription":250,"createdAt":251,"updatedAt":252,"publishedAt":253,"noindex":17,"layout":17,"documentId":254,"category":17},704,"pricing","Choose the right Personizely pricing plan for your needs","Personizely offers you flexible pricing options that will help you get ahead in no time. Jump on your free trial today and see what it can do for you!","2022-04-07T17:05:40.544Z","2026-04-06T20:37:41.149Z","2026-04-06T20:37:42.855Z","ex3ubodxo1ny87cqve886dlq",[],{"id":257,"text":258,"title":258,"description":259,"button":17,"link":17,"children":260},50,"Resources","Unlock the power of Personizely with in-depth insights, step-by-step guides, and case studies.",[261,284,307],{"id":262,"text":263,"description":264,"icon":265,"link":273},161,"Blog","Learn how to grow your online business with proven use cases",{"id":266,"name":267,"alternativeText":17,"caption":17,"width":25,"height":25,"formats":17,"hash":268,"ext":37,"mime":38,"size":269,"url":270,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":271,"updatedAt":271,"documentId":272,"publishedAt":44},943,"thumb.svg","thumb_df1b68ce15",0.6,"/uploads/thumb_df1b68ce15.svg","2023-10-10T14:16:29.017Z","a62m09w7iit37oqvi5l6tqh5",{"id":274,"text":263,"href":47,"landingPage":275},1139,{"id":276,"slug":277,"title":263,"metaTitle":278,"metaDescription":279,"createdAt":280,"updatedAt":281,"publishedAt":282,"noindex":17,"layout":17,"documentId":283,"category":17},2,"blog","Read articles and news about the most efficient marketing techniques","Find the best tips and tricks that will help you get the most out of Personizely, as well as your marketing strategy. The only advice you’ll ever need.","2022-04-07T14:08:39.475Z","2022-11-18T19:29:52.172Z","2022-04-07T17:13:10.278Z","nb89p215wcn04e2nkcxq25br",{"id":285,"text":286,"description":287,"icon":288,"link":296},162,"Case Studies","Discover how brands like yours use Personizely to succeed",{"id":289,"name":290,"alternativeText":17,"caption":17,"width":25,"height":25,"formats":17,"hash":291,"ext":37,"mime":38,"size":292,"url":293,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":294,"updatedAt":294,"documentId":295,"publishedAt":44},944,"thumb (1).svg","thumb_1_5e1cfa1751",1.33,"/uploads/thumb_1_5e1cfa1751.svg","2023-10-10T14:16:29.025Z","x94kep610bpkhzprn775rgz0",{"id":297,"text":17,"href":47,"landingPage":298},1140,{"id":299,"slug":300,"title":286,"metaTitle":301,"metaDescription":302,"createdAt":303,"updatedAt":304,"publishedAt":305,"noindex":17,"layout":17,"documentId":306,"category":17},110,"case-studies","Boosting Conversions and Sales: Success Stories with Personizely","See how other e-commerce brands are using Personizely to increase conversions, boost sales\u2028& get more out of their website traffic.","2023-10-09T09:02:11.031Z","2024-05-10T16:52:33.175Z","2023-10-09T09:04:08.051Z","umiosgcfpd7e3m2szvwdfswz",{"id":308,"text":309,"description":310,"icon":311,"link":318},152,"Help Desk","Need help using Personizely? Check out our step-by-step product tutorials",{"id":312,"name":313,"alternativeText":17,"caption":17,"width":25,"height":25,"formats":17,"hash":314,"ext":37,"mime":38,"size":292,"url":315,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":316,"updatedAt":316,"documentId":317,"publishedAt":44},942,"thumb (3).svg","thumb_3_b6f594ef6f","/uploads/thumb_3_b6f594ef6f.svg","2023-10-10T14:16:29.010Z","fubhvnkojooqofwf4ega6ee8",{"id":319,"text":309,"href":320,"landingPage":17},1141,"https://help.personizely.net",{"id":322,"documentId":323,"copyright":324,"logo":325,"button":334,"columns":338},23,"ugsmjgizm7r525nprbbp7s00","© 2026 Personizely. All rights reserved.",{"id":276,"name":326,"alternativeText":327,"caption":327,"width":17,"height":17,"formats":17,"hash":328,"ext":37,"mime":38,"size":329,"url":330,"previewUrl":17,"provider":41,"provider_metadata":17,"createdAt":331,"updatedAt":332,"documentId":333,"publishedAt":44},"logo","Personizely","logo_White_375703099a_badb5bf557",5.75,"/uploads/logo_White_375703099a_badb5bf557.svg","2022-04-07T11:47:57.758Z","2022-11-16T18:24:35.093Z","qpwu4agm23y6u2lcekau4f7i",{"id":335,"text":336,"color":13,"size":337,"rounded":15,"href":17,"landingPage":17},4426,"Go to top","large",[339,358,407,563,612],{"id":340,"title":26,"links":341},97,[342,346,351,355],{"id":343,"text":31,"href":47,"landingPage":344},1179,{"id":49,"slug":50,"title":31,"metaTitle":51,"metaDescription":52,"createdAt":53,"updatedAt":54,"publishedAt":55,"noindex":56,"layout":17,"documentId":57,"category":345},{"id":59,"name":26,"slug":60,"createdAt":61,"updatedAt":62,"publishedAt":63,"documentId":64},{"id":347,"text":348,"href":47,"landingPage":349},1180,"Website personalization",{"id":81,"slug":82,"title":67,"metaTitle":83,"metaDescription":84,"createdAt":85,"updatedAt":86,"publishedAt":87,"noindex":17,"layout":17,"documentId":88,"category":350},{"id":59,"name":26,"slug":60,"createdAt":61,"updatedAt":62,"publishedAt":63,"documentId":64},{"id":352,"text":92,"href":47,"landingPage":353},1181,{"id":105,"slug":106,"title":107,"metaTitle":108,"metaDescription":109,"createdAt":110,"updatedAt":111,"publishedAt":112,"noindex":56,"layout":17,"documentId":113,"category":354},{"id":59,"name":26,"slug":60,"createdAt":61,"updatedAt":62,"publishedAt":63,"documentId":64},{"id":356,"text":117,"href":47,"landingPage":357},1182,{"id":130,"slug":131,"title":117,"metaTitle":132,"metaDescription":133,"createdAt":134,"updatedAt":135,"publishedAt":136,"noindex":17,"layout":17,"documentId":137,"category":17},{"id":359,"title":360,"links":361},98,"Free tools",[362,381,394],{"id":363,"text":364,"href":17,"landingPage":365},1183,"Product pricing calculator",{"id":366,"slug":367,"title":368,"metaTitle":368,"metaDescription":369,"createdAt":370,"updatedAt":371,"publishedAt":372,"noindex":56,"layout":17,"documentId":373,"category":374},627,"product-pricing-calculator","Free Product Pricing Calculator Tool","Free product pricing calculator to estimate unit cost, retail price, and profit