Datasets used in Dr. Ma's courses. Each dataset includes a brief description and direct download links.
CCST Data for Norming
This section contains the Cognitive Complexity in Scientific Thinking dataset for norming and the full dataset version.
Use this data for score norming, comparative analyses, and instructional research on scientific thinking outcomes.
Chinese character size test (CCST) data
Description:
The Chinese character size test (CCST) is an open-access standardized test that measures children's character recognition, the character size of simplified Chinese. The formal CCST includes five booklets respectively designed for primary school students in grades 1-6. Each booklet consists of 150 multiple-choice and dichotomously-scored items that require students to select the correct Chinese character from homophonic, morphologically-related, or semantically-related distractors based on audio materials.
The CCST were assembled using the vertical equation design. Each booklet includes 60 to 75 item characters learned during the current grade, 0 to 15 characters from previous grades, and 60 to 90 characters from the next grades. There are at least 40 anchor items between adjacent booklets, allowing for comparable test scores across test forms and grades. Besides, this test assembly design could reduce the probability of students answering items that are too difficult or too easy, and improve the overall test discrimination. The CCST has no time limit. The average test time was 11.13 minutes, and 98.61% of students completed the test within 16 minutes. Therefore, the CCST can be easily administered to primary school students in a group setting.
Key features of the Chinese character size test.
Test Features
Descriptions
Score/Interpretation
The Chinese character size reflects the number of Chinese characters that participants recognised during reading or listening activities.
Participants
Mandarin Chinese students in grade 1-6 (age range: 6-13).
Completion Time
Between 5-16 minutes, an average of 11.13 minutes.
Quantity of Items
150 items in a single booklet, 525 items in the item bank.
Reliability
The Cronbach's alpha reliability of the formal CCST booklets was 0.93, ranging from 0.91 to 0.95.
Validity
Construct validity, Criterion-related validity
Reference Types
Criterion-referenced and norm-referenced. The Chinese character size score is aligned with the Compulsory Education Language Curriculum Standards issued by the Chinese Ministry of Education and can be used to assess whether primary school students' character sizes are compatible with the educational objectives of the three key stages of education, i.e., by the end of Grade 2, 4, and 6, students should know at least 1,600, 2,500, and 3,000 Chinese characters, respectively. The norm sample consisted of 7,459 primary school students from 20 schools using the probability proportional to size (PPS) sampling method, representing approximately 980,000 primary school students in Beijing as a whole.
Test Frequency
Yearly (recommended)
Administration
Computer-based assessment, compatible with Inquisit software.
Benefits
Measure chinese character size with reference to the national curricumlum criterion.
Contribute useful information when assessing character recognition, as part of a language evaluation, throughout the primary school years.
Directly compare character size with norm references.
Format:
The CCST data include anonymized demographic information, Chinese character recognition (CR), character size, reading ability, Chinese language exam scores, and item-leveled test data of 7459 primary school students.
CCST_data_norm.csv contains demographic information and character size variable.
CCST_data.csv contains more information.
The data were retrieved from https://osf.io/ktf5c/ on Aug 6, 2025. More information can be found in Li, et al. (2025).
References
Li, Y., Wei, Y., & Li, H. (2025). Chinese character size test: Test development, validation, and standards-referenced norms for Chinese primary students. Behavior Research Methods, 57(6), 155.
Course Survey Data
Course survey responses collected for teaching and learning analytics. The data file is paired with a codebook and original survey form,
making it suitable for classroom evaluation, survey methods practice, and psychometric exercises.
ECPE dataset for educational and psychological measurement analyses. This file can be used to practice dimensionality checks,
item-level modeling, and score interpretation workflows.
Examination for the Certificate of Proficiency in English (ECPE) data
Description:
Examination for the Certificate of Proficiency in English (ECPE) data (the grammar section) has been used in Henson and Templin (2007), Templin and Hoffman (2013), Feng, Habing, and Huebner (2014), and Templin and Bradshaw (2014), among others.
Format:
Binary responses of 2922 examinees to 28 items.
1 - correct response
0 - incorrect response
References
Henson, R. A., & Templin, J. (2007, April). Large-scale language assessment using cognitive diagnosis models. Paper presented at the annual meeting of the National Council for Measurement in Education in Chicago, Illinois.
