{"id":2032402,"date":"2023-07-26T12:31:01","date_gmt":"2023-07-26T19:31:01","guid":{"rendered":"https:\/\/www.esri.com\/arcgis-blog\/?post_type=blog&p=2032402"},"modified":"2023-07-26T14:05:10","modified_gmt":"2023-07-26T21:05:10","slug":"examine-data-accuracy-in-arcgis-business-analyst-using-acs-reliability-estimates","status":"publish","type":"blog","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/bus-analyst\/analytics\/examine-data-accuracy-in-arcgis-business-analyst-using-acs-reliability-estimates","title":{"rendered":"Examine data accuracy in ArcGIS Business Analyst using ACS reliability estimates"},"author":317312,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"open","ping_status":"closed","template":"","format":"standard","meta":{"_acf_changed":false,"_searchwp_excluded":""},"categories":[23341],"tags":[36021,626901,31361,759262,767712],"industry":[],"product":[36711],"class_list":["post-2032402","blog","type-blog","status-publish","format-standard","hentry","category-analytics","tag-american-community-survey","tag-arcgis-business-analyst","tag-census","tag-margin-of-error","tag-reliability","product-bus-analyst"],"acf":{"authors":[{"ID":317312,"user_firstname":"Elif","user_lastname":"Bulut","nickname":"Elif Bulut","user_nicename":"ebulut","display_name":"Elif Bulut","user_email":"ebulut@esri.com","user_url":"","user_registered":"2022-08-24 18:23:17","user_description":"Elif is a Product Engineer of Social Analysis and Data Science on the ArcGIS Business Analyst team. She holds a PhD in Sociology and applies spatial data science and social research to help users explore demographic trends, community characteristics, and access to resources. She is passionate about turning complex data into clear insights that support real-world decision-making.","user_avatar":""}],"short_description":"This blog article provides a concise overview of the reliability score, its calculation, and practical application within Business Analyst.","flexible_content":[{"acf_fc_layout":"content","content":"

Have you ever <\/span>wondered<\/span> about the <\/span><\/span>Reliability<\/span><\/span> button <\/span>located<\/span> next to<\/span> the count and percent options <\/span>in <\/span>the\u202f<\/span><\/span>data browser<\/span><\/span><\/a> wh<\/span>en <\/span>searching for a variable in ArcGIS Business Analyst?<\/span><\/span>\u00a0<\/span><\/p>\n"},{"acf_fc_layout":"image","image":{"ID":2032412,"id":2032412,"title":"Reliability Button in Data Browser","filename":"new_Reliability-Button-in-Data-Browser.jpg","filesize":180418,"url":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser.jpg","link":"https:\/\/www.esri.com\/arcgis-blog\/products\/bus-analyst\/analytics\/examine-data-accuracy-in-arcgis-business-analyst-using-acs-reliability-estimates\/new_reliability-button-in-data-browser","alt":"","author":"317312","description":"","caption":"","name":"new_reliability-button-in-data-browser","status":"inherit","uploaded_to":2032402,"date":"2023-07-25 22:53:03","modified":"2023-07-25 22:53:21","menu_order":0,"mime_type":"image\/jpeg","type":"image","subtype":"jpeg","icon":"https:\/\/www.esri.com\/arcgis-blog\/wp-includes\/images\/media\/default.png","width":1747,"height":847,"sizes":{"thumbnail":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser-213x200.jpg","thumbnail-width":213,"thumbnail-height":200,"medium":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser.jpg","medium-width":464,"medium-height":225,"medium_large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser.jpg","medium_large-width":768,"medium_large-height":372,"large":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser.jpg","large-width":1747,"large-height":847,"1536x1536":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser-1536x745.jpg","1536x1536-width":1536,"1536x1536-height":745,"2048x2048":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser.jpg","2048x2048-width":1747,"2048x2048-height":847,"card_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser-826x400.jpg","card_image-width":826,"card_image-height":400,"wide_image":"https:\/\/www.esri.com\/arcgis-blog\/app\/uploads\/2023\/07\/new_Reliability-Button-in-Data-Browser.jpg","wide_image-width":1747,"wide_image-height":847}},"image_position":"center","orientation":"horizontal","hyperlink":""},{"acf_fc_layout":"content","content":"

