The R Markdown document provides code that simulates 5 eigenvalues for 3 different tests assuming unidimensionality. Then, corresponding scree plots are produced, including a horizontal line at eigenvalue = 1 for reference.

The R Markdown document provides code that simulates individual responses on 20 items for 1000 respondents. Specifically, responses are simulated differently depending on membership to one of three groups (of sizes 800, 150, and 50). Two versions of line plots are created to display percentage correct for each group across the 20 items. The second version of the plot includes error bands around each line to visualize standard error.

The R Markdown document provides code that simulates ability estimates for two groups on three different tests. Cut-scores for four proficiency categories is simulated for the three tests, as well. Two different versions of density curve plots are constructed that plot filled density curves along with cut-score lines. One plot plots separate density curves for the two different groups.

The R Markdown document provides code that simulates student responses based on simulated abilities and item characteristics (assuming a 2PL model). Response data was simulated for 20 items and 4,000 respondents for three different testing scenarios. The first test is assumed to have no DIF. The second test assumes DIF for three items due to some group membership (G1). The third test makes a similar assumption of DIF for three items due to another group membership (G3). Uniform and nonuniform types of DIF are used in various combinations. A function is then created to fit logistic regression models for assessing both types of DIF, as well as overall DIF, and extract the results into a master data frame. Then, some final cleaning is done and flagged items are filtered and displayed into unique data frames.

The R Markdown document provides code that simulates percentage correct across three response options for 30 items for 3 multiple-choice tests. Then, percentage correct is visualized using two different plots. A heat map is used for visualizing percentage endorsement of all response options across items and tests. Colors are used to distinguish the correct response options from the others and intensity of color is used to reflect percentage. A lollipop plot is used to visualize percentage correct on a horizontal axis. Individual points are color-coated by whether percentage correct exceeded or fell below 50%.

The R Markdown document provides code for simulating score distributions, item difficulties (for two item types) and cut-scores for three separate tests. The simulated data is then used to construct Wright plots that put score distributions and difficulties on the same axis, while integrating cut-scores, different item types, and differing units for the secondary axis.

The R Markdown document provides code that simulates 30 2PL items and 3 cut-scores for 3 separate tests. A set of plots are then created that display points two-dimensionally by their a and b parameter estimates. Points are also color-coated to reflect which cut-score they provide the most information for as well as flagging low-information items.

The R Markdown document provides code for generating CSEM plots across multiple tests. Three different SEM trends are created, along with simulated cut-scores. The plots contain line plots of SEM as a function of scale score, along with vertical dashed lines denoting cut-scores.

The R Markdown document provides code for simulating a sampling distribution of a sample mean. Then, the following plots are constructed related to the sampling distribution: an animated plot showing the distribution slowly build, a final static plot of the simulated distribution, and two colored plots reflecting two probability statements regarding sample means.

The R Markdown document provides code for simulating samples from a constructed population distribution. Then, four plots are made that include histograms and overlayed density curves.

The R Markdown document provides code for generating power probability plots for demonstrating the relationships between power and its various factors. This is done using one-sample Z-test as the example hypothesis test. Factors considered include effect size, significance level, sample size, standard deviation, and one-tailed vs. two-tailed testing.

The R Markdown document provides code and corresponding figures demonstrating two ways of animating the gradual construction of a histogram. There is also code demonstrating how to animate changes in distributions when doing simple transformations on a data set.

The R Markdown document provides code and output related to simulating confidence intervals differing by confidence level and sample size. Designed for demonstrating performance of confidence intervals when varying the factors of confidence level and sample size.

The R Markdown document provides code and output related to simulating fair and weighted coin tosses. Designed for demonstrating behavior of probabilities in both the short-term and long-term.