Templin, J., & Bradshaw, L. (2014). Hierarchical diagnostic classification models: A family of models for estimating and testing attribute hierarchies. Psychometrika, 79, 317-339.
Templin, J., & Hoffman, L. (2013). Obtaining diagnostic classification model estimates using Mplus. Educational Measurement: Issues and Practice, 32, 37-50.
Big Five Inventory (BFI) Data
25 personality self report items taken from the International Personality Item Pool (ipip.ori.org) were included as part of the Synthetic Aperture Personality Assessment (SAPA) web based personality assessment project. The data from 2800 subjects are included here as a demonstration set for scale construction, factor analysis, and Item Response Theory analysis. Three additional demographic variables (sex, education, and age) are also included.
The data were retrieved from psych R package.
Big Five Inventory (BFI) data
Description:
This section contains two files from a Big Five personality dataset.
- bfi.csv: item-level responses for Big Five domains (Agreeableness, Conscientiousness, Extraversion, Neuroticism, Openness) with demographic variables (gender, education, age).
- bfi_scored.csv: scored trait means for the same five domains.
Format of bfi.csv:
A data frame with 2800 observations on the following 28 variables. (The q numbers are the SAPA item numbers).
A1
Am indifferent to the feelings of others. (q_146)
A2
Inquire about others' well-being. (q_1162)
A3
Know how to comfort others. (q_1206)
A4
Love children. (q_1364)
A5
Make people feel at ease. (q_1419)
C1
Am exacting in my work. (q_124)
C2
Continue until everything is perfect. (q_530)
C3
Do things according to a plan. (q_619)
C4
Do things in a half-way manner. (q_626)
C5
Waste my time. (q_1949)
E1
Don't talk a lot. (q_712)
E2
Find it difficult to approach others. (q_901)
E3
Know how to captivate people. (q_1205)
E4
Make friends easily. (q_1410)
E5
Take charge. (q_1768)
N1
Get angry easily. (q_952)
N2
Get irritated easily. (q_974)
N3
Have frequent mood swings. (q_1099
N4
Often feel blue. (q_1479)
N5
Panic easily. (q_1505)
O1
Am full of ideas. (q_128)
O2
Avoid difficult reading material.(q_316)
O3
Carry the conversation to a higher level. (q_492)
O4
Spend time reflecting on things. (q_1738)
O5
Will not probe deeply into a subject. (q_1964)
gender
Males = 1, Females =2
education
1 = HS, 2 = finished HS, 3 = some college, 4 = college graduate 5 = graduate degree
age
age in years
Reliability Data
Three reliability-focused files are provided: alternative forms, parallel forms, and test-retest data.
These support demonstrations of reliability estimation, agreement studies, and longitudinal consistency checks.
Student response data for fraction subtraction tasks, including a full form and a 10-item subset.
This dataset is useful for item analysis, learning progression studies, and instructional diagnostics in mathematics education.
Fraction Subtraction (FS) data
Description:
Fraction Subtraction data (Tatsuoka, 1990, 2002) consists of responses of 536 examinees to items measuring fraction subtraction skills. Below are the items and skills measured.
Format:
Binary responses of 536 examinees to 20 (or 10) items.
1 - correct response
0 - incorrect response
References
Tatsuoka, K. K. (1990). Toward an integration of item-response theory and cognitive error diagnosis. In N. Frederiksen, R. Glaser, A. Lesgold, & M. Shafto (Eds.), Diagnostic monitoring of skill and knowledge acquisition (pp. 453-488). Hillsdale, NJ: Erlbaum.
Tatsuoka, C. (2002). Data analytic methods for latent partially ordered classification models. Journal of the Royal Statistical Society, Series C, Applied Statistics, 51, 337-350.
Holzinger and Swineford (1939) Dataset
Classic factor analysis dataset frequently used in measurement and SEM courses.
It is ideal for demonstrating CFA, model fit, and latent variable interpretation with a well-known historical dataset.
