final graphs for dissertation

tables and graphs of 3 cities and 4 stages

A webpage of a few graphs that is helpful to have in the background while reading chapter one.

Added control variable for age and one for the age of housing stock. Graphs and maps

working copy incase of trouble

Contains graphs of variables for each of seven class for three texas cities

Graphs of main variables for Chapter one

table of means and graphs of race/ethnicity, education and mhhinc

worked on cleaning data, model selection, and exploring the classification of different neighborhoods

Added three new contextual variables. PCA, seven dimensions. Did LPA with five classes and mapped to three cities

introduced a new variable. looked at scale versus moms in LPA. mapped out some data

Adding population and ln pop to LPA analysis

Maps, PCA => LPA => more maps => gentrification

maps of final data

Made some progress in the coding world. This is an update of my initial push with the data from Austin. It's pretty ruff.

word cloud of crystal's text datas

Lab that covers mainly cleaning and tidying data utilizing the 2015 5 yr ACS data from IPUMS

cleaning data

working with two different projections to show the distance between points in each projection differ

This HW examined cox ph model and discrete time analysis using 5 waves of the PSID from 2005 through 2013

Examining 3 waves of PSID data to determine if those who were displaced are at greater risk of moving from good to poor health. Used kaplan meier survival functions and PH parametric models

2017 PSID data group variable states, checking outcome health vs age, race, education and health

basic mlm using PSID 2017, exploring median income by state

mean, modal and multiple imputation

PCA on the subject of gentrification as a latent construct. Focused on the city of San Antonio

investigating poisson and negative binomial distributions for count data (i.e. how often something occurs with a given time period) as well as the need for offsets and overdispersion

This HW explores both nesting and stratification using BRFSS 2017 data. Variables: DV=health, predictors=race, education, income and marital status.

Logit Models, odds ratios and prevalence rates

Dem 7283 HW1 examining survey weights and there effects on full survey design

MCMC BRM and INLA fairly basic comparison dependent variable income 3 models 3/5 covariates

Used individual (gender and race) and group level (poverty level) predictors to see the effect on the graduating High School

Fitting model with random slopes and random intercepts

European Social Survey data set. Used dichotomous dependent variable and linear mixed model to investigate the variation between genders of immigrants who originated from different regions of the world