Epidemiology & Technology

Search site

Search Results

CVAT Install behind Nginx Reverse Proxy and CSRF Mitigation

I recently installed CVAT on a local VM. CVAT uses docker and installs a local Traefik container within the VM. The docs give instructions on how to run it on domain with free SSL by LetsEncrypt, but these docs assume that SSL termination happens on Traefik reverse proxy. However, In

September 10, 2024

Understanding Cataract Prevalence and Operated variables in RAAB

black flat screen computer monitor

There are various ways that cataract can be defined when analysing data from RAAB surveys. Here, I review the RAAB Analysis R scripts to understand how it is being done in the autogenerated tables. Understanding the case_when syntax This syntax is used very commonly for creating new variables based on

Using RAAB6/RAAB7 Analysis R scripts on Desktop

The RAAB team has provided the analytic scripts on the GitHub repo. Once you download the scripts, you need some configuration on your desktopn to be able to use them. First is obviously you need to install R package. You also need to install pandoc [from here] Then you need

Survival Analysis in Stata

Cheat-sheet DETAILS A Key concept in survival analysis is ANALYSIS TIME. All analyses are performed in terms of time since becoming at risk, called analysis time. Subjects are exposed at t = time = 0 and later fail. Observations with t = time <= 0 are ignored because information before

Some resources for Stata Graphs

Apart from the routine, you can create some interesting graphs

Deviance and Deviance ratio in Logistic models

Once you start using logistic regression and have come beyond the basic model, you will start going into model diagnostics and comparison of model performances across various peculations for a specific outcome. you will then start coming across concepts of deviance and deviance ratios. Let us understand briefly, how to

Stata customised tables of Regression results

Person Pointing Paper Line Graph

Stata added collect and enable suite of commands. I am discovering them now having migrated to Stata 18 from Stata 15. Useful Links Sample Output for etable using Collect suite SAMPLE OUTPUT for Collect

Global Estimates of Blindness and Visual Impairments

Data from various global estiamates are summarized here for easy reference: Link to my personal google sheet: https://docs.google.com/spreadsheets/d/1iTgBmRA4VwWE1fzRKA1YD1fzzMvn90Vu/edit?usp=sharing&ouid=113111648583609130450&rtpof=true&sd=true Pascolini, 2010 NUMBERS (millions)WorldIndiaPopulation6737.901181.40Visual Impairment ( PVA < 6\18)285.3962.62Blindness (PVA < 3\60)39.378.08Low Vision (< 6\18-3\60)246.0254.54PREVALENCE (1000 per million population)WorldIndiaVisual Impairment ( PVA < 6\18)42.3653.00Blindness (PVA < 3\60)5.846.84Low Vision (< 6\18-3\60)36.5146.17 20102010GLOBALGLOBALBlindness PVA

LASSO in Stata

Crossvaldiation By default, stata will select model with highest lambda. By default, stata fits up to 100 models with varying lambdas. The model with largest out of sample r-square and minimum CV mean prediction error gets selected by cross-validation LASSO commands SSC Addons based methods Stabdard Lasso estimation commands Lasso

Stata and ML resources

ai generated, artificial intelligence, big data

Some links to Stata and ML resources Conference Articles / Presentations / Stata Journal Stata Blog Articles from 2020 Other Resources Seven Steps in developing a prediction model Source: Towards better clinical prediction models: seven steps for development and an ABCD for validation - PMC (nih.gov)