Holzinger and Swineford (1939) dataset
Description
The classic Holzinger and Swineford (1939) dataset consists of mental ability test scores of seventh- and eighth-grade children from two different schools (Pasteur and Grant-White). In the original dataset (available in the MBESS package), there are scores for 26 tests.
However, a smaller subset with 9 variables is more widely used in the literature (for example in Joreskog's 1969 paper, which also uses the 145 subjects from the Grant-White school only).
This dataset is retrieved from lavaan R package.
Variable
Description
x1
Visual perception
x2
Cubes
x3
Lozenges
x4
Paragraph comprehension
x5
Sentence completion
x6
Word meaning
x7
Speeded addition
x8
Speeded counting of dots
x9
Speeded discrimination straight and curved capitals
References
Holzinger, K. J., & Swineford, F. (1939). A study in factor analysis: The stability of a bi-factor solution. Supplementary Educational Monographs, no. 48. Chicago: University of Chicago, Department of Education.
Housing Data
This dataset includes 311 public housing residents from six public housing projects. Two projects were high-rise
buildings for seniors and individuals with disabilities, and four projects were for families. The data come from
a study of public housing relocations in Atlanta (Oakley, Ruel, and Wilson, 2008; Ruel, Oakley, Wilson, and Maddox, 2010).
LIVES daily hassles data from multiple waves, supporting cross-wave comparisons and longitudinal analyses.
The included paper provides research context for variables and design choices.
LIVES-Daily Hassles Scale (LIVES-DHS) data
Description:
The LIVES-DHS consists of 18 items represented by five factors that describe five sources of daily hassles: financial, physical, relational, environmental, and professional. The LIVES-DHS was collected in Wave 6 (2017) of a data collection from a 7-year longitudinal study on professional paths conducted at the Swiss National Centre of Competence in Research-Overcoming Vulnerabilities: Life Course Perspective (NCCR LIVES). See Udayar, et al. (2023) for more information.
Format:
Respondents are asked to indicate the extent to which a series of possible daily hassles concerned them on a 5-point Likert-type scale (1 = not at all, 2 = a little, 3 = it does not concern me, 4 = somewhat, 5 = very much).
The original data were retrieved from https://osf.io/6zvud/ on August 6, 2025. Two sub-datasets were created using the R code below:
data=df[,c("T6_Gender",colnames(df)[startsWith(colnames(df),"T6_daily")])]
data$sample <- df$`filter_$`+1
data=data[which(!is.na(data$sample)),]
write.csv(data,"LIVES-DHS-W6.csv",row.names = F)
data7=df[,startsWith(colnames(df),"T7_daily")]
data7 <- data7[complete.cases(data7),]
write.csv(data7,"LIVES-DHS-W7.csv",row.names = F)
The data has 22 items. Four of them (i.e., items 12, 20,21 and 22) were removed.
There are five factors:
SF = ~ T6_dailyhassles_1 + T6_dailyhassles_2 + T6_dailyhassles_3
SR = ~ T6_dailyhassles_8 + T6_dailyhassles_9 + T6_dailyhassles_10 + T6_dailyhassles_11
SPr = ~ T6_dailyhassles_16 +T6_dailyhassles_17 + T6_dailyhassles_18 + T6_dailyhassles_19
Sph = ~ T6_dailyhassles_4 + T6_dailyhassles_5 + T6_dailyhassles_6 + T6_dailyhassles_7
SE = ~ T6_dailyhassles_13 + T6_dailyhassles_14 + T6_dailyhassles_15
where SF = financial source; SPh= physical source; SPr = professional source; SR = relational source; SE= environmental source.
In LIVES-DHS-W6.csv, sample=1 for EFA sample and sample=2 for CFA sample used in Udayar, et al. (2023).
References
Udayar, S., Urbanaviciute, I., Morselli, D., Bollmann, G., Rossier, J., & Spini, D. (2023). The LIVES daily hassles scale and its relation to life satisfaction. Assessment, 30(2), 348-363.
Multiple-Choice Item Data
Item response data from multiple-choice assessments. This file supports demonstrations of distractor behavior,
item quality diagnostics, and classical or modern item analysis methods.
Multiple choice item data
Description:
This example data contains 20 unscored multiple-choice items with 100 examinees. This data is obtained from CTT R package.
