Field Days and Field Length

Susan Frede, VP Research

November, 2008

Overview

One of the main advantages of using the Internet to collect marketing research data is the speed at which data can be collected. The benefit of speed, however, also brings the concern that the quality of the data may be negatively impacted. As researchers we strive to understand how data and business decisions may be impacted by the day of week the field starts or by how long the field is open.

Background

In February 2008, Lightspeed Research fielded a 25-cell test to address questions around the appropriate field period for online studies. This research-on-research study involved five concepts. Each concept had five separate samples, one launched each day of the week from Monday through Friday. Respondents had seven days from the day the sample was launched to respond.

All concepts were tested monadically using identical surveys. The demographic universes were selected as appropriate for the product target market. Key concept measures included Purchase Intent, Uniqueness, Value, Liking, Believability, Quantity, and Frequency. Respondents were also asked a number of category habit and brand usage questions.

The following topics are addressed in this white paper:

• Is it necessary to include both weekends and weekdays in the field period?
• Does it matter how long the field is left open?
• Does it matter what day of the week the field starts?

Weekday vs. Weekend Responders

There are no significant differences between weekday and weekend responders on key measures (see Table 1). There are also few significant differences between weekday and weekend responders on demographics and habits. The only notable differences are on locations where surveys are typically completed and time to complete the survey. Those responding on the weekend are more likely to complete the survey at home and are less likely to take over 24 hours to complete the survey (i.e., stop the survey and return to complete it). The lack of significant differences suggests that including both weekend and weekday responders is not necessary to have a representative sample.

Length of Field

Day 1 and day 2 of the field have the largest proportion of completes (see Chart). There are very few completes on days 5 through 7. For this research, reminders were not sent to respondents. However, other research on research has shown that reminders don’t increase response rate significantly or improve representativeness. There are some differences in key measures depending on the day of field respondents answer the survey (see Table 2). Specifically, day 7 responders tend to give lower key measure scores. Purchase intent and key measure scores tend to be very consistent on days 1 thru 3. However, the earlier responders (especially day 1 and day 2 responders and to a lesser extent, day 3 responders) tend to be slightly different demographically. Earlier responders tend to be older and part of smaller households with no children and lower income. They are also more likely to be Caucasian and retired. Later responders (day 4-7) tend to be those who may have busier lives (i.e. employed full time, children/families). These demographic differences suggest that field should remain open at least four days in order to get a representative sample.

Purchase intent and key measures are consistent with the seven-day field period data when looking at different cumulative totals. Table 3 shows combined data for the five concepts, but even for individual concepts differences are not observed. There are also no meaningful differences on demographics and habits across these four groups. This data coupled with completion rates, suggests a four-day field period is sufficient to get stable results.

Day of Week Field Launch

In general, scores tend to be slightly lower for Thursday launches and slightly higher for Friday launches (see Table 4). However, this same pattern is not observed for all five individual concepts. In addition, the differences versus Total are generally small. In fact, only the top box uniqueness score on Thursday is greater than +/-2 versus Total. Coupled with no meaningful demographic and habit differences across the field launch days suggests that field can be started any day of the week.

Conclusions and Recommendations

Based on this research on research, Lightspeed Research recommends a minimum of a four-day field period. This leads to more representative samples and ultimately more accurate data and business decisions.

The day the field launches does not appear to impact data and there is no difference between those responding on the weekend versus during the week. Therefore, there is no need to launch on a consistent day of the week or include both weekends and weekdays in the field period. The one exception to this recommendation is when there is a need to track scheduled marketing activity. For example, there may be a need to get immediate reaction to a new television advertisement.

About Lightspeed Research

Lightspeed Research (www.lightspeedresearch.com) is the market researcher’s choice for digitally accessing and deriving insight from consumer opinions and behaviors whenever, wherever and in whatever segments needed. The industry’s most thorough panelist prescreening process and large global pool delivers business-ready results quickly and costeffectively. From proprietary online access panels to specialty panels, custom panels and innovative mobile surveys, Lightspeed Research offers the industry’s highest-quality and most complete combination of qualitative and quantitative online research. This is backed by an expert client operations team that provides a range of data collection services, from sample management and survey design to programming and reporting. Part of Kantar, a division of WPP, Lightspeed Research serves clients and cultivates online panelists across the Americas, Europe and Asia Pacific.