fast. Adjust supplies, labor, and markup instantly.","2025-11-21T17:39:37.407Z","2025-12-10T16:47:33.079Z","2025-12-10T16:47:33.723Z","tvkemyw4qnvcolucnukqp94z",{"id":375,"name":376,"slug":377,"createdAt":378,"updatedAt":378,"publishedAt":379,"documentId":380},19,"Tools","tools","2025-11-21T15:57:40.990Z","2025-11-21T15:57:41.018Z","rb1970leqihe0hegzxrqyp43",{"id":382,"text":383,"href":47,"landingPage":384},1184,"Sample size calculator",{"id":385,"slug":386,"title":387,"metaTitle":387,"metaDescription":388,"createdAt":389,"updatedAt":390,"publishedAt":391,"noindex":56,"layout":17,"documentId":392,"category":393},674,"sample-size-calculator","Sample size calculator tool for A/B tests (Free)","Free sample size calculator for A/B tests. Calculate how many visitors you need to run statistically valid experiments.","2025-11-21T15:58:04.106Z","2026-01-20T08:16:17.688Z","2026-01-20T08:16:18.438Z","bk88a8r6pz34bqvvqsi399hn",{"id":375,"name":376,"slug":377,"createdAt":378,"updatedAt":378,"publishedAt":379,"documentId":380},{"id":395,"text":396,"href":47,"landingPage":397},1185,"Hypothesis generator",{"id":398,"slug":399,"title":400,"metaTitle":400,"metaDescription":401,"createdAt":402,"updatedAt":403,"publishedAt":404,"noindex":56,"layout":17,"documentId":405,"category":406},689,"hypothesis-generator","Free AI Hypothesis Generator for A/B Testing","Free Hypothesis Generator for CRO and A/B testing. Turn insights into structured, test-ready hypotheses fast.","2026-02-16T16:25:31.897Z","2026-02-24T13:45:25.178Z","2026-02-24T13:45:25.948Z","hhy0tiban42dernibl8mukwr",{"id":375,"name":376,"slug":377,"createdAt":378,"updatedAt":378,"publishedAt":379,"documentId":380},{"id":408,"title":409,"links":410},99,"Compare",[411,431,445,458,471,485,498,511,524,537,550],{"id":412,"text":413,"href":47,"landingPage":414},1186,"Intelligems",{"id":415,"slug":416,"title":417,"metaTitle":417,"metaDescription":418,"createdAt":419,"updatedAt":420,"publishedAt":421,"noindex":17,"layout":17,"documentId":422,"category":423},705,"intelligems-alternative","Meet Personizely. The Best Alternative to Intelligems","Looking for a flexible, easy-to-use Intelligems alternative? See how Personizely stacks up in our side-by-side Personizely vs Intelligems comparison.","2025-04-17T14:04:33.931Z","2026-06-03T08:58:34.866Z","2026-06-03T08:58:51.930Z","nkri5meu2aquw4de5pibebk1",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},5,"Competitor","compare","2022-10-31T12:38:56.277Z","2022-12-01T15:22:19.360Z","2022-10-31T14:38:56.602Z","dx08fjr7xf0ntnm821vf1y1d",{"id":432,"text":433,"href":47,"landingPage":434},1187,"Visually",{"id":435,"slug":436,"title":437,"metaTitle":438,"metaDescription":439,"createdAt":440,"updatedAt":441,"publishedAt":442,"noindex":17,"layout":17,"documentId":443,"category":444},464,"visually-alternative","Visually Alternative","Visually Alternative - Visually vs Personizely Comparison","Check out this Visually vs Personizely comparison and discover why Personizely is the best Visually alternative for CRO, testing, and personalization.","2025-04-22T08:17:51.809Z","2025-04-25T13:38:02.883Z","2025-04-25T13:38:03.537Z","we51nga7m527d73ci9hfv2bo",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":446,"text":447,"href":47,"landingPage":448},1188,"Shoplift",{"id":449,"slug":450,"title":451,"metaTitle":451,"metaDescription":452,"createdAt":453,"updatedAt":454,"publishedAt":455,"noindex":56,"layout":17,"documentId":456,"category":457},706,"shoplift-alternative","Meet Personizely. The Best Alternative to Shoplift","Need a powerful Shoplift alternative? Explore this Shoplift vs Personizely comparison to see why Personizely is a smarter solution for your growth.","2025-04-22T09:31:24.856Z","2026-06-03T08:59:20.061Z","2026-06-03T08:59:29.835Z","hibs570wlq31rrrmp21taq4c",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":459,"text":460,"href":47,"landingPage":461},1189,"Optimizely",{"id":462,"slug":463,"title":464,"metaTitle":464,"metaDescription":465,"createdAt":466,"updatedAt":467,"publishedAt":468,"noindex":17,"layout":17,"documentId":469,"category":470},472,"optimizely-alternative","Optimizely Alternative - Optimizely vs Personizely Comparison","Looking for a more modern, affordable Optimizely alternative? See the detailed Optimizely vs Personizely comparison to help you choose the best tool.","2025-04-22T17:56:14.632Z","2025-04-30T17:16:43.223Z","2025-04-30T17:16:43.764Z","njgcw2ht78qnmpatkar6n68q",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":472,"text":473,"href":47,"landingPage":474},1190,"VWO",{"id":475,"slug":476,"title":477,"metaTitle":478,"metaDescription":479,"createdAt":480,"updatedAt":481,"publishedAt":482,"noindex":15,"layout":17,"documentId":483,"category":484},577,"vwo-alternative","VWO Alternative","VWO Alternative - VWO vs Personizely Comparison","Looking for a more affordable VWO alternative? Find a detailed VWO vs Personizely comparison and scale your business with an all-in-one CRO platform.","2025-04-22T13:02:52.294Z","2025-11-05T09:39:16.124Z","2025-11-05T09:39:16.986Z","erju4d138nimucxtezift63k",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":486,"text":487,"href":47,"landingPage":488},1191,"Dynamic Yield",{"id":489,"slug":490,"title":491,"metaTitle":491,"metaDescription":492,"createdAt":493,"updatedAt":494,"publishedAt":495,"noindex":17,"layout":17,"documentId":496,"category":497},471,"dynamicyield-alternative","Dynamic Yield Alternative - Dynamic Yield vs Personizely","Want a Dynamic Yield alternative without the enterprise-level price tag? Check this Dynamic Yield vs Personizely comparison to find the best tool.","2025-04-22T17:52:12.862Z","2025-04-30T15:44:01.668Z","2025-04-30T15:44:02.284Z","l6q42yvaz5d06s1zq80pwkrn",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":499,"text":500,"href":47,"landingPage":501},1192,"Kameleoon",{"id":502,"slug":503,"title":504,"metaTitle":504,"metaDescription":505,"createdAt":506,"updatedAt":507,"publishedAt":508,"noindex":17,"layout":17,"documentId":509,"category":510},475,"kameleoon-alternative","Kameleoon