Format:
Multiple-choice responses of 100 examinees to 20 items. Each item has four options: A, B, C and D.
Below is the answer key:
i1 = "D", i2 = "A", i3 = "A", i4 = "D", i5 = "D",
i6 = "A", i7 = "D", i8 = "B", i9 = "D", i10 = "A",
i11 = "A", i12 = "D", i13 = "C", i14 = "C", i15 = "B",
i16 = "C", i17 = "D", i18 = "A", i19 = "A", i20 = "B"
Note that in the above answer key, one item is mis-keyed.
References
Willse JT (2018). CTT: Classical Test Theory Functions_. doi:10.32614/CRAN.package.
R package version 2.3.3
Rosenberg Self-Esteem Scale (SES) Data
This dataset includes responses to the 10-item Rosenberg Self-Esteem Scale with response coding details.
The complete description from the SES folder is included below.
Rosenberg Self-Esteem Scale (SES) data
Description:
The data were collected online with an interactive version of the Rosenberg Self-Esteem Scale.
The following items were rated on the following scale where 1=strongly disagree, 2=disagree, 3=agree, and 4=strongly agree:
1. I feel that I am a person of worth, at least on an equal plane with others.
2. I feel that I have a number of good qualities.
3. All in all, I am inclined to feel that I am a failure.
4. I am able to do things as well as most other people.
5. I feel I do not have much to be proud of.
6. I take a positive attitude toward myself.
7. On the whole, I am satisfied with myself.
8. I wish I could have more respect for myself.
9. I certainly feel useless at times.
10. At times I think I am no good at all.
Note. Items 3, 5, 8, 9 and 10 were reversely coded. 0 indicate no answer or missing data.
2001 Technology Survey
Dataset and codebook for the 2001 technology survey retrieved from here.
Video Game Dependence Scale data are available in both 80-item and 26-item forms.
This section supports scale development exercises, short-form validation, and structural comparisons across forms.
Video Game Demand Scale (VGDS) data
Description:
The Video Game Demand Scale was developed by Bowman, et al. (2018). This data consists of a total of N = 660 participants gave complete answers to the 80 VGDS pool items-20 for each different type of demand-by consulting the literatures reviewed earlier in this manuscript, consulting existing open-ended data from past data collections to cull players' natural language about demand, and through deliberation within the research team. This 80-item bank was randomized and presented to participants, with items written in Likert-style with seven response options from "Strongly Disagree" to "Strongly Agree."
Format:
After a series of EFA, Bowman, et al. (2018) retained a 5-factor solution with 26 items, in which cognitive, emotional, and social demand factored in line with reviewed literature, and physical demand was factored into only two dimensions reflecting controller demand and physical exertion, respectively.
- The cognitive demand dimension items are principally about directed and purposeful thinking-perhaps most directly capturing the mental and rational aspects of video game play. the retained items are more closely aligned with the extent to which a game engages the player's mental faculties-like the notion of attentional demand
- The emotional demand involves items with colloquial references to game-induced affect is notable: the game tugged on heartstrings and gave me the feels. These items coalesced with items reflecting perceived player-centered emotions (being emotionally invested, moved, and having emotional responses) and context-centered emotions (in that emotions ran high and that emotions were unexpected).
- Two different types of physical demand emerged in the data, with game controls being very natural, second nature, and easy to handle being more associated with the discrete controller device (controller demand) and being physically exhausted and feeling drained after gameplay that seem to focus more holistically on involving the entire body in physical activity (exertional demand).
- The social demand factor similarly comprised items indicating a convergence of items representing both game-induced sociality (it was an important part of the game) and player-initiated sociality (feeling obligated to others), as well as items suggestive of both explicit awareness of and response to others through concrete influences (they had an impact on how I played) and more heuristic assessments of their influence that may suggest more implicit social demand (being aware of others)
Description of the original 80 items (boldfaced items were retained after EFA, with factor name in parathesis):
COG1 - The game left me mentally exhausted.
COG2 - The game involved a lot of problem-solving.
