Free to follow every thread. No paywall, no dead ends.
Survey (human research) | HearLore
Survey (human research)
In 1838, the Statistical Society of London did something that would eventually reshape how humanity understands itself, yet it began with a simple, almost mundane goal: to record the history of strikes. A committee within the society printed a list of questions and distributed them to gather data on industrial and social conditions, marking the first known instance of a written questionnaire in recorded history. This was not a grand political maneuver or a scientific breakthrough in the modern sense, but a deliberate attempt to elicit an impartial history from workers and employers alike. The questions were designed to be comprehensive, seeking to capture the complete narrative of labor disputes rather than just the surface-level facts. This early experiment laid the groundwork for a methodology that would eventually evolve from paper slips to complex digital algorithms, transforming the way governments, corporations, and researchers understand human behavior. The society's decision to use a written format allowed for standardization, ensuring that every respondent received the exact same set of inquiries, a principle that remains central to survey research today. The impact of this 1838 initiative rippled outward, influencing how data was collected for decades, eventually leading to the establishment of national censuses and the sophisticated polling mechanisms that define modern public opinion.
The Census and The Count
The most famous public survey in the United States is the national census, a massive undertaking that has been held every ten years since 1790. This is not merely a headcount but a complex demographic operation that attempts to capture the age, ethnicity, and household relationships of every person within the nation's borders. The United Nations defines the essential features of such censuses as individual enumeration, universality within a defined territory, simultaneity, and defined periodicity, recommending that population censuses be taken at least every 10 years. The census serves as the bedrock for survey research, providing the framework against which all other samples are measured. Without the census, it would be impossible to determine if a sample of 9,731 households in Great Britain, as seen in the 2006 General Household Survey, truly represents the larger population. The census also extends beyond people to include agriculture, business, and traffic censuses, creating a comprehensive map of a nation's resources and activities. In the United States, the National Survey of Family Growth, conducted by the Centers for Disease Control and Prevention, relies on the census framework to understand trends in fertility and family structure, having surveyed 22,682 interviews between 2006 and 2010. The sheer scale of these operations requires immense coordination, yet they remain the primary tool for governments to allocate resources and plan for the future. The census is a testament to the power of systematic data collection, turning the chaotic diversity of human life into manageable statistics that can guide policy and public health initiatives.
When did the Statistical Society of London conduct the first known written questionnaire?
The Statistical Society of London conducted the first known written questionnaire in 1838. This committee printed a list of questions to gather data on industrial and social conditions and record the history of strikes.
How often does the United States hold its national census?
The United States holds its national census every ten years since 1790. The United Nations recommends that population censuses be taken at least every 10 years to ensure individual enumeration and universality within a defined territory.
What percentage of global data collection expenditure was accounted for by online surveys in 2006?
Online surveys accounted for 20% of global data collection expenditure as of 2006. The development of the Internet fostered web surveys which now offer innovative ways to gather data and eliminate the laborious process of data entry.
How many interviews were conducted in the National Survey of Family Growth between 2006 and 2010?
The National Survey of Family Growth conducted 22,682 interviews between 2006 and 2010. This survey relies on the census framework to understand trends in fertility and family structure.
When did the Panel Study of Income Dynamics begin collecting data in the United States?
The Panel Study of Income Dynamics began collecting data from the same families and their descendants in 1968. As of 2009, this longitudinal study involved more than 9,000 individuals.
How many countries participated in the Generations and Gender Survey?
The Generations and Gender Survey has collected at least one wave of surveys in 19 countries. This global survey includes countries in Europe as well as Australia and Japan with an average of 9,000 respondents per country.
The method of collecting survey data has undergone a radical transformation, shifting from traditional paper-and-pencil interviewing to computer-assisted interviewing and eventually to mobile and online platforms. In the early days, researchers relied on face-to-face interactions or mail surveys, which were time-consuming and often limited by geography. The introduction of the telephone survey, used at least as early as the 1940s, allowed for broader reach, though it introduced new challenges such as interviewer bias and the inability to convey visual information. The development of the Internet in the late-20th century fostered online surveys and web surveys, which now account for 20% of global data-collection expenditure as of 2006. This shift has dramatically reduced costs; a World Bank study in Guatemala found a 71% decrease in cost when using mobile data collection compared to the previous paper-based approach. Mobile surveys, which are now opened on over 50% of devices, offer innovative ways to gather data and eliminate the laborious process of data entry, allowing for quicker response times and the ability to reach previously hard-to-reach target groups. Despite these advantages, the transition has not been seamless, with concerns about privacy, the quality of data from non-probability samples, and the potential for ballot stuffing in online environments. The evolution of survey methodology reflects the broader technological advancements of society, adapting to the changing ways people communicate and interact with the world.
