What do People prefer and What is more effective for Maps: a Decision making Test - Advances in Cartography and GIScience - page 175

and magazine maps. It would be desirable in the future to ask respondents
about familiarity with spatial data, and to ask them to describe situations in
which they usually encounter and make use of maps.
The Kruskal-Wallis tested the null hypothesis that the medians of the two
task results within each of the three levels of map preference are the same.
Since the P-value is greater than or equal to 0.05, there is not a statistically
significant difference between the medians at the 95.0% confidence level.
Therefore, it can be assumed that map preference does not influence the
results achieved.
Figure 6: Map preference
3.2 Direct acquisition task
The Kruskal-Wallis test proves that there is a statistically significant dif-
ference between the medians of the direct acquisition task results and the
experimental groups. The multiple comparison procedure by LSD ( Table
2 ) indicates that the choropleth maps group and range-graded proportional
symbol maps group achieved similar results, which are statistically differ-
ent from the dot maps group. The absolute results for the direct acquisition
task results ( Figure 7 ) show a slightly worse performance by the dot maps
group for this specific task when compared to the other two groups.