Variables that show the <\/span>Reliability <\/span><\/b>button in the data browser have\u2014in addition to other calculation options like count and percentage\u2014a reliability score.<\/span>\u00a0<\/span>\u00a0<\/span><\/p>\n

What is reliability?<\/span><\/b>\u00a0<\/span><\/p>\n

Simply put, a variable\u2019s reliability score serves as an indicator of the reliability of American Community Survey (ACS) estimates. The Reliability button only appears on ACS variables, and helps users understand the level of confidence they can have in the data provided by ACS. This feature is essential for making informed decisions based on accurate and reliable information within ArcGIS Business Analyst.\u00a0<\/span>\u00a0<\/span><\/p>\n

In this blog article, we provide a concise overview of the reliability score, its calculation, and practical application within Business Analyst.<\/span>\u00a0<\/span><\/p>\n

Why is it important to verify the reliability of ACS data?<\/span><\/b>\u00a0<\/span><\/p>\n

The American Community Survey (ACS) data is one of the most commonly used public datasets for understanding population and housing characteristics in the U.S. However, it is crucial to interpret the data accurately. To this end, Esri demographers analyze the raw data and assign reliability scores to ACS variables.<\/span>\u00a0<\/span><\/p>\n

The ACS employs a continuous measurement, also known as a rolling sample, where a small percentage of the population is sampled every month. Due to the relatively small yearly sample sizes, the ACS survey pools 60 months\u2019 of data to produce reliable estimates for small areas. Even when we use the 5-year estimates from ACS though, there will always be differences between the sample and the total population because of the fact that entire population is not surveyed. Sampling error arises when only a portion of the population is surveyed to estimate characteristics of the entire population. To address this issue, the ACS reports for most standard census geographies include margins of error (MOEs) with the estimates.\u00a0<\/span>\u00a0<\/span><\/p>\n

The MOE measures the variability of an estimate resulting from sampling error. This tells data users that the estimate is not a precise figure but instead represents a range of potential values. Hence, the MOE serves as a crucial metric for data users, allowing them to understand the range of uncertainty for each estimate. This range can be calculated with 90 percent confidence by adding or subtracting the MOE to\/from the estimate. The range of values is referred to as the \u2018confidence interval,\u2019 indicating that the U.S. Census Bureau has 90% confidence that the population count falls between the upper and lower values. For instance, if the ACS reports an estimate of 120 with a margin of error of +\/- 30, there is a 90 percent likelihood that the total population value falls between 90 (120 – 30) and 150 (120 + 30). A larger MOE indicates lower precision in the estimate, reducing confidence in its proximity to the true population value.<\/span>\u00a0<\/span>\u00a0<\/span><\/p>\n

Statistical margins of error have significant implications for decision-making among market analysts, business owners, and policy makers. Suppose a company conducts a survey to estimate the percentage of potential customers interested in buying a new product. The survey results show that 75% of respondents are interested in the product, with a margin of error of +\/- 10%. This means that the true customer interest level could be as high as 85% (75% + 10%) or as low as 65% (75% – 10%). The larger the margin of error, the less confidence the company can have in the estimate’s accuracy, affecting their decision-making process.<\/span>\u00a0<\/span><\/p>\n

Esri\u2019s reliability thresholds<\/span><\/b>\u00a0<\/span><\/p>\n

Assessing the quality of an estimate solely based on the margin of error (MOE) can be challenging. To simplify this assessment, Esri has introduced reliability symbols in their maps and reports. The reliability symbols are divided into three categories: high, medium, and low reliability.\u00a0<\/span>\u00a0<\/span><\/p>\n

The reliability estimates are derived from an estimate\u2019s coefficient of variation (CV), which measures the amount of sampling error relative to the size of the estimate. When the error is large relative to the estimate, the coefficient will be large, indicating lower reliability. As the coefficient increases, the reliability decreases.<\/span>\u00a0<\/span><\/p>\n