Skip to main content

Table 2 Flashbulb recall test regression results for CONPAS survey data

From: Addressing recall bias in (post-)conflict data collection and analysis: lessons from a large-scale health survey in Colombia

 

(1)

(2)

(3)

Conflict intensity level

Not affected

Ref.

Ref.

Ref.

Villavicencio

0.0194 (0.0512)

0.0687 (0.0505)

0.0568 (0.0462)

Lightly affected

0.1064 (0.0541)

0.0666 (0.0465)

0.0639 (0.0420)

Heavily affected

0.0997** (0.0370)

0.0608 (0.0371)

0.0549 (0.0351)

Control variables

Demographics

No

Yes

Yes

Population density

No

Yes

Yes

Event importance

No

No

Yes

  1. Demographics include sex, age and education. Event importance refers to the responses to the questions “How clearly do you recall Colombia's participation in the 2014 FIFA Football World Cup in Brazil?” and “At that time, how much importance did you attach to the event of Colombia's participation in the 2014 FIFA Football World Cup in Brazil?”, included as categorical variables for each response option. **p < 0.05, ***p < 0.01. Taylor-linearized standard errors in parentheses account for complex survey sample design