Alternative - Kameleoon vs Personizely Comparison","Kameleoon’s steep pricing got you looking for a Kameleoon alternative? Check this Kameleoon vs Personizely comparison for more information.","2025-04-22T18:06:39.283Z","2025-04-30T17:47:18.729Z","2025-04-30T17:47:19.304Z","lfks4hjzmtncxhbwkk5hvgzt",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":512,"text":513,"href":47,"landingPage":514},1193,"AB Tasty",{"id":515,"slug":516,"title":517,"metaTitle":517,"metaDescription":518,"createdAt":519,"updatedAt":520,"publishedAt":521,"noindex":17,"layout":17,"documentId":522,"category":523},473,"abtasty-alternative","AB Tasty Alternative - AB Tasty vs Personizely Comparison","Looking for AB Tasty alternatives that work for both SMBs and enterprises? See this AB Tasty vs Personizely comparison to find the right tool for you.","2025-04-22T17:59:23.383Z","2025-04-30T17:29:30.712Z","2025-04-30T17:29:31.318Z","bi9p6p0jjv16l218khgqzkl5",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":525,"text":526,"href":47,"landingPage":527},1194,"Nosto",{"id":528,"slug":529,"title":530,"metaTitle":530,"metaDescription":531,"createdAt":532,"updatedAt":533,"publishedAt":534,"noindex":17,"layout":17,"documentId":535,"category":536},474,"nosto-alternative","Nosto Alternative - Nosto vs Personizely Comparison","Limited features got you looking for a Nosto alternative? Check out this Nosto vs Personizely comparison to choose the best tool for your business.","2025-04-22T18:02:32.262Z","2025-04-30T17:39:30.956Z","2025-04-30T17:39:32.219Z","u6u1z41o2tcw3noj7t9e48iy",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":538,"text":539,"href":47,"landingPage":540},1195,"Convert",{"id":541,"slug":542,"title":543,"metaTitle":543,"metaDescription":544,"createdAt":545,"updatedAt":546,"publishedAt":547,"noindex":17,"layout":17,"documentId":548,"category":549},470,"convert-alternative","Convert Alternative - Convert vs Personizely Comparison","Exploring Convert alternatives? This Personizely vs Convert comparison will help you make a smarter, data-driven choice for your next CRO platform.","2025-04-22T17:43:27.820Z","2025-04-30T15:32:54.126Z","2025-04-30T15:32:54.705Z","x9wj12fk0chu0yglgof2vl4z",{"id":424,"name":425,"slug":426,"createdAt":427,"updatedAt":428,"publishedAt":429,"documentId":430},{"id":551,"text":552,"href":47,"landingPage":553},1196,"Compare all",{"id":554,"slug":555,"title":556,"metaTitle":557,"metaDescription":558,"createdAt":559,"updatedAt":560,"publishedAt":561,"noindex":17,"layout":17,"documentId":562,"category":17},709,"competitors","Competitors","Compare Personizely to other competitors on the market","Learn about the differences and similarities between Personizely and our competitors. You want to find the best option, and we are here to help.","2022-05-18T07:34:25.996Z","2026-06-04T08:18:27.152Z","2026-06-04T08:18:27.941Z","idj2bckkchsl639mp2phlhan",{"id":564,"title":565,"links":566},100,"Company",[567,580,584,587,590,594,598],{"id":568,"text":569,"href":47,"landingPage":570},1197,"About us",{"id":571,"slug":572,"title":573,"metaTitle":574,"metaDescription":575,"createdAt":576,"updatedAt":577,"publishedAt":578,"noindex":17,"layout":17,"documentId":579,"category":17},1,"about-us","About Us","Get a closer look at Personizely, and the motivation behind it","Get to know Personizely better, your new favorite marketing tool that will become indispensable in your arsenal after just a couple of days.","2022-04-06T20:32:34.570Z","2024-11-18T11:34:52.756Z","2022-04-07T16:17:19.029Z","pues4sdwvfc6zecqfeg4w7px",{"id":581,"text":582,"href":47,"landingPage":583},1198,"Affiliate program",{"id":208,"slug":209,"title":210,"metaTitle":211,"metaDescription":212,"createdAt":213,"updatedAt":214,"publishedAt":215,"noindex":17,"layout":17,"documentId":216,"category":17},{"id":585,"text":243,"href":47,"landingPage":586},1199,{"id":247,"slug":248,"title":243,"metaTitle":249,"metaDescription":250,"createdAt":251,"updatedAt":252,"publishedAt":253,"noindex":17,"layout":17,"documentId":254,"category":17},{"id":588,"text":263,"href":47,"landingPage":589},1200,{"id":276,"slug":277,"title":263,"metaTitle":278,"metaDescription":279,"createdAt":280,"updatedAt":281,"publishedAt":282,"noindex":17,"layout":17,"documentId":283,"category":17},{"id":591,"text":592,"href":593,"landingPage":17},1201,"Glossary","/glossary",{"id":595,"text":596,"href":597,"landingPage":17},1202,"Helpdesk","https://help.personizely.net/",{"id":599,"text":600,"href":17,"landingPage":601},1203,"Book a demo",{"id":602,"slug":603,"title":604,"metaTitle":605,"metaDescription":606,"createdAt":607,"updatedAt":608,"publishedAt":609,"noindex":56,"layout":610,"documentId":611,"category":17},717,"demo","Book a Demo","Tell us what you want to achieve with Personizely and we’ll show you how. ","Discover how Personizely can be tailored to your goals. Share your aspirations with us, and we'll demonstrate the most effective ways to leverage our platform to meet and exceed your objectives.","2024-04-02T11:22:32.618Z","2026-06-10T13:43:06.241Z","2026-06-10T13:43:06.844Z","clean","x7xl76hlj15n76acjtw2enet",{"id":613,"title":614,"links":615},101,"Legal",[616,635,648],{"id":617,"text":618,"href":47,"landingPage":619},1204,"Terms",{"id":620,"slug":621,"title":622,"metaTitle":623,"metaDescription":624,"createdAt":625,"updatedAt":626,"publishedAt":627,"noindex":17,"layout":17,"documentId":628,"category":629},467,"terms-and-conditions","Terms and conditions","There are always rules, and Personizely makes sure you know them","Read all the terms and conditions to get a better understanding of Personizely and our rules. Make sure you agree with everything you are