Susan Frede is the VP of Research at Lightspeed Research. She has worked in the research field for 23 years, has published numerous research-on-research papers and is a well-respected speaker at key industry events. Some of the topics she has recently explored include questionnaire length, best practices for online research, suspicious and professional respondents and data stability. You can contact Susan at sfrede@lightspeedresearch.com

Generic vs. Non-Generic Survey Invitations

Susan Frede, VP Research

November, 2008

Introduction

The survey invitation is important because it is the first contact with a prospective respondent. It can cause respondents to decide not to respond as well as impact how they respond. There has been much discussion around the amount of detail that should be given in the invitation. Some suggest that limiting the information reduces self-selection bias and reduces the ability of respondents to misrepresent themselves intentionally or to provide inaccurate information in order to qualify for surveys. Others suggest that including more information increases the likelihood that respondents will participate.

Background

Lightspeed Research tested five concepts using two different survey invitations. The generic invitation stated simply that a new survey was available without telling the respondent the subject of the survey. The non-generic invitation provided the subject. Both sets of invitations gave an estimate of time as well as the number of reward points the respondent would earn. Both mentioned entry into a sweepstakes and gave directions on how to take the survey.

All concepts were tested monadically using identical surveys for the generic and non-generic versions. The demographic universes were selected as appropriate for the product target market. Key concept measures included Purchase Intent, Uniqueness, Value, Liking, Believability, Quantity, and Frequency. Respondents also were asked a number of category habit and brand usage questions.

Key Measures

There are no statistically significant differences between generic and non-generic invitations for key concept measures (see Table 1 on next page). This suggests the type of invitation does not have the potential to change business decisions.

Response and Completion Rates

There are no statistically significant differences in response or completion rates between the generic and non-generic invitations.

Other Measures

Several other items have been examined to understand if the type of invitation has an impact. These include:

• Demographics – In this research, the return samples line up well between the generic and non-generic groups on demographics. There are a few statistical differences, but there are no consistent patterns.
• Category and Brand Usage – For several concepts the non-generic invitation version has slightly different category and brand usage. This includes higher frequency of category usage, higher brand usage for several brands, and a slightly higher number of brands used. Perhaps telling respondents the subject of the survey causes them to answer differently in order to qualify for the survey or the possible placement of a product.
• Suspicious Respondent Behavior – Respondents in the non-generic groups are no more likely than those in the generic groups to exhibit suspicious behavior. This includes both inattentive and fraudulent behavior.

Conclusions

Including the subject of the survey in the invitation does not significantly improve response rates. Given there are no differences in key measures between the generic and non-generic survey invitations, Lightspeed Research recommends sending respondents generic survey invitations. Generic survey invitations lessen the chance that category and brand usage questions are impacted by suspicious behavior as well as reducing the potential impact of self-selection bias, which may be higher for certain categories.

About Lightspeed Research

Lightspeed Research (www.lightspeedresearch.com) is the market researcher’s choice for digitally accessing and deriving insight from consumer opinions and behaviors whenever, wherever and in whatever segments needed. The industry’s most thorough panelist pre-screening process and large global pool delivers business-ready results quickly and cost-effectively. From proprietary online access panels to specialty panels, custom panels and innovative mobile surveys, Lightspeed Research offers the industry’s highest-quality and most complete combination of qualitative and quantitative online research. This is backed by an expert client operations team that provides a range of data collection services, from sample management and survey design to programming and reporting. Part of Kantar, a division of WPP, Lightspeed Research serves clients and cultivates online panelists across the Americas, Europe and Asia Pacific.

Susan Frede is the VP of Research at Lightspeed Research. She has worked in the research field for 23 years, has published numerous research-on-research papers and is a well-respected speaker at key industry events. Some of the topics she has recently explored include questionnaire length, best practices for online research, suspicious and professional respondents and data stability.

Impact of Survey Reminders
Susan Frede, VP Research
November, 2008

Because sending survey reminders has little or no cost implication with Internet surveys, it is often a common practice to send one or more reminders to potential respondents. However, data quality and respondent retention may be compromised when consumers are bombarded with too much communication about a survey.

Background

Lightspeed Research tested five concepts utilizing survey reminders and then tested the same five concepts without utilizing survey reminders. For the groups receiving a reminder, only respondents who had not completed the survey at the time of the reminder received the reminder. All concepts were tested monadically using identical surveys for the reminder and non-reminder versions. The demographic universes were selected as appropriate for the product target market. Key concept measures included Purchase Intent, Uniqueness, Value, Liking, Believability, Quantity, and Frequency. Respondents also were asked a number of category habit and brand usage questions.

