Sign in

Sai Krishna

@thechaoticneuron.bsky.social
86 followers 12 following 78 posts

I do statistics 📈, writing ✍️ and acting 🎭 - in no certain order Here to become wiser with every post. d-saikrishna.github.io

PostsRepliesMedia
Sai Krishna @thechaoticneuron.bsky.social · 28/04/2025
Air is a public good and in any society with common sense, it should be a top government priority to provide clean air. Alas, as we wait for that common sense to dawn on us, let's at least mask up in the meantime. #SkySky AirQuality
020
Sai Krishna @thechaoticneuron.bsky.social · 21/03/2025
LogProbs is a cool Prompt Engineering skill. 🤖📈 #Statsky #Stats #AI #LLM medium.com/@saikrishna_...
medium.com
LogProbs
LogProbs is one of the basic skills for a Prompt Engineer to have.
000
Sai Krishna @thechaoticneuron.bsky.social · 06/03/2025
One key insight about the impact of LLMs on creative writing from Andrej Karpathy’s LLM Deepdive: medium.com/@saikrishna_... #AI 🤖📈 #LLM #WritingCommunity
medium.com
Will an AI joke land?
One key insight about the impact of LLMs on creative writing from Andrej Karpathy’s LLM Deepdive
000
Sai Krishna @thechaoticneuron.bsky.social · 22/01/2025
When I write stories, I ensure that I have the climax first with all its payoffs 😁
000
Sai Krishna @thechaoticneuron.bsky.social · 15/01/2025
#Poetry #TinyPoem
000
Sai Krishna @thechaoticneuron.bsky.social · 15/01/2025
Survey of 416 residents. The polling group has a sampling error of 3% in their familiar territories. 95% Confidence Interval falls below 50%. Yet the audacity/ignorance to claim that entire Greenland supports to be adopted by the US. 🏛️ #rstats #PASky 🤖📈 #Stats
030
Sai Krishna @thechaoticneuron.bsky.social · 10/01/2025
𝐖𝐡𝐞𝐧 𝐬𝐡𝐨𝐮𝐥𝐝 𝐲𝐨𝐮 𝐛𝐫𝐮𝐬𝐡 𝐲𝐨𝐮𝐫 𝐭𝐞𝐞𝐭𝐡? 1. Brush twice a day — Morning and Night after dinner. 2. Morning, it’s better to 𝐛𝐫𝐮𝐬𝐡 𝐚𝐟𝐭𝐞𝐫 𝐛𝐫𝐞𝐚𝐤𝐟𝐚𝐬𝐭. If you find it scandalous, read this blog! medium.com/@saikrishna_... #rstats #Stats #StatSky 🤖📈
medium.com
When to brush your teeth? A good ANOVA study!
I found this paper which did a simple ANOVA study to find out when should one brush their teeth!
041
Sai Krishna @thechaoticneuron.bsky.social · 06/01/2025
Don’t wanna be the best #Poetry #TinyPoem
000
Sai Krishna @thechaoticneuron.bsky.social · 03/01/2025
Greed #Poetry #TinyPoem
010
Sai Krishna @thechaoticneuron.bsky.social · 02/01/2025
Trident of endeavour Science works, finds truths Business pays, fulfils desires Power lies, frauds morals #Poetry #TinyPoem #haiku
010
Sai Krishna @thechaoticneuron.bsky.social · 01/01/2025
Happy New Year! #Poetry #TinyPoem
000
Sai Krishna @thechaoticneuron.bsky.social · 31/12/2024
Farts of a city #Poetry #TinyPoem #AirQuality
000
Sai Krishna @thechaoticneuron.bsky.social · 30/12/2024
Trying my hand at writing poems 🌝 Thanks to Douglas Kearney’s course! www.coursera.org/learn/poetry... #Poetry #TinyPoem
030
Sai Krishna @thechaoticneuron.bsky.social · 23/12/2024
TL;DR Paper tried to compare air quality between land cover classes using Kruskal Wallis tests link.springer.com/article/10.1... But practical significance seems neglected for statistical significance. What do you say? #Stats #rstats 🤖📈 medium.com/@saikrishna_...
