![Equitable Equations](/img/default-banner.jpg)
- 396
- 1 812 407
Equitable Equations
United States
Приєднався 11 бер 2020
Hi everybody! I'm Andrew Gard, a professor of mathematics and computer science at Lake Forest College, just north of Chicago, USA, where I teach statistics in R to beginning, intermediate, and advanced students. I started this channel because I believe that statistics and data science can be empowering and liberating for everyone.
Proceeds of this channel always benefit equity-based community organizations. Currently I'm supporting Chicago Scholars (chicagoscholars.org/). Please join me!
Proceeds of this channel always benefit equity-based community organizations. Currently I'm supporting Chicago Scholars (chicagoscholars.org/). Please join me!
Poisson regression in R
Let's model counts using R! If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Переглядів: 733
Відео
Poisson regression
Переглядів 79221 день тому
Poisson regression is used to model counts, like the number of viewers for vids on UA-cam, Let's get into it! If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Deviance in logistic regression models
Переглядів 762Місяць тому
Why isn't it a great idea to use residual sum of squares to assess logistical models? I'll explain and then show you some better options. If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Simple linear regression in R
Переглядів 1,3 тис.Місяць тому
A simple introduction to simple linear regression suitable for a first stats class that uses R, like mine at Lake Forest College. If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Not-so-simple linear regression with R
Переглядів 4,6 тис.2 місяці тому
Simple linear regression isn't so simple! We'll do a test/train split, build and diagnose a model, consider p-values, look for influential points, make predictions, compute root mean squared error, and more. This is a deep dive! If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Bibliographies with R and Quarto
Переглядів 1,2 тис.2 місяці тому
Today I'm using BibDesk to generate a bibliography file for use in a Quarto document. Easy! If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Beautiful tables with the gt package
Переглядів 3,3 тис.3 місяці тому
Clean, clear tables may not be glamorous, but they're *so* important. Let's get into it! If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Cross references in R and Quarto
Переглядів 1 тис.3 місяці тому
It's easy to reference a figure, table, or equation in a Quarto document. I'll show you how! If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Beautiful presentations with R and Quarto
Переглядів 3,6 тис.3 місяці тому
Beyond the basics! We'll talk about transitions, backgrounds, columns, callouts, and more. If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Return of the starwars data set
Переглядів 8484 місяці тому
What's with all those list columns anyway? What can we do about them? If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
LaTeX for R users
Переглядів 2,3 тис.4 місяці тому
Learn how to make nerdy documents even more effective and beautiful with LaTeX. Your mom will be so proud! If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Using Quarto with R and Python for reports, slides, and web publishing
Переглядів 3,8 тис.5 місяців тому
Quarto is an amazing tool for data communication. Let's learn it! If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
Understanding the structure of R functions
Переглядів 1,5 тис.5 місяців тому
How are R functions evaluated? What are their components and how can you see them? If this vid helps you, please help me a tiny bit by mashing that 'like' button. For more #rstats joy, crush that 'subscribe' button!
How to add annotations to ggplots in R
Переглядів 1,6 тис.7 місяців тому
How to add annotations to ggplots in R
Regression analysis in R: backward selection
Переглядів 3,9 тис.8 місяців тому
Regression analysis in R: backward selection
Computing normal probabilities: examples
Переглядів 6698 місяців тому
Computing normal probabilities: examples
Mutating data frames with case_when
Переглядів 1,5 тис.9 місяців тому
Mutating data frames with case_when
Data visualization with R in 36 minutes
Переглядів 24 тис.9 місяців тому
Data visualization with R in 36 minutes
Scatterplots and regression lines in R
Переглядів 7 тис.9 місяців тому
Scatterplots and regression lines in R
Data analysis with R: the Billboard Hot 100
Переглядів 5 тис.10 місяців тому
Data analysis with R: the Billboard Hot 100
Controlling the family-wise error rate
Переглядів 55010 місяців тому
Controlling the family-wise error rate
How to create an "other" category in R
Переглядів 1,9 тис.Рік тому
How to create an "other" category in R
I didn't understand the concept of k what it would be, can you solve by letting k equals to some value
Hi! It's helpful to think of k as carrying information about the size (broadly speaking) of the rejection region. It's related to the level of significance and can be computed once that's specified, but this isn't typically helpful to do. The important thing in the NP-lemma is that such a k *exists*.
why not in 5 minutes?