The Hidden Biases
Survey research is not immune to the flaws of human nature, and the data it produces can be skewed by a variety of biases that researchers must constantly guard against. One of the most pervasive issues is acquiescence bias, a phenomenon where many people have acquiescent personalities and are more likely to agree with statements than disagree, regardless of the content. This tendency can lead to inaccurate results, as respondents may see the question-asker as an expert and react positively to the question asked, even if they do not truly agree. Another significant challenge is the discrepancy between reported behavior and actual behavior, particularly in sensitive areas such as sex-related queries. Studies have shown that men often amplify their number of sex partners, while women tend to downplay and slash their true number, creating a gender discrepancy in self-reported lifetime number of sex partners. This dishonesty, while pronounced in some areas, is not universal, and researchers must use caution when extrapolating self-reports to actual behaviors. The value of collected data completely depends upon how truthful respondents are in their answers, and survey researchers often avoid reactive measurement by examining the accuracy of verbal reports and directly observing respondents' behavior. The presence of interviewer bias, where some people may be more willing to discuss a sensitive issue with a female interviewer than with a male one, further complicates the data collection process. These biases highlight the complexity of survey research, requiring researchers to employ sophisticated statistical techniques to correct for measurement error and ensure the validity of their findings.
The Science Of Sampling
The success of survey research hinges on the representativeness of the sample with respect to a target population of interest, a concept that has become a cornerstone of empirical research in social sciences, marketing, and official statistics. With the application of probability sampling in the 1930s, surveys became a standard tool for empirical research, allowing researchers to generalize findings from a sample to the population. The difference between probability samples, where the inclusion probabilities for all units of the target population is known in advance, and non-probability samples, which often require less time and effort but generally do not support statistical inference, is crucial. Probability samples are highly affected by problems of non-coverage, where not all members of the general population have Internet access, and frame problems, where online survey invitations are most conveniently distributed using e-mail, but there are no e-mail directories of the general population that might be used as a sampling frame. The choice between administration modes is influenced by several factors, including costs, coverage of the target population, flexibility of asking questions, respondents' willingness to participate, and response accuracy. Different methods create mode effects that change how respondents answer, and researchers must carefully consider these factors when designing a survey. The Panel Study of Income Dynamics in the United States, which has collected data from the same families and their descendants since 1968, stands as a testament to the power of longitudinal sampling, involving more than 9,000 individuals as of 2009. The Socio-Economic Panel, a longitudinal panel dataset of the population in Germany, started in 1984 and reinterviews adult household members annually, involving about 12,000 households and more than 20,000 adult persons sampled in 2007. These studies demonstrate the importance of maintaining a representative sample over time to track changes in attitudes and behaviors.
The Global Reach Of Surveys
Surveys have expanded beyond national borders to become a global tool for understanding human behavior and social trends. The Generations and Gender Survey, conducted in several countries in Europe as well as Australia and Japan, has collected at least one wave of surveys in 19 countries, with an average of 9,000 respondents per country. The Integrated Household Survey, a survey made up of multiple other surveys in the UK, includes about 340,000 respondents, making it the largest collection of social data in the UK after the census. The Household, Income and Labour Dynamics in Australia Survey, where the wave 1 panel consisted of 7,682 households and 19,914 individuals, provides a detailed picture of the economic and social conditions of Australian households. These global surveys are essential for comparing the attitudes of different populations and looking for changes in attitudes over time. They also play a crucial role in healthcare, where medical survey research is particularly concerned with uncovering knowledge-practice gaps. In other words, some medical surveys aim at exploring the difference between the proper practice and the actual practice reported by the healthcare professionals. Healthcare professionals that may be enrolled in survey studies include physicians, nurses, and physical therapists among others. The results of survey research can inform the public health domain and help conduct health awareness campaigns in vulnerable populations and guide healthcare policy-makers. This is especially true when survey research deals with a wide spread disease that constitutes a nationwide or global health challenge. The global reach of surveys allows researchers to identify patterns and trends that transcend national boundaries, providing a comprehensive understanding of human behavior and social dynamics.