Publications by Ellise Suffill
CEL_pairwise_n_bootstrap
CEL: This script includes stuff for generating pairwise comparisons of all possible pairs of participants within conditions (Baseline, No labels, With labels), and includes the baseline alignment for each pairing. load packages/data + set up library(lme4) library(lmerTest) library(tidyverse) library(dplyr) data <- read.csv(file="~/Desktop/CEL_c...
13531 sym R (21817 sym/55 pcs) 3 img
SAL_cluster
SAL clusters set up ## ## Attaching package: 'dplyr' ## The following objects are masked from 'package:stats': ## ## filter, lag ## The following objects are masked from 'package:base': ## ## intersect, setdiff, setequal, union ## [1] SAL_101b SAL_103b SAL_104b SAL_105b SAL_106b SAL_107b SAL_108b SAL_109b ## [9] SAL_110b SAL_111b SAL...
1242 sym R (46864 sym/78 pcs) 88 img
CEL_ICC
Sorting ICC analysis #this part uses the Euclidean distances from the sorting task to examine agreement across sorters #within the baseline, no labels and with labels conditions. #Focusing on ICC2 = Single random raters ##split by training*labels group and run ICCs #BASELINE type ICC F df1 df2 p lower bound upper bound ICC1 0.036 2.153...
310 sym 3 tbl
CEL_cluster_composition
Load and munge Load helper functions and libraries library(tidyverse) ## ── Attaching packages ─────────────────────────────────────── tidyverse 1.3.0 ── ## ✔ ggplot2 3.2.1 ✔ purrr 0.3.3 ## ✔ tibble 2.1.3 ✔ dplyr 0.8.3 ## ✔ tidyr 1.0.0 ...
3612 sym R (39835 sym/83 pcs) 5 img
CEL_category_distance
Useful summary function for within-subject variation ## Gives count, mean, standard deviation, standard error of the mean, and confidence interval (default 95%). ## data: a data frame. ## measurevar: the name of a column that contains the variable to be summariezed ## groupvars: a vector containing names of columns that contain grouping var...
495 sym R (32043 sym/33 pcs) 1 img
CEL_combined_category_distance
WITHIN VS BETWEEN CATEGORY DISTANCES IN SORTING (CATEGORICALITY) In sorting, are within-category item distances smaller than between-category item distances? And how does this relate to condition? in-lab All conditions are sensitive to category structure (smaller within- than between-category item distances), but this effect is most pronounced i...
4620 sym R (22267 sym/32 pcs) 8 img
CEL_combined_xAB
CEL xAB/Match-to-sample Side by side analysis for in-lab and online variants of CEL xAB/match-to-sample Req packages: library(lme4) library(lmerTest) library(dplyr) library(Rmisc) library(ggplot2) library(ggthemes) library(directlabels) library(ggpubr) library(kableExtra) Load in data from in-lab and online studies Remember that the in-lab match...
9429 sym R (13437 sym/30 pcs) 6 img
CEL_combined_purity
Script to load and compare in-lab and online cel data for: > A or B prototype purity > Likelihood of clustering by distortion of item (typ_pair) A / B PROTOTYPE CLUSTER ‘PURITY’ Essentially we use likelihood of clustering w prototype but for within only (i.e., ‘other’/between-category comparisons removed), and focused on main effect of C...
3953 sym R (19412 sym/21 pcs) 7 img
CEL_combined_alignment
CATEGORY ALIGNMENT (WITHIN CONDITION COMPARISONS) In sorting, how similar are people’s sorts within conditions, and how does this vary across conditions? in-lab With labels people have significantly more similar sorts than do Baseline or No labels people. Baseline and No labels people do not significantly differ in alignment. in-lab plot in-...
1270 sym R (16371 sym/16 pcs) 3 img
CEL_combined_alignment~categoricality
ALIGNMENT ~ CATEGORICALITY Does individual categoricality predict average alignment in-lab Significant effect of categoricality on alignment (increased categoricality tends to predict increased avg alignment). Main effects of condition but this doesn’t interact with categoricality. in-lab distribution of cluster number by condition in-lab mo...
1518 sym R (6886 sym/11 pcs) 5 img