1. Is there a correlation of touch ratios between convex and concave models?
Null hypothesis: There is no correlation of the touch ratios of different countries between the two different models, as the models are physically different from each other.
Method: using the circular mask for country shapes, only consider touches in the areas of the circles
cor(s$concave,s$convex) [1] 0.8974139
The correlation is very high!
Where is the object touched more - at the base or in the countrycircles? About 75% of the touches are in the countrycircles; there is relatively small variation across conditions and model type.
Now let’s look at much much the ring components were touched in each model in each condition. The touch ratios for each ring of the models seem also correlated across both models.
cor(g$concave,g$convex)[1] 0.7601623
2. How significant are the touch ratio differences between countries and models?
Linear regression of the touch ratio (using the circlemask) with countries as dummy variables with the model type (convex concave) and condition (1-3) as a controls.
The country is Italy, Norway, Spain, and United Kingdom are significantly less touched with Norway, having considerable effects (~8%). Condition 2 is on average 2% less touched.
seg_touch %>% lm(formula = touchratio_country ~ as.factor(convex) + country ) -> m1
summary(m1)
Call:
lm(formula = touchratio_country ~ as.factor(convex) + country,
data = .)
Residuals:
Min 1Q Median 3Q Max
-0.30792 -0.12418 -0.00365 0.10143 0.47819
Coefficients:
Estimate Std. Error t value Pr(>|t|)
(Intercept) 0.25942 0.02699 9.613 < 2e-16 ***
as.factor(convex)1 0.02482 0.01707 1.454 0.146779
countryItaly -0.16114 0.03621 -4.450 1.14e-05 ***
countryNorway -0.14367 0.03621 -3.968 8.72e-05 ***
countryPoland -0.00699 0.03621 -0.193 0.847021
countrySouth Korea -0.04264 0.03621 -1.178 0.239666
countrySpain -0.09502 0.03621 -2.624 0.009043 **
countrySwitzerland 0.02368 0.03621 0.654 0.513537
countryUnited Kingdom -0.13038 0.03621 -3.601 0.000361 ***
countryUnited States -0.01790 0.03621 -0.494 0.621439
---
Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
Residual standard error: 0.1659 on 368 degrees of freedom
Multiple R-squared: 0.1427, Adjusted R-squared: 0.1217
F-statistic: 6.806 on 9 and 368 DF, p-value: 4.642e-09
5. Do Participants speak while touching, or either speak or touch?
Laura separate analysis
6. Is there a correlation between amount of touch and the reasoning by the Participant?
Correctness, confidence, uncertainty. Which areas and features do participants feel uncertain about? For example, identifying categories was really tricky with the model, and made people unsure about the data
7. Qualitative analysis of uncertainty and touch behavior
Discussion of parts of the model that are very frequently touched, and takeaways about the design of the physicalization.
8. Where are people touching?
Which different kinds of touches do we observe, and how do they impact reasoning? Analysis Bernice.