medium.com
Statistical issues in this paper studying relation between air quality and LULC
A paper got published in Environmental Monitoring and Assessment. It studied relation between land-use classes (Urban, Shrubland, Forest…
020
Sai Krishna @thechaoticneuron.bsky.social · 19/12/2024
Grove air quality sensor + ESP8266 reporting indoor air quality to a google sheet every 10 minutes #IoT github.com/d-saikrishna...
010
Sai Krishna @thechaoticneuron.bsky.social · 18/12/2024
“Air quality data saves lives. Where air quality is reported, action is taken, and air quality improves.” Oh I so wish 🌝
010
Sai Krishna @thechaoticneuron.bsky.social · 17/12/2024
Which place is this?
000
Sai Krishna @thechaoticneuron.bsky.social · 17/12/2024
Depends on what we are doing with the data. A regression on it will optimise for global fit - thereby compromising predictions/inferences over the local imbalanced parts of the data. medium.com/@saikrishna_...
medium.com
Real estate broker working with Linear Regression on imbalanced data
I used Housing price data for this analysis. Previous blog based on the same dataset are:
110
Sai Krishna @thechaoticneuron.bsky.social · 16/12/2024
🏛️ Interesting argument on lack of democratic accountability 🏛️ osf.io/preprints/os... 1. It’s not the lack of awareness. But political partisanship is an obstacle to accountability. 2. Lack of social capital. Public support to policies that preserve public goods reduces if there is personal cost
023
Sai Krishna @thechaoticneuron.bsky.social · 15/12/2024
We wrote about gaps in monitoring data and its interpretation of air quality. urbanemissions.info/wp-content/u... Stats gaps of representativeness, selection bias etc., creep into these datasets. Media, policy making should consider them before forming opinions.
urbanemissions.info
000
Sai Krishna @thechaoticneuron.bsky.social · 14/12/2024
I’m assuming this is Python for Data Science - this is a good free course www.wqu.edu/adsl-apply
wqu.edu
WQU | Apply for the Applied Data Science Lab
Join the Applied Data Science Lab: Access application, online program requirements, course and certificate information, FAQs, and more.
020
Reposted by Sai Krishna
Nabeel Siddiqui @nabsiddiqui.bsky.social · 13/12/2024
This is my yearly reminder that published results of coefficients using logistic regression in Python are likely wrong because they are L2 penalized by default: github.com/scikit-learn... #rstats #statistics #digitalhumanities
github.com
Suggestion: Add support for unpenalized logistic regression · Issue #6738 · scikit-learn/scikit-learn
LinearRegression provides unpenalized OLS, and SGDClassifier, which supports loss="log", also supports penalty="none". But if you want plain old unpenalized logistic regression, you have to fake it...
0114
Sai Krishna @thechaoticneuron.bsky.social · 13/12/2024
If I ask you to forecast pollution in Delhi on some random day, you'd say a number X If I further ask you to forecast on a Winter Day, you'd top up X with some y This is Bayes theorem running in your head. This blog attempts to quantify it medium.com/@saikrishna_... #rstats #stats 🤖📈
medium.com
Bayesian probabilistic forecasts using categorical information | Part 1
In this blog, I will make Bayesian forecasts of Ozone concentrations.
0100
Sai Krishna @thechaoticneuron.bsky.social · 13/12/2024
I wrote a book in Telugu where I addressed a few harmful beliefs (astrology, homeo, superstitions, biases) using basic stats concepts. This blog of mine is one such attempt. medium.com/@saikrishna_...
medium.com
Bayesian Feminist
My friend believes that women are bad employees.
