8Using the performance package for item discrimination
Rather than using our own home made functions, we can use the performance package to calculate item discrimination. This is a package that is designed for psychometrics, and has a number of useful functions for calculating item statistics.
library(performance)library(tidyverse)
8.1 Dichotomous items
# load in the datasetresponses <-read_csv('data/responses.csv')# select the columns we wantresponses <- responses %>%select(contains('_score'))
# load in the datasetresponses <-read_csv('data/pc-data.csv')# drop the first six columnsresp <- responses %>%select(-c(1:6))# choose the columns that start with C1_resp_c1 <- resp %>%select(starts_with('C1_'))
# load in the dataset# get the item statspoly_item_stats <- performance::item_reliability(resp_c1)knitr::kable(poly_item_stats)
term
alpha_if_deleted
item_discrimination
C1_1ai
0.850
0.147
C1_1aii
0.848
0.296
C1_1bi
0.851
0.105
C1_1bii
0.848
0.276
C1_1biii
0.846
0.355
C1_1biv
0.847
0.396
C1_1ci
0.846
0.370
C1_1cii
0.842
0.479
C1_1di
0.848
0.284
C1_1dii
0.846
0.364
C1_1e
0.839
0.543
C1_1eSPaG
0.845
0.433
C1_2ai
0.845
0.375
C1_2aii
0.848
0.273
C1_2bi
0.850
0.135
C1_2bii
0.848
0.291
C1_2biii
0.849
0.254
C1_2biv
0.843
0.455
C1_2bv
0.843
0.463
C1_2c
0.837
0.606
C1_2d
0.841
0.506
C1_3ai
0.840
0.536
C1_3aii
0.848
0.291
C1_3aiii
0.844
0.408
C1_3bi
0.850
0.117
C1_3bii
0.843
0.437
C1_3ci
0.845
0.384
C1_3cii
0.838
0.563
C1_3d
0.841
0.503
Andrich, David, and Ida Marais. 2019. “The Idea of Measurement.” In A Course in Rasch Measurement Theory, 3–11. Springer Nature Singapore. https://doi.org/10.1007/978-981-13-7496-8_1.
Bond, Trevor G., Zi Yan, and Moritz Heene. 2020. Applying the Rasch Model: Fundamental Measurement in the Human Sciences. Routledge. https://doi.org/10.4324/9780429030499.
Cappelleri, Jason Lundy, J. C. 2014. “Overview of Classical Test Theory and Item Response Theory for the Quantitative Assessment of Items in Developing Patient-Reported Outcomes Measures.”Clinical Therapeutics 36 (5): 648–62. https://doi.org/https://doi.org/10.1016/j.clinthera.2014.04.006.
Cronbach, Lee J. 1951. “Coefficient Alpha and the Internal Structure of Tests.”Psychometrika 16 (3): 297–334. https://doi.org/10.1007/bf02310555.
Goldstein, H., and Steve Blinkhorn. 1982. “The Rasch Model Still Does Not Fit.”British Educational Research Journal 8 (2): 167–70. https://doi.org/10.1080/0141192820080207.
Lord, Frederic M, and Melvin R Novick. 2008. Statistical Theories of Mental Test Scores. IAP.
McNeish, Daniel. 2018. “Thanks Coefficient Alpha, We’ll Take It from Here.”Psychological Methods 23 (3): 412–33. https://doi.org/10.1037/met0000144.
Panayides, Panayiotis, Colin Robinson, and Peter Tymms. 2010. “The Assessment Revolution That Has Passed England by: Rasch Measurement.”British Educational Research Journal 36 (4): 611–26. https://doi.org/10.1080/01411920903018182.
Sijtsma, Klaas. 2008. “On the Use, the Misuse, and the Very Limited Usefulness of Cronbach’s Alpha.”Psychometrika 74 (1): 107–20. https://doi.org/10.1007/s11336-008-9101-0.
Wright, Benjamin D, and Magdalena Mok. 2000. “Rasch Models Overview.”Journal of Applied Measurement 1 (1): 83–106.