Key Measures

There are no statistically significant differences between reminder and non-reminder versions for key concept measures (see Table 1). This suggests that sending (or not sending) a reminder does not have the potential to impact business decisions.

Response and Completion Rates

Response and completion rates are not impacted consistently by reminders. For three of the five concepts response and completion rates are slightly higher when respondents are sent a reminder, while for the other two rates are slightly lower.

Completion Day

Generally, there is no difference between the reminder and no-reminder versions for the number of respondents completing the survey each day (see Table 3). This is especially true once a reminder is sent (either day 4 or day 5). This suggests that a reminder does not increase response or completion rates.

Who Receives Reminders

Reminders are more likely to go to females who are employed full time and are part of larger households with kids. This does not have an impact on the representivity of samples given that return samples line up well between the reminder and no reminder groups on demographics. Perhaps those receiving reminders tend to be busy and, in general, are more likely to be later survey completers.

Other Measures

Several other items have been examined to understand if sending a reminder has an impact.
These include:

• Category and Brand Usage – Like demographics, the samples generally line up well between the reminder and no-reminder groups on category and brand usage.
• Suspicious Respondent Behavior – There are no differences in suspicious behavior between the reminder and no-reminder groups.

Conclusions

Based on this research, Lightspeed Research does not recommend sending our panelists reminders about surveys they have not completed. Reminders do not increase response rates and the key measures are not impacted by reminders. Our panel management practices allow us to achieve representative samples without sending reminders.

About Lightspeed Research

Lightspeed Research (www.lightspeedresearch.com) is the market researcher’s choice for digitally accessing and deriving insight from consumer opinions and behaviors whenever, wherever and in whatever segments needed. The industry’s most thorough panelist prescreening process and large global pool delivers business-ready results quickly and costeffectively. From proprietary online access panels to specialty panels, custom panels and innovative mobile surveys, Lightspeed Research offers the industry’s highest-quality and most complete combination of qualitative and quantitative online research. This is backed by an expert client operations team that provides a range of data collection services, from sample management and survey design to programming and reporting. Part of Kantar, a division of WPP, Lightspeed Research serves clients and cultivates online panelists across the Americas, Europe and Asia Pacific.

Susan Frede is the VP of Research at Lightspeed Research. She has worked in the research field for 23 years, has published numerous research-on research papers and is a well-respected speaker at key industry events. Some of the topics she has recently explored include questionnaire length, best practices for online research, suspicious and professional respondents and data stability. You can contact Susan at sfrede@lightspeedresearch.com

Susan Frede, VP Research
November, 2008

Online research has become an accepted and widely used research methodology because of its benefits of lower cost and faster turnaround. As with any research methodology, it is important that online research produce stable, consistent results from test to test. Given the quick adoption of the online methodology in the U.S. concerns have emerged regarding the stability of online data and the ability to replicate results especially with concept tests. The goal of this research is to assess the stability of online research for collecting concept test data using the MySurvey Consumer Panel.

Background

Lightspeed Research has fielded two separate tests to address the question of stability:

• August 2006 Test – 10 concepts, both branded and unbranded, were tested from a variety of industry sectors. Nearly 6000 interviews were conducted with approximately 300 per concept per point in time.
• July/August 2007 Test – 20 branded consumer package goods concepts were tested. Nearly 17,000 interviews were conducted with approximately 400 per concept per point in time.

In both studies, each concept was tested monadically at two points in time with one week between the test and retest to minimize any potential impact from seasonality and market changes. The demographic universes were selected as appropriate for the product target market. Key concept measures included Purchase Intent, Uniqueness, Value, Liking, Believability, Quantity and Frequency. Respondents also were asked a number of category habit and brand usage questions.

Concept Purchase Intent

Purchase intent is the most important measure in concept testing. In both tests results are generally consistent between the two time periods, indicating stable results (see Table 1). Of the 60 statistical comparisons for purchase intent, 56 or 93% are not statistically different at the 95% confidence level (see Appendix for data). The small percentage of difference is well within the error expected from a probabilistic sample.

Other Key Measures

Similar to purchase intent, there are few statistically significant differences between the two time periods for the other key measures (see Table 2). Of the total comparisons 92% (380 out of 412) are not significantly different at the 95% confidence level. No sample is a perfect representation of the population of interest, which leads to some fluctuation in scores from sample to sample (random sampling error). Again, the small percentage of difference is well within the error expected from a probabilistic sample.

