Documentation for: Designing Passwords for Web Survey Access: The Effects of Password Length and Complexity on Survey and Panel Recruitment

This archive does not contain any data but code and codebooks. For our analyses we use administrative data of the Institute for Employment Research (detail information about the data and its version). The data are social data with administrative origin which are processed and kept by IAB according to Social Code III. There are certain legal restrictions due to the protection of data privacy. The data contain sensitive information and therefore are subject to the confidentiality regulations of the German Social Code (Book I, Section 35, Paragraph 1). The data are held by the Institute for Employment Research (IAB), Regensburger Str. 104, D-90478 Nürnberg, email: [e-mail], phone: [phone]. If you wish to access this data for replication purposes, please get in contact with the author, see https://iab.de/en/facts-and-figures-2/data-access-for-replication-purposes/. For the publication we received an exemption to upload the data on July 17th 2025 by the editor of Public Opinion Quarterly. Abstract of paper: Online probability panels that recruit participants via postal invitation letters use passwords to manage access to the survey. While previous research has examined primarily whether providing a password affects response rates, less attention has been given to the impact of password strength, defined by length and complexity, on response propensities. Password length refers to the number of characters in a password, while complexity refers to the set of characters (e.g., lowercase letters, digits). This study evaluates the influence of password length and complexity on various participation levels (i.e., survey access, response rates, and panel registration) as well as the propensity to consent to data linkage and item response rates for income questions. We conducted an experiment in the first wave of a German online probability survey and manipulated password length and complexity. Additionally, we included a group using the default length and complexity settings (eight uppercase letters) of the survey hosting service. The participants were randomly assigned to one of these groups. The findings indicate that longer and more complex passwords increase both participation rates and the propensity to consent to data linkage between survey and administrative data.