2022-04-04

Stated Preference (SP) Survey

What is Stated Preference (SP) Survey

Stated preference (SP) surveys are a powerful tool used by researchers and decision-makers to gain insights into individuals' preferences and values for goods, services, or attributes that may not be directly observable or available in the marketplace. By asking respondents to express their preferences for hypothetical alternatives, SP surveys allow researchers to understand how people make choices and trade-offs in various contexts, such as environmental policy, transportation planning, healthcare, and marketing.

Importance of SP Surveys in Decision Making

In a world full of competing priorities, understanding individuals' preferences and values is crucial for businesses and policymakers alike. Stated preference surveys have gained prominence over the years because they offer a flexible and efficient way to estimate people's preferences and willingness to pay for non-market goods or services.

For businesses, SP surveys can provide valuable insights into consumer preferences, allowing them to tailor their products and services to better meet the needs of their customers. By understanding how individuals assign value to different attributes, businesses can make more informed decisions about the development, implementation, and improvement of their offerings. Furthermore, SP surveys can help identify potential gaps in current offerings and uncover opportunities for innovation and growth.

For policymakers, SP surveys can help assess the potential impact and acceptability of various policies or public investments. For example, transportation planners can use SP surveys to understand how people value different attributes of a transportation system, such as travel time, cost, and reliability. Environmental policymakers can use SP surveys to estimate the public's willingness to pay for the preservation of natural resources or the reduction of pollution. By incorporating these insights into their decision-making processes, policymakers can make more informed choices about resource allocation, investment priorities, and policy design.

Designing SP Survey

Identifying the Objectives

The first step in designing a successful stated preference survey is to clearly define the objectives of the study. The objectives will guide the development of the survey, including the choice of questions, the target population, and the data collection methods. Objectives should be specific, measurable, and relevant to the decision-making context. Examples of objectives may include:

Estimating willingness to pay for a new public service or amenity
Understanding trade-offs between different product attributes
Assessing the demand for a new transportation option

Defining the Target Population

Once the objectives have been established, it is crucial to define the target population of interest. This may include specific demographic groups, geographic regions, or individuals with particular characteristics or experiences. A clear understanding of the target population will help ensure that the survey results are representative and relevant to the decision-making context.

Crafting the Questionnaire

A well-designed questionnaire is essential for obtaining reliable and valid data from a stated preference survey. The questionnaire should be carefully crafted to minimize potential biases and ensure that respondents can easily understand and answer the questions.

There are several types of questions that can be used in stated preference surveys, including:

Choice tasks
Respondents are presented with a set of alternatives and asked to choose the one they prefer. This can help reveal the relative importance of different attributes and trade-offs people are willing to make.
Ranking tasks
Respondents are asked to rank a list of alternatives based on their preferences. This can help identify the most and least preferred options.
Rating tasks
Respondents are asked to rate alternatives on a scale (e.g., 1-10 or 1-5). This can provide insights into the intensity of preferences.

Implementation of SP Surveys

Data Collection Methods

Once the survey objectives have been identified, and the questionnaire designed, the next step is to implement the stated preference survey. There are several data collection methods that can be used, each with its own advantages and challenges.

Online Surveys
Online surveys have become increasingly popular due to their cost-effectiveness and ease of implementation. They can reach a wide audience quickly and provide respondents with the flexibility to complete the survey at their own pace. However, online surveys may suffer from lower response rates and potential biases related to internet access or digital literacy.
Paper Surveys
Paper surveys can be mailed to respondents or distributed in person. They may be preferable for certain populations, such as older adults or those with limited internet access. However, paper surveys can be more expensive and time-consuming to administer, and they may suffer from a higher risk of data entry errors.
Telephone Surveys
Telephone surveys involve contacting respondents by phone and collecting responses verbally. They can provide a more personal touch and potentially higher response rates, but they may also be more expensive and time-consuming to administer. Additionally, telephone surveys can be affected by biases related to the interviewer's presence or the respondent's comfort in sharing their preferences over the phone.
In-person Interviews
In-person interviews involve face-to-face interactions between the interviewer and the respondent. They can yield rich qualitative data and high response rates but are typically more expensive and time-consuming than other methods. In-person interviews can also be affected by interviewer biases and social desirability biases.

Sampling Techniques

Selecting a representative sample of the target population is essential for obtaining reliable and valid insights from a stated preference survey. There are several sampling techniques that can be employed, including:

Simple random sampling
Each member of the target population has an equal chance of being selected.
Stratified sampling
The target population is divided into subgroups, and random samples are drawn from each subgroup.
Cluster sampling: The target population is divided into clusters, and a random sample of clusters is selected for the survey.

The choice of sampling technique will depend on the research objectives, the target population, and the available resources.

Analyzing SP Survey Data

Data Processing

After data collection is complete, the next step is to process and clean the data to ensure its accuracy and reliability. This may involve tasks such as data entry, data validation, and handling missing or incomplete responses. Proper data processing is crucial for obtaining meaningful and valid results from the stated preference survey.