Demographics

Balancing outgoing samples on key demographic variables helps ensure representative return samples. In both tests, the return samples line up well between the waves on demographics. There are a few statistical differences, but no sample has differences across all the demographic variables and none is so skewed that key measures are impacted.

Category & Brand Usage/Purchase

Category and brand usage/purchase differences between samples can dramatically impact results. For example, having more users of a category in a sample can inflate key measure scores. Having samples that are demographically balanced reduces the potential for differences in category and brand usage/purchase thus producing more stable concept results. There are three category/brand usage differences between the waves: (See Appendix for data.) Those in wave 1 for Concept 10 are significantly more likely to be brand users. However, this does not impact key measure results because the concept is for a new variant of the product that current users are not likely to use. Those in wave 1 for Concept 20 are significantly more likely to be brand users. This does cause slightly, but not significantly higher purchase intent scores in wave 1. Those in wave 1 for Concept 24 are significantly more likely to be brand users. This is driving the purchase intent score differences for Concept 24.

It is important to examine all samples carefully to make sure category habits and brand usage fall within an acceptable range. When there are differences, weighting can bring imbalances in line.

Conclusions

This research demonstrates that Lightspeed Research produces stable concept test results with few statistically significant differences between time periods on key measures when utilizing the MySurvey Consumer Panel as a sample source. This research also points to the importance of careful evaluation of demographics, habits, and brand usage/purchase for each sample to identify any variations that could impact key measures.

Lightspeed Research provides stable concept test results because of our panel and sample management practices, which allow us to build samples that are representative of the population of interest on key demographic variables. Balancing on these key demographic variables reduces the chance of having category and brand usage differences between samples, which can drive differences in concept evaluations. The best way to guarantee stable results is to use professionally managed samples.

About Lightspeed Research

Lightspeed Research (www.lightspeedresearch.com) is the market researcher’s choice for digitally accessing and deriving insight from consumer opinions and behaviors whenever, wherever and in whatever segments needed. The industry’s most thorough panelist pre-screening process and large global pool delivers business-ready results quickly and cost-effectively. From proprietary online access panels to specialty panels, custom panels and innovative mobile surveys, Lightspeed Research offers the industry’s highest-quality and most complete combination of qualitative and quantitative online research. This is backed by an expert client operations team that provides a range of data collection services, from sample management and survey design to programming and reporting. Part of Kantar, a division of WPP, Lightspeed Research serves clients and cultivates online panelists across the Americas, Europe and Asia Pacific.

Susan Frede is the VP of Research at Lightspeed Research. She has worked in the research field for 23 years, has published numerous research-on-research papers and is a well-respected speaker at key industry events. Some of the topics she has recently explored include questionnaire length, best practices for online research, suspicious and professional respondents and data stability.
You can contact Susan at sfrede@lightspeedresearch.com

Susan Frede, VP Research

Overview

In recent studies, Lightspeed Research has observed an inverse relationship between questionnaire length and completion rates. Initial observations show decreasing completion rates as questionnaire length increases, and an increased number of respondent dropouts for lengthier surveys.

How can this affect your research? Lower completion rates and higher dropout rates may lead to lower quality data and can impact business decisions. Longer questionnaires also may cause respondent fatigue and poorer quality responses. In some cases, respondents may not give as much consideration to questions at the end of a long questionnaire as to questions at the beginning. When fatigued respondents take short-cuts in their thinking, researchers are left with response bias.

Key Research Questions

In June of 2008 Lightspeed Research fielded research-on-research to answer the following questions:

• How long is too long?
• What is the relationship between questionnaire length and dropout rates?
• Are certain types of questions more likely to cause dropouts?
• As questionnaires get longer, how does length impact the representivity of the sample?
• How are key measures impacted as questionnaire length increases?
• Are panelists less satisfied with the survey experience with longer questionnaires?
• Does suspicious behavior increase as questionnaire length increases?
• How many and what types of questions can be asked before exposure to a stimulus without impacting key measure scores?

Research Design

Six versions of a concept questionnaire were fielded for a new snack food idea. The length, as well as the order of the questions varied. The four main versions based on median completion time were:

• 8-minute questionnaire (ideal)
• 17-minute questionnaire
• 20-minute questionnaire
• 24-minute questionnaire

Two additional questionnaire versions asked extra screening questions prior to concept exposure. One version added approximately one minute and the other two minutes of interview time to the 8-minute questionnaire prior to concept exposure.