COG3 - The game was cognitively demanding. (Cog)
COG4 - I had to think very hard when playing the game. (Cog)
COG5 - The game required a lot of mental gymnastics. (Cog)
COG6 - The game was confusing to me.
COG7 - The game's challenges were very clear to me.
COG8 - It was very easy to comprehend this game.
COG9 - The mental challenges in this game had an impact on how I played. (Cog)
COG10 - This game doesn't require a lot of mental effort. (Cog)
COG11 - I was able to figure that game out quickly.
COG12 - When playing this game, my brain felt overloaded.
COG13 - This game made me question my own intelligence.
COG14 - It took a lot of thinking to understand the point of the game.
COG15 - This game was unexpectedly complicated.
COG16 - I didn't have to pay very close attention to the game while playing.
COG17 - The game made me draw on all of my mental resources. (Cog)
COG18 - The game required me to keep track of a lot of things.
COG19 - The game stimulated my brain. (Cog)
COG20 - I had to think through what was happening in the game.
EMOT1 - I was emotionally exhausted after playing the game.
EMOT2 - I was emotionally invested in the game.
EMOT3 - The game really got to me.
EMOT4 - The game gave me the feels. (Emotional)
EMOT5 - I cared deeply about what was happening in the game.
EMOT6 - I was moved by the game. (Emotional)
EMOT7 - I wasn't emotionally invested in the outcomes of the game.
EMOT8 - When playing, I was emotionally wrapped up in the game.
EMOT9 - I had emotional responses to the events in the game.
EMOT10 - My emotions ran high while playing this game.
EMOT11 - The game tugged at my heartstrings. (Emotional)
EMOT12 - I had a lot of unexpected feelings during gameplay. (Emotional)
EMOT13 - I felt emotionally detached from this game.
EMOT14 - The events in the game really didn't matter to me.
EMOT15 - Things happening in the game weren't relevant to me.
EMOT16 - I had a strong emotional bond with the game content. (Emotional)
EMOT17 - Playing the game got me riled up.
EMOT18 - I'm passionate about the game.
EMOT19 - I felt conflicted about things that happened in the game.
EMOT20 - The emotions that I felt while playing this game had an impact on how I played.
PHYS1 - I was physically exhausted after playing. (Exertional demand)
PHYS2 - I felt strained after playing. (Exertional demand)
PHYS3 - The game required a lot of physical movement from me.
PHYS4 - The game's controls were like second nature to me. (Controller demand)
PHYS5 - The controls were very natural to me. (Controller demand)
PHYS6 - The controls felt like an extension of me.
PHYS7 - My body felt drained after gameplay. (Exertional demand)
PHYS8 - I had a difficult time finding different game controls when I needed to.
PHYS9 - The game was physically relaxing for me.
PHYS10 - The game controls were easy to handle for me. (Controller demand)
PHYS11 - The game was physically demanding. (Exertional demand)
PHYS12 - The game required very little input from me.
PHYS13 - The game controls tripped me up. (Controller demand)
PHYS14 - I felt a lot of physical discomfort when playing.
PHYS15 - I was physically overwhelmed when playing the game.
PHYS16 - The game required constant input from me.
PHYS17 - I was tired after playing this game.
PHYS18 - The physical requirements to play this game had an impact on how I played.
PHYS19 - I had to do a lot of things simultaneously while playing this game.
PHYS20 - I felt rushed while trying to play this game.
SOC1 - After playing the game, I just felt like I needed to be alone.
SOC2 - This game was socially demanding. (Social)
SOC3 - While playing, I was aware of others in the game. (Social)
SOC4 - I felt that I was constantly being watched while playing.
SOC5 - This game was unexpectedly social for me.
SOC6 - During gameplay, I felt strong social connections with others.
SOC7 - I felt pressure to have relationships with others in the game.
SOC8 - I felt obligated to others, while playing. (Social)
SOC9 - I felt taxed after being around others in the game.
SOC10 - It took a lot out of me to be around others in the game.
SOC11 - The social connections in this game were very energizing to me.
SOC12 - When playing, I could feel the presence of others around me.
SOC13 - I was compelled to interact with others in the game. (Social)
SOC14 - I was exhausted after having so many social interactions in this game.