030
Sai Krishna @thechaoticneuron.bsky.social · 12/12/2024
In a Gaussian distribution. An uninformative prior need not have any closed bounds. So MLE would be identical to Bayesian estimate. But give a closed bound (say mean height is uniformly distributed but within 100-200 cm) — Bayesian posterior estimates will consider this close bound — not MLE
000
Sai Krishna @thechaoticneuron.bsky.social · 12/12/2024
No answers :/ Anyways. Even without an uninformative prior, we provide a bounded prior in a Bernoulli trial. P(p) = 1 (when 0<=p<=1) P(p)=0 (otherwise) So the bayesian estimates are informed of this bounded nature of p. The MLE doesn’t consider that. Hence the difference. #rstats #stats 🤖📈
100
Sai Krishna @thechaoticneuron.bsky.social · 11/12/2024
Yes. I mentioned uniform prior. Should have mentioned mean estimate as well. But the question remains! Why mle estimate is different for a Bernoulli trial. Mle estimate of mean and Bayesian estimate (mean of posterior with gaussian prior) is the same for a normal distribution
000
Sai Krishna @thechaoticneuron.bsky.social · 11/12/2024
Quiz time! Why is the Maximum Likelihood Estimate (MLE) of probability of success (p) in a Bernoulli trial not equal to the Bayesian Estimate? p_mle = r/n p_bayesian = (r+1)/(n+2) (Assuming uninformative prior) r = number of successes n = number of trials #rstats #stats 🤖📈
121
Sai Krishna @thechaoticneuron.bsky.social · 11/12/2024
So if x^2 is the confounder, adding x to the model may not completely remove the Omitted Variable Bias 😬😬😬 Seems obvious now. But wow, that’s an interesting thing! Makes causal inference more complex
021
Sai Krishna @thechaoticneuron.bsky.social · 10/12/2024
😂😂😂😂😂😂
000
Sai Krishna @thechaoticneuron.bsky.social · 09/12/2024
𝐖𝐡𝐚𝐭 𝐢𝐬 𝐢𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧? It impinges on a thinking mind and makes it change its opinion. How should this change be affected? 𝐁𝐀𝐘𝐄𝐒 𝐓𝐇𝐄𝐎𝐑𝐄𝐌. 𝐓𝐡𝐞 𝐥𝐢𝐤𝐞𝐥𝐢𝐡𝐨𝐨𝐝 𝐟𝐮𝐧𝐜𝐭𝐢𝐨𝐧 𝐠𝐞𝐧𝐞𝐫𝐚𝐭𝐞𝐝 𝐛𝐲 𝐭𝐡𝐞 𝐝𝐚𝐭𝐚 𝐢𝐬 𝐭𝐡𝐞 𝐈𝐧𝐟𝐨𝐫𝐦𝐚𝐭𝐢𝐨𝐧 - an extract from an autobiographical essay of statistician Debabrata Basu #stats #rstats 🤖📈
020
Sai Krishna @thechaoticneuron.bsky.social · 08/12/2024
Can we ‘determine’ if the coin toss would result in a head or a tail? Yes, if he know the mass of the coin, density, weather conditions, initial force of the spin, initial face up, position of impact etc. That’s a deterministic view. A frequentist will report 50% chance.
110
Sai Krishna @thechaoticneuron.bsky.social · 07/12/2024
Freshly published: Assessing Air Quality during India’s National Clean Air Programme (NCAP) www.sciencedirect.com/science/arti...
sciencedirect.com
Assessing Air Quality During India’s National Clean Air Programme (NCAP): 2019-2023
Did air quality improve during India’s National Clean Air Programme (NCAP)? Since its inception in 2019, 131 cities were designated as non-attainment …
022
Sai Krishna @thechaoticneuron.bsky.social · 07/12/2024
You can scroll down to find more meanings as well :) I don’t want to be pedantic here. But you should look up deterministic models that have correlated variables. Have a good weekend! 🕺
000
Sai Krishna @thechaoticneuron.bsky.social · 07/12/2024
I did. And correlated variables (without causation) are part of “deterministic” models. Them not being “causes” didn’t stop them from being part of deterministic modes. Because “to determine” is sometimes to decide something. And many correlations help in decisions, even if they’re not causes.