Response & Dropout Rates

Response rates are fairly consistent across the questionnaire lengths. However, dropout rates increase as questionnaire length increases.

Sample Representivity

Respondents dropping out are somewhat different demographically than those completing the entire survey. They are more likely to be older, retired, male and from smaller households without children. Those dropping out also are less likely to do all the grocery shopping and tend to purchase snack foods less often. Although the dropouts are different, they are so few in number that the overall sample is still representative when excluding them. Demographics, habits, and brand usage are generally consistent across the six questionnaire versions among those answering through at least purchase intent (the completion point). Thus, sample representivity does not appear to be impacted by questionnaire length.

Concept Measures

While questionnaire length does not impact sample representivity, it does have the potential to impact concept measures. In the Lightspeed Research study, the concept scores for the 8-minute questionnaire version tend to be higher than scores for the longer questionnaires. The 20- and 24-minute questionnaire versions receive significantly fewer “definitely would buy” ratings compared to the 8-minute version. There are also several significant differences on liking, value, uniqueness, and believability between the 8 minute version and the longer versions. (See Table 2 on the following page.) It is important to keep the number of questions prior to concept exposure to a minimum. There are several significant differences between the 8-minute questionnaire version and the two versions with the extra upfront questions.

Survey Satisfaction

In the Lightspeed Research study, the shortest questionnaire versions (8-10 minutes) are viewed as more fun while the longer versions (17-24 minutes) are more likely to be seen as boring. On the longest questionnaire version (24 minutes) respondents are less likely to agree that this survey “helps companies make products that better meet people’s needs.”

Respondents taking the longer questionnaire versions (17-24 minutes) are more likely to report that they found questions difficult to answer (6-7% vs. 4% for the shorter versions). Regardless of questionnaire length, the three most frequent questionnaire complaints are:

• Number and type of answer choices – Respondents want to give honest, accurate answers, but sometimes feel that is not possible with the answer choices provided. Researchers sometimes want to force respondents to express an opinion, but it is important to keep in mind that this can be frustrating for respondents. Several respondents suggest including ‘don’t know’ or ‘none’ as an answer choice. It is not a good idea to include these choices on every question because it provides an easy out. However, if a list is not exhaustive then a ‘don’t know’ or ‘none’ choice can be valid.
• Answering questions based solely on reading a description of the product – Researchers need to tell respondents to base their answers on what they read. The more specific questions are, the harder it is for respondents to answer. For example, asking respondents to rate the flavor or aftertaste is very difficult without having tried the product.
• No ability to skip questions that don’t apply – If a respondent doesn’t use the category that is the subject of the questions, asking him/her multiple category specific questions can become frustrating even when “don’t use” is an answer choice. Consideration should be given to skipping questions that do not apply.

Because this questionnaire includes a mix of questions and it concerns a product category that most people use, no respondents commented that the questionnaire is repetitive. However, in other research, we have seen comments that repetitive questions negatively impact overall survey enjoyment. Respondents don’t see the need for repeating questions. Interestingly, those who say a survey is repetitive are also more likely to say it is too long.

Suspicious Behavior

Respondents completing a longer questionnaire are no more likely than those completing a short one to be classified as suspicious (exhibiting fraudulent or inattentive behavior). But, when a large number of questions are placed at the beginning of the questionnaire, it does lead to more suspicious behavior. The 8-minute questionnaire version has fewer respondents straight-lining an attribute battery (giving the same rating to all attributes) that falls late in the questionnaire.

Respondents claiming to be members of eight or more panels have been identified as professional respondents. There does not appear to be a relationship between number of panels and questionnaire length.

Impact of Upfront Questions

As previously mentioned, there are differences in key concept measures (Table 2) and increases in suspicious behavior (Table 4) when the initial screening section of the questionnaire is longer. There are also some significant differences in habit and attitude questions when asked before, as opposed to after, concept exposure. Frequency of purchasing and eating snack foods tends to be higher when asked after concept exposure. Also, for four of thirteen attitude statements about nutrition, ratings are significantly higher after concept exposure. Exposure to the snack concept could be biasing results, however, care also needs to be taken in placing too many questions prior to concept exposure as those questions can bias the concept measures. This suggests that it is important to be consistent in where questions are asked in the questionnaire, so that any bias remains consistent from one project to the next. None of the screening questions on the 9- and 10-minute questionnaire versions causes a large number of respondents to drop out. However, based on past research-on-research, long grid questions or several grid questions in a row early in the survey generally cause more dropouts. The 10-minute questionnaire has a single grid question upfront with only 13 items. Lightspeed Research has also seen more respondents drop out on allocation questions. These questions generally ask respondents to indicate how many of their last 10 purchases were for each brand. The longer the brand list, the longer it can potentially take to complete this question. The 20-and 24-minute questionnaire versions do include a very simple allocation question (17 brands) and there are several dropouts on this question.