signing.","2022-04-07T17:27:21.407Z","2025-04-29T08:50:16.315Z","2025-04-29T08:50:17.306Z","cfvwni995gv7ez5tj5iwka5f",{"id":571,"name":614,"slug":630,"createdAt":631,"updatedAt":632,"publishedAt":633,"documentId":634},"legal","2022-04-07T17:26:34.379Z","2022-11-18T19:29:47.090Z","2022-04-07T20:33:44.712Z","nxfazq39bqk9j15d00lq4l0w",{"id":636,"text":637,"href":47,"landingPage":638},1205,"Privacy",{"id":424,"slug":639,"title":640,"metaTitle":641,"metaDescription":642,"createdAt":643,"updatedAt":644,"publishedAt":645,"noindex":17,"layout":17,"documentId":646,"category":647},"privacy-policy","Privacy Policy","Read about our Privacy Policy for a better understanding of it","Personizely cares about your privacy, and here you can read about how we protect it. Always make sure you read the fine print, and protect your data.","2022-04-07T23:05:25.113Z","2022-11-18T19:29:52.341Z","2022-04-08T02:05:26.071Z","yf7w0wmuw8bern81q4419ij7",{"id":571,"name":614,"slug":630,"createdAt":631,"updatedAt":632,"publishedAt":633,"documentId":634},{"id":649,"text":650,"href":47,"landingPage":651},1206,"GDPR",{"id":652,"slug":653,"title":650,"metaTitle":654,"metaDescription":655,"createdAt":656,"updatedAt":657,"publishedAt":658,"noindex":17,"layout":17,"documentId":659,"category":660},775,"gdpr","Read about the General Data Protection Regulations at Personizely","Find everything you need to know about the Personizely GDPR regulations and how personal data is processed and used within the EU.","2022-04-14T14:08:04.700Z","2026-07-13T09:15:19.498Z","2026-07-13T09:15:19.975Z","t8l37a0ypr6ew1azjkbf3lv7",{"id":571,"name":614,"slug":630,"createdAt":631,"updatedAt":632,"publishedAt":633,"documentId":634},{"id":489,"documentId":662,"slug":663,"title":664,"excerpt":665,"noindex":56,"date":666,"metaTitle":664,"metaDescription":667,"createdAt":668,"updatedAt":669,"publishedAt":670,"term":671,"sections":672},"f0smbj3cff4qxz2qhivru9y2","sample-ratio-mismatch","What Is Sample Ratio Mismatch? Meaning & Examples","SRM happens when traffic isn't distributed as expected across variants, making your test results unreliable.","2026-07-21T21:00:00.000Z","Sample ratio mismatch means your test groups aren't split the way you intended. Learn why this invalidates results and how to catch it before it's too late.","2026-07-17T07:34:32.144Z","2026-07-22T13:11:37.937Z","2026-07-22T13:11:37.985Z","Sample Ratio Mismatch",[673,677],{"__component":674,"id":675,"title":664,"content":676},"post.section",3820,"Sample ratio mismatch is a statistically significant discrepancy between the expected and observed sizes of experiment groups. In other words, sample ratio mismatch occurs when user allocation deviates from expected ratios. You set up treatment and control groups with a defined traffic distribution, say 50/50, and the actual count of users assigned to each variant drifts far from that target.\n\nTo build intuition, think of a fair coin. Flip it 100 times, and you might see 52 heads and 48 tails. That is normal variation. But if you flip it 1,000 times and see 700 heads, something is clearly off with the coin. The same logic applies when you randomly assign users in an experiment.\n\nHere is a concrete numeric example. You launch a test with a planned 50/50 split and 100,000 total users. You expect roughly 50,000 in each group. Instead, you observe 63,000 in control and 37,000 in treatment. That gap is far too large for random sampling noise, and it triggers an SRM alarm.\n\nThe term sample ratio mismatch SRM is widely used in the context of [online controlled experiments](https://www.microsoft.com/en-us/research/articles/diagnosing-sample-ratio-mismatch-in-a-b-testing/), feature tests, and marketing experiments. Whether you are testing a new checkout page layout or a pricing change, the principle is the same: if SRM occurs when user assignment deviates from the expected ratio, the experiment has a problem worth investigating.\n\n![Diagram comparing an expected 50/50 split between control and treatment groups with an observed 51/49 split, illustrating a sample ratio mismatch.](https://www.personizely.net/strapi/uploads/Expected_vs_Observed_Ratio_in_Sample_Ratio_Mismatch_85eddf8082.png)\n\n## Why sample ratio mismatch matters\n\nRandom assignment is the foundation of trustworthy A/B testing. Statistical tests assume random assignment to groups, and when that assumption breaks, every downstream metric becomes suspect. Sample ratio mismatch (SRM) can lead to misleading conclusions in A/B testing results, and in the worst cases, it can cause the entire experiment to produce invalid results.\n\nWhen an SRM issue surfaces, it usually signals selection bias, where certain types of users are more likely to end up in one group than another. This means the groups are no longer comparable, and the apparent treatment effect may actually be due to differences in who saw each variant, not the effect of the treatment itself. SRM indicates potential biases in user assignment or data processing that have nothing to do with the treatment being tested.\n\nConsider a common scenario: you run an experiment on a checkout page to test a new design intended to increase revenue. Due to a targeting bug, a disproportionate share of high-value mobile users is routed into the treatment group. As a result, revenue metrics spike in the treatment group. However, this lift is not caused by the new design but by the uneven distribution of users. Without detecting SRM, your team may mistakenly believe the new design is effective and roll it out to all users, only to find no real improvement in revenue.\n\nThe impact of SRM is significant and widespread in the industry. Research from Microsoft shows that about 6 percent of A/B tests experience SRM, while LinkedIn reports rates near 10 percent for more complex experiments. This prevalence highlights the importance of routinely checking for SRM to maintain experiment integrity. Experiments affected by SRM tend to show twice as many statistically significant metrics compared to clean experiments. This inflation of false positives means that SRM not only undermines trust in individual tests but can also distort the overall experimentation program by promoting false discoveries.