SOC15 - I was concerned with how I interacted with others in the game.
SOC16 - I cared a lot about what others thought of me in the game.
SOC17 - Being around others in the game had an impact on how I played. (Social)
SOC18 - I didn't notice any others while playing the game.
SOC19 - The game placed a priority on social relationships.
SOC20 - Socializing was an important part of playing this game. (Social)
The data were retrieved from https://osf.io/x5jch on Aug 7, 2025, and processed with the following R code:
HS=VGDS[,1:80]
colnames(HS)=c(paste0("COG",1:20),paste0("EMOT",1:20),paste0("PHYS",1:20),paste0("SOC",1:20))
write.csv(HS,"vgds.csv",row.names = F)
References
Bowman, N. D., Wasserman, J., & Banks, J. (2018). Development of the video game demand scale. In Video games (pp. 208-233). Routledge.
Complete Description (VGDS-G 26-item)
Video Game Demand Scale (VGDS) data
Description:
The Video Game Demand Scale was developed by Bowman, et al. (2018). The Germany version was developed by Koban and Bowman (2021). The data consisted of N = 560 participants (M = 24.83 years, SD = 4.38, range: 18-63 years) with n = 137 identifying themselves as female (24.5%), n = 404 as male (72.1%), and n = 19 who decided not to specify their biological sex (3.4%). Players were recruited at a mid-sized German university via a campus-wide email invitation.
Format:
The original VGDS consisted of 26 items loading onto five factors: cognitive, emotional, physical (broken into controller demands and physical exertion), and social demands. Items were answered on a 7-point Likert scale (1 = strongly disagree, 7 = strongly agree), in response to the participants most recent gaming experience.
Description of the 26-item scale:
Cognitive (COG)
- COG1 - The game was cognitively demanding.
- COG2 - I had to think very hard when playing the game.
- COG3 - The game required a lot of mental gymnastics.
- COG4 - This game doesn't require a lot of mental effort.
- COG5 - The game made me draw on all of my mental resources.
- COG6 - The mental challenges in this game had an impact on how I played.
- COG7 - The game really stimulated my brain.
Emotional (EMOT)
- EMOT1 - The game tugged at my heartstrings.
- EMOT2 - The game gave me the feels.
- EMOT3 - I was moved by the game.
- EMOT4 - I had a strong emotional bond with the game content.
- EMOT5 - I had a lot of unexpected feelings during gameplay.
Control (CON) (Assumed as a control-related physical dimension)
- CON1 - The controls were very natural to me.
- CON2 - The game's controls were like second nature to me.
- CON3 - The game controls were easy to handle for me.
- CON4 - The game controls tripped me up.
Physical (PHY)
- PHY1 - I was physically exhausted after playing.
- PHY2 - I felt strained after playing.
- PHY3 - My body felt drained after gameplay.
- PHY4 - The game was physically demanding.
Social (SOC)
- SOC1 - Socializing was an important part of playing this game.
- SOC2 - While playing, I was aware of others in the game.
- SOC3 - I was compelled to interact with others in the game.
- SOC4 - I felt obligated to others, while playing.
- SOC5 - Being around others in the game had an impact on how I played.
- SOC6 - This game was socially demanding.
The data were retrieved from https://osf.io/x5jch on Aug 7, 2025. The datafile contains 560 participants from Germany and 660 participants from U.S. (indicated by GROUP variable).
References
Bowman, N. D., Wasserman, J., & Banks, J. (2018). Development of the video game demand scale. In Video games (pp. 208-233). Routledge.
Koban, K., & Bowman, N. D. (2021). Further validation and cross-cultural replication of the video game demand scale. Journal of Media Psychology: Theories, Methods, and Applications, 33(1), 39-48. https://doi.org/10.1027/1864-1105/a000280
Food Choices and Preferences of College Students
This dataset includes information on food choices, nutrition, preferences, childhood favorites, and other
information from college students. There are 126 responses from students.
Food Choices and Preferences of College Students
Description:
This dataset includes information on food choices, nutrition, preferences, childhood favorites, and other information from college students. There are 126 responses from students.
The dataset was retrieved from https://www.kaggle.com/datasets/borapajo/food-choices