Conclusions

This research-on-research shows that there is a relationship between questionnaire length and dropout rates. Dropout rates increase as questionnaire length increases. Although respondents who drop out are different from those who complete the entire questionnaire, overall sample representivity is not impacted by questionnaire length. Questionnaire length does affect key concept measures, so business decisions could be impacted. Shorter questionnaires are viewed as more fun while longer questionnaires are seen as boring. Also, respondents are more likely to report having difficulty answering questions in the longer
versions. Although straight lining behavior is slightly higher among all but the shortest questionnaires, longer questionnaires don’t necessarily lead to more suspicious behavior. Longer questionnaires don’t tend to appeal more to professional respondents because those completing the longer questionnaires are not on a greater number of panels. Asking more questions prior to concept exposure can cause biased concept results. When more questions are asked upfront, respondents are less likely to continue after the screening portion of the questionnaire and are more likely to exhibit suspicious behavior.

Recommendations

So how long is too long? Concept test results are impacted starting around 20 minutes. Therefore, Lightspeed Research recommends keeping online questionnaire length under 20 minutes. With shorter questionnaires, respondents are more likely to stay engaged and Lightspeed Research is able to establish better rapport with our panelists. Better rapport leads to less attrition and better quality responses. Some suggestions for reducing questionnaire length:

• Carefully evaluate each questionnaire to eliminate “nice to know” questions (i.e. questions that don’t directly relate to the objectives and success criteria).
• Keep the number of questions asked prior to concept exposure to a minimum.
• Think about questions from the respondent’s point of view – if you were a respondent would you want to answer? For example:
  • Is it necessary to gather brand usage information down to nearly a SKU level? Can respondents accurately report this information?
  • Can respondents answer specific attribute questions about a product when all they have seen is a concept?
• Use technology to make questionnaires more respondent friendly (e.g. to skip questions that don’t apply).
• Watch out for repetitious questions. You may think you are asking different questions (e.g. product is healthy and product is good for you), but respondents often don’t see it that way.
• Consider using split questionnaire designs to break a long questionnaire into manageable tasks. The second questionnaire is fielded to those returning the first questionnaire. This makes the task a little less daunting for respondents while still gathering all the information from the same respondents.

About Lightspeed Research

Lightspeed Research (www.lightspeedresearch.com) is the market researcher’s choice for digitally accessing and deriving insight from consumer opinions and behaviors whenever, wherever and in whatever segments needed. The industry’s most thorough panelist prescreening process and large global pool delivers business-ready results quickly and costeffectively. From proprietary online access panels to specialty panels, custom panels and innovative mobile surveys, Lightspeed Research offers the industry’s highest-quality and most complete combination of qualitative and quantitative online research. This is backed by an expert client operations team that provides a range of data collection services, from sample management and survey design to programming and reporting. Part of Kantar, a division of WPP, Lightspeed Research serves clients and cultivates online panelists across the Americas, Europe and Asia Pacific. Susan Frede is the VP of Research at Lightspeed Research. She has worked in the research field for 23 years, has published numerous research-on-research papers and is a well-respected speaker at key industry events. Some of the topics she has recently explored include questionnaire length, best practices for online research, suspicious and professional respondents and data stability. You can contact Susan at sfrede@lightspeedresearch.com

Examines the potential impact of the invitation process –- in particular incentives and invitation wording – on online data collection.

Investigates and provides recommendations regarding the impact of questionnaire length on survey completion and response rates.

Presented at the ESOMAR Panel Research Conference in Barcelona
Findings based on a comprehensive review of several components of the online data collection process – particularly the invitation process –- and their impact on data integrity.

Published in the MRA’s Alert Magazine
An article focusing on the use of online data collection methods in political polling.

Presents the findings of how the timing of survey invitations influences certain demographics’ participation in online surveys.