Publications by Gabriel Rodriguez
Lab 1 STAT 415
1 Introduction This lab will walk you through some of the code for performing a simulation like the one in Handout 1, and a spreadsheet analysis like the one in Handout 2. You will also start to explore the influence of changing priors. Important note regarding code: We will cover code for performing and summarizing Bayesian analyses in much more...
18604 sym R (5654 sym/43 pcs) 12 img 5 tbl
Lab 2 STAT 415
1 Introduction In the handouts we have focused on inference for a population proportion. This lab will introduce you to another of the most common problems in statistics: inference for a population mean of a numerical variable. You will apply a process similar to what we covered in handouts to perform Bayesian inference for a population mean. Thi...
32990 sym R (11992 sym/91 pcs) 6 img 4 tbl
Lab 3 STAT 415
1 Introduction In the handouts we have focused on inference for a population proportion. This lab will continue Lab 2 and cover inference for a population mean of a numerical variable. In particular, this lab covers: Predictive distributions for a numerical variable Continuous prior and posterior distributions for a population mean As in Lab 2,...
23312 sym R (7995 sym/51 pcs) 10 img 2 tbl
Investigation 2 - STAT 415
This RMarkdown file provides a template for you to fill in. Read the file from start to finish, completing the parts as indicated. Some blank “code chunks” are provided; you are welcome to add more (CTRL-ALT-I) as needed. There are also a few places where you should type text responses. Feel free to add additional text responses as necessary....
15771 sym R (11559 sym/100 pcs) 8 img 1 tbl
Lab 5 STAT 415
1 Introduction You should start by reading Section 10 of the textbook. All of Bayesian inference is based on the posterior distribution of parameters given sample data. Therefore, the main computational task in a Bayesian analysis is computing, or approximating, the posterior distribution. We have seen three ways to compute/approximate the poster...
10156 sym R (5100 sym/21 pcs) 5 img
Lab 7 STAT 415
1 Introduction Most interesting statistical problems involve multiple unknown parameters. For example, many problems involve comparing two (or more) populations or groups based on two (or more) samples. In such situations, each population or group will have its own parameters, and there will often be dependence between parameters. We are usually ...
25304 sym R (9227 sym/42 pcs) 16 img 1 tbl
Lab 5 STAT 415
1 Introduction Bayes factors can be used as part of a Bayesian approach to null hypothesis testing. However, Bayes factors can be highly sensitive to choice of prior. Also, rejecting a point null hypothesis (e.g., \(H_0:\theta = 0.5\)) is hardly ever an interesting or meaningful conclusion. Rather, the posterior distribution provides all relevant...
12218 sym R (4079 sym/29 pcs)
STAT 415 Final Project Code
set.seed(314) Priors Truncated Normal Prior hist(((vix$CLOSE / 100)^2)/252, col = "lightblue",breaks = 50, main = "Realized Volatility of VIX Index", xlab = "Daily ReaL Vol") z = rtruncnorm(10000, a = 0, b = Inf, mean = 0, sd = .003) hist(z, col = "lightblue", main = "Truncated Normal Prior Distribution w/ Mu = 0 & SD = .003", xlab = "Logarit...
278 sym R (5424 sym/20 pcs) 13 img