\n\nEven small allocation differences can have outsized effects. For example, a 1 percent deviation from the intended sample ratio can distort key metrics by as much as 2 percent. When experiments are run at scale across many teams and products, these small inaccuracies compound, leading to widespread incorrect conclusions about what works and what does not.\n\nSRM also complicates the interpretation of experiment results because it violates the assumption that treatment and control groups are comparable. This comparability is essential for causal inference. If the groups differ systematically in characteristics like device type, geography, or user behavior, then any observed differences in outcomes may reflect these underlying differences rather than the effect of the tested change. For example, if more engaged users disproportionately fall into one group, that group may appear to perform better regardless of the treatment.\n\nAnother consequence of SRM is that it reduces the statistical power of the experiment. When group sizes deviate from the planned ratio, the effective sample size for detecting true effects is reduced. This reduction can increase the likelihood of type II errors, where a real effect goes undetected. Conversely, SRM can inflate false positive rates by introducing bias that mimics a treatment effect.\n\nSRM can also lead to wasted resources and lost time. Experiments affected by SRM often need to be stopped and restarted after the root cause is identified and fixed. This delay slows down the product development cycle and reduces the overall velocity of experimentation. Teams may also lose confidence in the experimentation platform if SRM issues occur frequently, undermining the culture of data-driven decision-making.\n\nDetecting SRM early is crucial to minimize its impact. Automated monitoring tools that track the allocation ratios and alert experimenters when deviations exceed thresholds help prevent prolonged exposure to biased data. These tools enable quick investigation and remediation, preserving the integrity of ongoing tests.\n\nIn addition to detection, understanding the root causes of SRM is vital. Common causes include bugs in randomization code, inconsistent user identifiers, targeting errors that exclude users unevenly, and data logging issues such as dropped events or delayed ingestion. Each cause requires a different approach to resolution, emphasizing the need for thorough diagnostics.\n\nFinally, SRM awareness encourages better experiment design and implementation practices. Teams that prioritize avoiding SRM invest in robust randomization libraries, consistent user ID management, and comprehensive logging pipelines. They also establish clear protocols for monitoring and responding to allocation imbalances, which collectively improve the quality and reliability of their experimentation efforts.\n\n## How sample ratio mismatch works\n\nEvery experiment starts with an intended allocation rule. For example, \"assign each new user to control or treatment with 50 percent probability.\" This defines the expected sample ratio. In a correctly implemented test, the realized counts fluctuate around this rule, but those deviations should be consistent with chance variation for the given sample size.\n\nSRM detection compares observed group sizes with expected sizes under the planned sample ratio and evaluates whether the difference is unusually large. The evaluation uses statistical methods that quantify how surprising the observed split would be if randomization were working perfectly.\n\nThis comparison must happen at the level at which randomization happens. If your platform randomizes at the user level, SRM detection should count unique users, not sessions or page views. If you use sessions as the unit of analysis when users are the randomization unit, behavioral differences between variants (like one variant encouraging more users to return) can create an apparent imbalance that is not actually a randomization failure.\n\nMost mature experimentation platforms automate SRM detection. The system runs checks repeatedly while the test is live, catching problems within hours rather than only at the end. However, SRM does not tell you which group is \"right\" or what the true treatment effect is. It only flags that something about randomization or data collection is likely broken.\n\nDiagnosing sample ratio mismatch is a two step process: first detect that an SRM exists, then investigate the root cause.\n\n### Detection\n\nDetection relies on the chi squared test, which is the most commonly used approach. Chi-square tests are commonly used to identify SRM issues, and a chi-squared goodness-of-fit test can detect SRM reliably across a range of sample sizes. You compute expected counts per variant (total users times the planned allocation proportion), compare them to the observed counts, and calculate the test statistic. Chi-squared tests can identify sample ratio mismatch (SRM) by producing an SRM p value that tells you the probability of seeing a mismatch at least as extreme under correct randomization.\n\nAn SRM check fails if groups are not split 50/50 as intended (or whatever your target ratio is) and the resulting p value is below your threshold. An SRM p value below 0.01 indicates unbalanced exposures, and a p value below 0.01 is the threshold many platforms use, though some organizations choose 0.001 or even 0.0005 to further reduce false positives.\n\nWhen a very low p value appears, for instance 10 to the power of negative 10, it is overwhelmingly unlikely that the mismatch is random.\n\n### Investigation\n\nAfter confirming SRM, investigation begins by plotting traffic counts over time to identify when the mismatch started. Tying the onset to a specific code deploy, the experiment's start date, or a configuration change helps quickly identify the source.