110
Sai Krishna @thechaoticneuron.bsky.social · 07/12/2024
But deterministic models are not necessarily causal models. If I can determine that X happens when Y happens, even if Y is not the cause, then it’s a deterministic model. A lot of physical models are framed that way.
110
Sai Krishna @thechaoticneuron.bsky.social · 05/12/2024
🏛️ A good read for policy folks 🏛️
000
Sai Krishna @thechaoticneuron.bsky.social · 05/12/2024
Fitting data is easier than fitting thoughts in 300 characters? :p
010
Sai Krishna @thechaoticneuron.bsky.social · 05/12/2024
Hello Adrian... you should use #rstats or #stats or 🤖📈 to make your posts appear in relevant feeds. I've done it for you now :)
110
Sai Krishna @thechaoticneuron.bsky.social · 04/12/2024
How can a causal variable become useless in prediction? 100% Mediation in Action! medium.com/@saikrishna_... #rstats #stats #Statistics 🤖📈
medium.com
100% Mediation in Action
I wrote about Mediators in the previous blog. This is a follow-up blog to it.
022
Sai Krishna @thechaoticneuron.bsky.social · 04/12/2024
Time to revise “Value of Science” essay by Richard Feynman calteches.library.caltech.edu/1575/1/Scien...
calteches.library.caltech.edu
000
Sai Krishna @thechaoticneuron.bsky.social · 03/12/2024
Color codes are not very important if you follow the text :)
010
Sai Krishna @thechaoticneuron.bsky.social · 02/12/2024
🏛️ Wonderful work 🏛️
021
Sai Krishna @thechaoticneuron.bsky.social · 02/12/2024
Cofounder causal diagram will become mediator causal diagram when we turn it. Both variables will be needed to get the unbiased effect of the Mediator. Mediator should be removed to get the unbiased effect of Confounder. #Stats is absurd at times :p #rstats 🤖📈 medium.com/@saikrishna_...
240
Sai Krishna @thechaoticneuron.bsky.social · 02/12/2024
Funny thing is cofounder causal diagram will become mediator causal diagram when we turn it. Both variables will be needed to get the unbiased effect of the Mediator. Mediator should be removed to get the unbiased effect of Confounder. Stats seem absurd at times :p medium.com/@saikrishna_...
000
Sai Krishna @thechaoticneuron.bsky.social · 02/12/2024
I wrote one piece on Omitted Variable Bias. medium.com/@saikrishna_... This seems like a good idea though to use the same style to explain confounders and mediators. Will think about that!
medium.com
Omitted Variable Bias (OVB)
You performed a regression between house prices and area and obtained a coefficient (β) for area.
031
Sai Krishna @thechaoticneuron.bsky.social · 01/12/2024
Anyone on this space who worked on Forest Cover Density (fcd) calculations using landsat images?
000
Sai Krishna @thechaoticneuron.bsky.social · 01/12/2024
Wrote a short story about a very important hobby :) dsaikrishna.substack.com/p/retire
dsaikrishna.substack.com
Retire
It has been a month since Padmakshi resigned.
000
Sai Krishna @thechaoticneuron.bsky.social · 01/12/2024
My articles on medium are free. Strange that it is asking for payment.
000
Sai Krishna @thechaoticneuron.bsky.social · 30/11/2024
Visualize Collider Bias with me. Wrote this for myself. To get an intuitive understanding of Collider bias without any regression equations and lines. Hope it helps other learners as well! medium.com/@saikrishna_... #stats #rstats
medium.com
Visualize Collider Bias with me
It’s 2020. You are a doctor. COVID19 has just picked up. You are going to face a flood of patients today.
74611