Exploratory Data Analysis

Exploratory data analysis (EDA) is a crucial first step in understanding the collected data. It involves summarizing and visualizing the data to uncover patterns, trends, and potential outliers. Common EDA techniques include descriptive statistics (e.g., mean, median, standard deviation), frequency tables, and graphical representations (e.g., histograms, bar charts, scatter plots). EDA can help researchers identify potential issues or areas of interest that require further investigation.

Modeling Techniques

Stated preference survey data often requires statistical modeling techniques to estimate the underlying preferences and values of respondents. Two popular approaches are choice modeling and conjoint analysis.

Choice Modeling
Choice modeling is a statistical technique used to analyze the choices respondents make among different alternatives presented in the survey. It allows researchers to estimate the relative importance of different attributes and the trade-offs individuals are willing to make. Common choice modeling techniques include multinomial logit models, nested logit models, and mixed logit models.
Conjoint Analysis
Conjoint analysis is another popular approach for analyzing stated preference data, particularly in marketing research. It involves decomposing respondents' preferences into part-worth utilities for each attribute level, which can be used to estimate the overall preference for different combinations of attributes. Conjoint analysis can help researchers understand the relative importance of different attributes and predict respondents' preferences for new or untested product or service offerings.

SP Survey Limitations

While stated preference surveys can provide valuable insights into individuals' preferences and values, they are not without limitations. This chapter will discuss some of the key concerns related to the use of SP surveys in decision-making and research.

Hypothetical Bias
One of the main limitations of stated preference surveys is hypothetical bias, which occurs when respondents' stated preferences differ from their actual preferences in real-world situations. Hypothetical bias may result from factors such as the absence of real consequences, cognitive limitations, or unfamiliarity with the scenarios presented in the survey. To mitigate hypothetical bias, researchers can use techniques such as cheap talk scripts, certainty calibration, and consequentiality reminders, which aim to encourage respondents to consider their answers more carefully and honestly.
Strategic Bias
Strategic bias occurs when respondents intentionally misrepresent their preferences in an attempt to influence the outcome of the survey or decision-making process. For example, individuals may overstate their willingness to pay for a public good if they believe that doing so will increase the likelihood of its provision. Researchers can minimize strategic bias by designing surveys that are less susceptible to manipulation, using incentive-compatible elicitation methods, or incorporating debriefing questions to assess respondents' motivations and honesty.
Social Desirability Bias
Social desirability bias refers to the tendency of respondents to provide answers that they believe will be viewed favorably by others, rather than reflecting their true preferences. This can lead to biased estimates of preferences and willingness to pay, particularly for sensitive or controversial topics. To reduce social desirability bias, researchers can ensure confidentiality and anonymity, use indirect questioning techniques (e.g., the randomized response technique), or employ self-administered survey modes (e.g., online surveys) that may be less prone to social pressures.

Example of SP Survey: Public Park Improvement Preferences

This chapter presents an example of a stated preference survey designed to measure public preferences for various improvements to a local park. This example will demonstrate how the principles discussed in previous chapters can be applied to a real-world scenario.

Introduction

The objective of this survey is to understand the public's preferences and willingness to pay for different park improvement options. The results will be used to inform the decision-making process for allocating resources and prioritizing park improvements.

Target Population

The target population for this survey consists of residents living in the neighborhood surrounding the park. The sample will be stratified by age, gender, and household income to ensure a representative sample of the local community.

Questionnaire Design

The questionnaire will include a series of choice tasks, where respondents will be asked to select their preferred park improvement option from a set of alternatives. Each alternative will be described using several attributes, such as cost, type of improvement, and expected impact on park usage.

Here is an example choice task:

Please choose the park improvement option that you prefer the most:

Option A

Cost: $10 increase in annual property taxes

Improvement: New playground equipment

Expected impact on park usage: 15% increase

Option B

Cost: $20 increase in annual property taxes

Improvement: Improved walking and biking trails

Expected impact on park usage: 25% increase

Option C

Cost: $30 increase in annual property taxes

Improvement: Additional green space and picnic areas

Expected impact on park usage: 10% increase

Option D

No improvements (no change in annual property taxes)

Data Collection

The survey will be administered using a combination of online and paper surveys. Online surveys will be sent to residents via email, while paper surveys will be mailed to a random sample of households in the target area. Follow-up reminders will be sent to nonrespondents to encourage participation and increase response rates.

Data Analysis

Data analysis will involve estimating a choice model to understand the relative importance of different attributes and the trade-offs respondents are willing to make. This will allow researchers to estimate the public's willingness to pay for different park improvement options and inform the decision-making process.

Reporting Results

The results of the stated preference survey will be presented in a report summarizing the key findings, including the estimated willingness to pay for different park improvement options and the potential impact on park usage. The report will also discuss the implications of the findings for park management and future investment decisions.