\n\nNext, analyze segments by slicing aggregated data across platform, country, browser type, logged in status, or traffic source to localize where the imbalance is strongest.\n\nAlso compare triggered versus untriggered users for experiments that require a specific trigger, such as viewing a widget or reaching a certain page. If the trigger logic is variant sensitive, it can produce missing users in one group.\n\nYou can also apply permutation tests to validate the chi squared result on smaller data sets, or use [Bayesian A/B testing](https://www.personizely.net/glossary/bayesian-ab-testing) methods for an alternative perspective on the mismatch probability.\n\nRatio mismatch can originate at several layers of the experiment stack. Here is a catalog of the most frequent root causes.\n\nAssignment stage issues include bugs in the randomization code, incorrect bucketing logic, or two different systems assigning users with inconsistent rules, all of which can skew the split. SRM can occur due to incorrect user assignment in experiments when the treatment assignment mechanism is flawed. Incorrect bucketing can lead to sample ratio mismatch even when the hashing function appears correct at first glance.\n\nUser identifier problems such as user ID corruption undermine consistent group assignment. Cookie resets, shared devices in households, anonymous versus logged in state transitions, or duplicate IDs merging total traffic incorrectly are common culprits.\n\nTargeting and eligibility errors happen when filters exclude some users from one variant after assignment, or feature flags are applied only to a subset of devices, creating an uneven distribution. If your test targets specific user segments but the targeting interacts with the variant code, one group may silently lose participants.\n\nExecution problems include redirect loops, page load failures, or app crashes that happen more often in one variant preventing exposures from being recorded. This creates a set of missing users in the affected group. Uneven rollout timing can also cause sample ratio mismatch if one variant launches hours before the other.\n\nLogging and data pipeline issues arise from tracking and logging failures. Dropped events from a particular platform, delayed data ingestion through stream processing systems, or aggressive bot filtering that removes more users from one group are all potential sources. Data processing errors can lead to sample ratio mismatch downstream, even when the assignment itself was clean.\n\nAnalysis stage errors include applying different filters to control groups and treatment groups, resetting the experiment's start date without resetting counts, or analyzing only users who completed a trigger influenced by the treatment, all of which can create the illusion of a ratio mismatch.\n\nThe best approach is to map potential causes to specific experiment components: assignment, exposure, logging, and analysis. This systematic framework, similar to knowledge discovery in data mining, helps narrow down the root cause efficiently.\n\nImagine you launch an A/B test with an intended 50/50 split. After three days, your dashboard shows 55 percent of users in treatment and 45 percent in control. That visual check is your first signal.\n\nFor a formal check, pull the unique user counts per variant from your experiment dashboard. Compute expected counts based on the planned allocation proportion. Run the chi squared test and compute the SRM p value. If the p value is below your threshold, you have a confirmed SRM. Spreadsheet tools can compute this directly using built in chi squared formulas, making this accessible for anyone, not just a data scientist.\n\nChecks should always be performed on unique users assigned to each variant, not on sessions or page views, when the randomization unit is the user. Otherwise, performance differences between variants that change visit frequency could create a false alarm.\n\nMature experimentation platforms often run SRM checks automatically. For instance, Statsig automatically checks for SRM in every experiment, flagging exposures as balanced or unbalanced. These low latency checks process each exposure event batch so that problems are caught within hours. Real-time dashboards help monitor experiment exposures effectively, and monitoring tools can alert users to potential SRM issues in real time, catching problems that manual inspection would miss.\n\nPlotting the SRM p value over time is especially useful. If the mismatch appeared only after a specific deployment, that timestamp becomes a strong lead for the investigation. Pair this view with user dashboards that show diagnostic tools like segment level breakdowns, and you can troubleshoot experiments much faster.\n\n## Examples of sample ratio mismatch\n\nHere are a few concrete scenarios that illustrate different failure modes.\n\n### Marketing traffic exclusion\n\nA paid campaign sends visitors to your site with a specific URL parameter. A code bug strips that parameter for one variant, and the experimentation platform fails to log those visitors. The result: a 60/40 observed split instead of 50/50, with more users appearing in control. A team trying to improve weekly revenue from that campaign would draw incorrect conclusions about the treatment's performance.\n\n### Performance regression\n\nThe treatment variant introduces heavier JavaScript that slows page load time. Some visitors abandon the page before the experiment exposure event fires. The underlying data shows many fewer logged treatment users, producing a severe ratio mismatch. The experiment results appear to show that the treatment has lower conversion, but the real story is that the slowest loading visitors never got counted at all.