bmkramer / 101innovations-survey-data

Stringing beads - identifying research workflows from tool usage data (clustering)
11 stars 5 forks source link

Workflows - Which tools are used together across the research workflow #5

Open bmkramer opened 8 years ago

bmkramer commented 8 years ago

Which tools are used together (across the research workflow)

Relation with https://github.com/bmkramer/101innovations-survey-data/issues/6

RMHogervorst commented 8 years ago

I've added a script that calculates frequencies

https://github.com/bmkramer/101innovations-survey-data/blob/master/frequencies_of_bivariate_tool_use.R

bmkramer commented 8 years ago

Added csv file with co-occurrence frequencies of all 136 preset tool options, generated by the script made by Roel https://github.com/bmkramer/101innovations-survey-data/blob/master/survey_presets_frequencies.csv

RMHogervorst commented 8 years ago

New idea: perform some sort of categorical principal components analyses with the homals package or equivalent. or a latent class analysis. PCA is a dimension reduction technique. and latent class analysis searches for a hidden (latent) classification that explains the observed patterns.