Publications by Justin Flattery
HW 1 - 603 Justin Flattery
Homework 1 My HW 1 for 603 Justin Flattery 2022-02-23 knitr::opts_chunk$set(echo = TRUE) Question 1 For each procedure we will construct a confidence interval around our estimate of the actual mean by fitting the sample about a t distribution. We can do this since we have the sample mean, sample size (thus degrees of freedom) and sample sta...
5607 sym R (1276 sym/45 pcs)
Homework 2
Homework 2 Homework 2 Justin Flattery 2022-03-10 knitr::opts_chunk$set(echo = TRUE) library('smss') library('alr4') 1 1.1.1 Predictor variable is ppdg and response variable is fertility 1.1.2 plot(x = UN11$ppgdp, y = UN11$fertility) A straight line mean function does not seem to be plausible for a summary of this graph. It appears to be...
3262 sym R (2242 sym/19 pcs) 7 img
Homework 3 603
Homework 3 My HW 3 for 603 Justin Flattery 2022-03-31 knitr::opts_chunk$set(echo = TRUE) library('smss') library('alr4') library(smss) 1 A. ŷ = −10,536 + 53.8x1 + 2.84x2. -10536 + (53.8*(1240)) + (2.84*(18000)) [1] 107296 Residual: 145000 - 107296 [1] 37704 B. For each square foot increase, there is an increase in price of $53.80...
3880 sym R (4832 sym/35 pcs)
Blog Post 6 - Text as Data
Blog Post 6 - Text as Data Justin Flattery 2022-05-10 My focus of this blogpost will be showing the updates to my project, particularly using LDA and STM modeling to create segmented topics from my corpus of proposed Covid-19 legislation. I want to note I am attaching R outputs as images for this blog due to the crashing topic modeling was c...
4165 sym 4 img
Homework 4
Homework 4 603 My HW 4 for 603 Justin Flattery 2022-05-02 Part 1 1) For backward elimination, beds will be deleted first because it has the highest p value For forward selection, size will be the first variable added because it has the highest significance (with p value = 0) I believe this is because the correlation between beds and price i...
2290 sym R (5196 sym/60 pcs) 3 img
Blog Post 5
Blog Post 5 My Blog Post 5 for Text as Data Justin Flattery 2022-04-10 knitr::opts_chunk$set(echo = TRUE) Blog Post 5 My goal for this blog post is to dig deeper into the descriptive analysis of my current corpus, specifically the bills summary for Covid legislation. I first, looked to remove words from my word cloud in Blog post 4 that see...
1490 sym R (5353 sym/37 pcs)
Blog Post 6 - Text as Data
Blog Post 6 Justin Flattery 2022-04-24 My focus of this blogpost will be showing the updates to my project, particularly using LDA and STM modeling to create segmented topics from my corpus of proposed Covid-19 legislation. First, using a k of 10 topics I created the following list of the most frequently used words for each topic. lda_model$...
1751 sym 3 img