\n\n### Mid test bot detection change\n\nPartway through the experiment, the engineering team updates bot detection rules. The new rules remove more high frequency users from the control group than from treatment. This creates an SRM and simultaneously biases revenue metrics upward for control, because the remaining control users happen to be higher value. Without diagnosing sample ratio mismatch, the team might conclude that the treatment hurt revenue.\n\n### Hidden segment imbalance\n\nThe overall split appears close to 50/50, but slicing by device reveals a strong imbalance among tablet users. If tablets represent a strategically important user segment, perhaps one with higher average order value, this localized SRM still distorts experiment results even though the top level numbers look fine.\n\n### Uneven rollout timing\n\nIf one variant of the experiment is rolled out earlier than the other, users exposed during the earlier period can cause an imbalance. For example, if the control group is live for several hours before the treatment launches, the total user counts will skew toward control. This timing mismatch can create a sample ratio mismatch that falsely signals an issue with randomization, when in fact it is a deployment sequencing problem.\n\n### User ID inconsistencies\n\nInconsistent or corrupted user identifiers can cause users to be assigned to different groups across sessions or devices. For instance, if a user's ID changes due to cookie resets or login status changes, the experiment platform might count them multiple times or misassign them, leading to an SRM. Ensuring stable and consistent user IDs is critical for accurate group assignment and reliable experiment results.\n\nIn each of these cases, naive interpretation of data points without SRM awareness would produce incorrect conclusions about treatment performance.\n\n![Four-step timeline for checking sample randomization, from starting with a sample and choosing a split ratio to randomly assigning users and running a sample ratio mismatch (SRM) check.](https://www.personizely.net/strapi/uploads/How_to_Check_if_Your_Sample_Is_Randomized_Correctly_a9d86c39e0.png)\n\n## Best practices to prevent and handle SRM\n\n### Standardize randomization logic\n\nStandardize randomization logic in a single service or library. When the assignment code is duplicated across multiple applications, inconsistencies creep in. A centralized assignment stage reduces this risk by ensuring all experiments use the same reliable method for user allocation, minimizing discrepancies that can cause sample ratio mismatch.\n\n### Run dry run or shadow tests\n\nRun dry run or shadow tests where variants are hidden but assignment and logging are exercised. This allows you to check that the sample ratio remains correct against historical data and expected counts before real launches. These tests help catch issues early in a controlled environment, preventing SRM from occurring in live experiments.\n\n### Routinely verify traffic allocations\n\nExperimenters should routinely verify traffic allocations against designed ratios. Set up monitoring on exposure counts, SRM p-value, and related health metrics with alerts that trigger when p-values cross your chosen threshold. Real-time alerting can help prevent SRM in A/B tests by catching problems before they contaminate weeks of data. DoorDash saw a 70 percent drop in SRM incidents after implementing systematic monitoring, demonstrating the practical value of this approach.\n\n### Document root causes and build checklists\n\nDocument typical root causes and build a checklist for knowledge management. When SRM appears, engineers and analysts should have a repeatable investigation process rather than starting from scratch each time. This organized approach speeds up diagnosis and resolution, reducing downtime and improving experiment reliability.\n\n### Pause or stop experiments with confirmed SRM\n\nPause or stop experiments with confirmed SRM. Ideally, restart them after the underlying implementation issue is resolved and data collection begins fresh. Continuing experiments with unresolved SRM risks invalid conclusions and wasted resources.\n\n### Cautiously apply advanced techniques to salvage insights\n\nWhile there are advanced techniques to salvage some insights from SRM-affected tests, such as restricting analysis to unaffected segments or applying weighted regression to adjust for the imbalance, these should be used cautiously and clearly labeled as exploratory. They are not substitutes for fixing the root cause, but can provide preliminary guidance when restarting is not immediately possible.\n\n## Key metrics for understanding SRM\n\nHere is a concise list of quantitative signals to watch when monitoring for sample ratio mismatch.\n\n| Metric                                                                        | Purpose                                                                                                |\n|-------------------------------------------------------------------------------|--------------------------------------------------------------------------------------------------------|\n| Observed allocation ratio per variant                                         | Primary signal; shows the percentage of users in each group over time                                  |\n| SRM p value (chi squared test)                                                | Central statistical indicator of whether the mismatch is likely due to random chance or a real problem |\n| Total unique users exposed per variant                                        | Helps detect missing exposure or logging problems when one group has an unexpectedly small sample size |\n| Segment level SRM metrics (platform, browser type, country, new vs returning) | Catches localized imbalances that the global ratio might mask                                          |\n| Error rate, page load time, crash rate                                        | Spikes in these correlate with telemetry loss that causes SRM                                          |\n\nReal-time dashboards help monitor these metrics continuously. Tracking them at both the global and segment level, using real-time analytics where possible, lets you detect SRM before it accumulates enough biased data to affect decisions.