Messages that increase COVID-19 vaccine acceptance: Evidence from online experiments in six Latin American countries

Abstract

As safe and effective vaccines become widely available, attaining herd immunity and limiting the spread of COVID-19 will depend on individuals choosing to vaccinate-and doing so quickly enough to outpace mutations. Using online surveys conducted across six Latin American countries in January 2021, we experimentally assess messages designed to counteract informational deficiencies and collective action problems that may drive hesitancy. We first find that basic vaccine information persuades around 8% of hesitant individuals to become willing to vaccinate, reduces intended wait to vaccinate by 0.4 months, and increases willingness to encourage others to vaccinate. Rather than facilitating free riding, learning, or social conformity, additional information about others' behavior increases vaccine acceptance when respondents expect herd immunity will be achieved. Finally, priming the social approval benefits of vaccinating also increases vaccine acceptance. These results suggest that providing information and shaping social expectations and incentives could both significantly increase vaccine uptake.

Fig 1. Overview of survey flow and treatment assignments.

The n refers to the number of respondents that reach a given box. The full survey questionnaire is included in S18 Appendix.

Fig 2. Distribution of vaccine willingness across countries (January 11–29, 2021).

The questions for each figure were asked at the beginning of the survey of all participants. Observations are weighted to match the joint distribution over education, sex, region, and age category from the most recent census in each country (a) “If a vaccine were available to me now, I would get vaccinated.” (b) “If a vaccine were available to you now, how many months would you wait before getting vaccinated?”.

Fig 3. Reasons for initial vaccine hesitancy and response to vaccine information treatments.

Panel (a) reports the percentage of hesitant respondents that chose each reason for hesitancy from a multi-response list. Panel Panel (b) reports the percentage of respondents that received a vaccine information treatment that chose each reason when asked how the vaccine information affected their concerns about COVID-19 vaccines. The exact questions and responses are shown in S18 Appendix.

Fig 4. Average effects of any vaccine information treatment on vaccine willingness, by country.

Each bar depicts a group outcome mean. The outcome in panel (a) is a five-point vaccine willingness scale ranging from “strongly disagree” (1) to “strongly agree” (5); the outcome in panel (b) is an indicator for “agree” or “strongly agree”; the outcome in panel (c) is the (reversed) number of months that a respondent would wait to get vaccinated once eligible for a vaccine; and the outcome in panel (d) is an indicator for a respondent being “somewhat likely” or “very likely” to encourage others to get vaccinated. Error bars denote 95% confidence intervals for treatment effects relative to the control group; the associated p values are from two-sided t tests. The underlying regression specifications for each outcome are described in S3 Appendix and the underlying regression table is reported in S6 Appendix.

Fig 5. Average effects of vaccine information variants on vaccine willingness.

Each bar depicts a group outcome mean, with the sample size in each group reported below. The outcome in panel (a) is a five-point vaccine willingness scale ranging from “strongly disagree” (1) to “strongly agree” (5); the outcome in panel (b) is an indicator for “agree” or “strongly agree”; the outcome in panel (c) is the (reversed) number of months that a respondent would wait to get vaccinated once eligible for a vaccine; and the outcome in panel (d) is an indicator for a respondent being “somewhat likely” or “very likely” to encourage others to get vaccinated. Error bars denote 95% confidence intervals for treatment effects relative to the control group; the associated p values are from two-sided t tests. The underlying regression specifications for each outcome are described in S3 Appendix and the underlying regression table is reported in S6 Appendix.

Fig 6. Effects of currently expected willingness information on vaccine willingness, by whether current willingness is above or below the expert herd immunity opinion a respondent was exposed to.

(a) Vaccine willingness scale. (b) Willing to take a vaccine. (c) Months would wait to get vaccinated. (d) Encourage others to get vaccinated. Each bar depicts a 95% confidence interval for the conditional average treatment effect of receiving the currently expected national willingness rate treatment, relative to just receiving an expert herd immunity opinion; the associated p values are from two-sided t tests and n captures the number of respondents in each subgroup. The outcome variables arrayed along the x axis are: a five-point vaccine willingness scale ranging from “strongly disagree” (1) to “strongly agree” (5); an indicator for “agree” or “strongly agree”; the (reversed) number of months that a respondent would wait to get vaccinated once eligible for a vaccine; and an indicator for a respondent being “somewhat likely” or “very likely” to encourage others to get vaccinated. The underlying regression specifications for each outcome are described in S3 Appendix and the underlying regression table is reported in S6 Appendix.

Fig 7. Average effects of motivational messages on vaccine willingness.

Each bar depicts a group outcome mean. The outcome in panel (a) is a five-point vaccine willingness scale ranging from “strongly disagree” (1) to “strongly agree” (5); the outcome in panel (b) is an indicator for “agree” or “strongly agree”; the outcome in panel (c) is the (reversed) number of months that a respondent would wait to get vaccinated once eligible for a vaccine; and the outcome in panel (d) is an indicator for a respondent being “somewhat likely” or “very likely” to encourage others to get vaccinated. Error bars denote 95% confidence intervals for treatment effects relative to the control group; the associated p values are from two-sided t tests. The underlying regression specifications for each outcome are described in S3 Appendix and the underlying regression table is reported in S6 Appendix.