# Scientific Visualization

### Approximation of sin(x) function with Gaussian Kernel

In this visualization, Gaussian Kernel model is implemented to approximate values of a given function sin(x). In other words, for a given range of x values, Gaussian Kernel model allows to predict values of sin(x). It can be oberved that approximated and sin(x) values are very close to each other. This plot was designed using `ggplot2`

.

Code is available here.

### Gibbs Sampling Convergence

This is a visualization of two parameters, variance and mean, which were sampled from their respective conditional posterior distributions until convergence. The upper plots show the trajectories of sampled Markov Chains. The lower plots show the number of iterations required to reach convergence for each parameter. This plot was designed using `ggplot2`

.

Code is available here.

This plot was created in collaboration with Kristina Levina.

### MCMC Convergence of Parameters

In this visualization, Markov chain Monte Carlo (MCMC) algorithm is used to draw parameters of Poisson regression from a multivariate posterior distribution. After approximately 250 iterations, the parameters start to converge. This plot was designed using `ggplot2`

.

Code is available here.

This plot was created in collaboration with Kristina Levina.