\n\n## Sample ratio mismatch and related concepts\n\nSRM sits within a broader ecosystem of experimentation and statistical concepts. Understanding the connections helps put SRM detection in context.\n\nSRM is often a visible symptom of selection bias. When certain user attributes make it more likely for someone to appear in one variant, the resulting data no longer supports causal claims. The concept parallels survivorship bias: during World War II, analysts at Columbia University studied returning bombers and initially proposed armoring the areas with the most bullet holes. Abraham Wald realized they should focus on the missing planes, the ones that did not return, because estimating plane vulnerability based only on surviving aircraft ignored the most critical damage zones. Similarly, when users go missing from one experiment group, the observed data tells an incomplete story.\n\nSRM p values relate to standard hypothesis testing concepts like [confidence level](https://personizely.net/glossary/confidence-level) and statistical significance. However, the SRM p value measures assignment balance, not treatment effect. These are distinct questions.\n\nSRM checks complement other diagnostics like power analysis, minimum detectable effect planning, guardrail metrics, and counterfactual logging. Research published through venues like the international conference on knowledge discovery and through Cambridge University Press has explored how regression modeling helps identify imbalances in treatment assignments and how orthogonal effects between overlapping experiments can cause or mask SRM.\n\nSRM detection also connects to [canary testing](https://personizely.net/glossary/canary-testing) and feature flag rollouts, because the same randomization and logging issues that cause SRM in experiments can affect gradual releases. Think of SRM detection as a mandatory precondition before trusting any effect size or uplift estimate from an A/B test.\n\n## Key takeaways\n\n* Sample ratio mismatch occurs when observed group sizes in an experiment deviate from the planned sample ratio more than random variation can reasonably explain.\n\n* SRM is strong evidence of selection bias or an implementation issue in assignment, logging, or analysis, and it undermines experimental integrity.\n\n* The standard way to detect SRM is to run a chi squared test and monitor the resulting SRM p value over time, ideally with automated alerts.\n\n* Preventing SRM through robust randomization, consistent identifiers, careful targeting, and reliable data pipelines saves significant time and avoids misleading experiment results.\n\n* Every mature experimentation program should treat SRM checks as a built in safeguard before drawing conclusions from test data.",{"__component":678,"id":679,"title":680,"items":681},"post.faq",828,"FAQs about Sample Ratio Mismatch",[682,686,690,694,698],{"id":683,"question":684,"answer":685,"active":56,"link":17},5400,"Is sample ratio mismatch always a sign that my experiment is invalid?","SRM is a strong warning signal, but not an automatic verdict that all results are unusable. If the root cause is localized to a clearly identifiable segment that can be safely excluded, it may be possible to recover some directional insight from the remaining data. However, the most conservative and reliable approach is usually to fix the underlying issue and rerun the experiment with clean randomization, so you can trust the full data set.",{"id":687,"question":688,"answer":689,"active":56,"link":17},5401,"Could SRM just be bad luck in randomization?","Small imbalances are expected by chance. The chi squared test quantifies exactly how surprising the observed split is. When the SRM p value is very low, such as below 0.01 or 0.0005, the probability that the mismatch is due purely to luck is extremely small. While extremely unlikely events are not impossible, in practice a low p value almost always points to a real implementation or data issue rather than a statistical fluke.",{"id":691,"question":692,"answer":693,"active":56,"link":17},5402,"Should I check for SRM on sessions or users?","SRM checks should be performed on the same unit that is randomized, which is usually the user or account. Using visits or sessions can be misleading, because one variant might change the frequency of visits, creating an apparent imbalance without any actual assignment problem. Confirm the randomization unit in your experimentation platform and align your imbalance check accordingly.",{"id":695,"question":696,"answer":697,"active":56,"link":17},5403,"What SRM p value threshold should I use?","Many teams use 0.01 as a practical threshold for declaring SRM, while some choose a more conservative threshold like 0.0005 to further reduce false positives. Align the threshold with your organization's risk tolerance and the volume of experiments you run, since very frequent testing increases the chance of occasional false alarms. Use a consistent threshold across experiments so that SRM flags are interpreted uniformly by analysts and decision makers. For more on balancing frequentist thresholds with Bayesian approaches, both methods offer useful lenses.",{"id":699,"question":700,"answer":701,"active":56,"link":17},5404,"What should I do when SRM occurs in a running experiment?","Pause new exposure to the experiment as soon as a confirmed SRM is detected, to avoid accumulating more biased data. Start an investigation that checks recent deployments, changes to targeting rules, monitoring logs, and segment level splits to find the root cause. Document the diagnosis and outcome, fix the underlying implementation issue, and then relaunch the experiment with a fresh randomization and renewed SRM monitoring.",1784728341224]