Play it at 10x and learn it in 4 why not??
I do appreciate it. R to me is a new programming language and I was browsing TY to see what should I and where to start. Yours in my opinion is the best one. Thank you
Does the fill command works only on NA cells or also in empty cells?
Will have to watch this video many more times at my pace. Otherwise, very nice and simplified video. Thanks Richard.
thanks a lot
Hi apologies I'm not quite sure how to search within the channel but does Andrew have an intro into Shiny apps?
Not yet, I’m sorry! If you go to the channels homepage it should be searchable. I’m doing machine learning stuff mostly right now
Thank you so much for the tutorial video! Very helpful for me on learning a lot about data!!!
Great tutorial! Thank you! I've been frustrated with replicating R commands that I don't really understand, but your video have made that clearer
Thanks for making me dealwith R in Just one Video !!!
thanks this was a great help!
Just a note - the conv_multiunit function from the measurements package does a nice job on unit conversions (miles per gallon to km per liter)
Very nice. I am torn whether one should start with base R or jump straight into the tidyverse when teaching R. I get the feeling that one does not appreciate the beauty and simplicity of the tidy (and pipe) approach until one has "suffered" through a little bit of base R s nested approach. After all some things may not run or be needlessly complex in the tidyverse but simple in base R. Any thoughts? - Thanks.
Andrew, Your point about the missings is interesting but it only amounts to a percent (113 hrs) and may thus not be worth trying to impute. Besides that there could be simple explaination for the missing hours. Perhaps the bike company was closed for a holiday and/or buisness-related activities. Imputation might therefore not be warranted.
Yep, totally! I actually have another vid set for release next week that talks about all of this before jumping in to add zeros. Those missing values are pretty much all at odd hours in the middle of the night. The effect on the model is on the order .7 bike per hour, which is surprisingly high.
@@EquitableEquations By the way I see you are in the Chicago region teaching. I attended uni up there and have family in the area.
There is only ONE value with heavy rain/ snow so why not just skip it??? (run Bikeshare |> count(weathersit) for a table).
Good discussion - especially of why you chose to use Poisson.
Believe me, tons of hours and days are wasted to finally run over with content of value like this. Thank you so much
hi, do you offer live online lessons to teach R?
Hi! I do sometimes, but I'm not able to take on new clients right now, I'm sorry. Busy times!
Good stuff!
There is nothing better than good old statistics in the era of ml/nn
You can find materials supporting this vid (and others) at github.com/equitable-equations/youtube. Here's the link to my vid on the {broom} package: ua-cam.com/video/Oy1_A_ZhCY0/v-deo.html
awesome video!
for those who couldn't get arrange function done: library(dplyr) df=diamonds_sm df2<-df %>%arrange(color) view(df2)
I'm getting error in library(tidymodels)=not found and also in "initial_split" not found
How do you download air-quality files?
Please provide the csv/xls file or link
You're awesome. I heard to come back here, having watched one of your videos; learning R in 39 minutes. I have a question please I'm doing the data analysis for my research titled; modeling of selected classification methods and comparison of their performance in the classification of anaemia patients among Nigerian children. Now, I've not been using much of R before this work. So I ran into an issue with my dataset. I have one on of my predictor variables to be continuous. When I declared its class in R as numeric, all values for that variable were overwritten as NAs. I can't start checking each cell because there are almost 11,000 observations. How do I fish out where the problem is?
You're awesome. I heard to come back here, having watched one of your videos; learning R in 39 minutes. I have a question please I'm doing the data analysis for my research titled; modeling of selected classification methods and comparison of their performance in the classification of anaemia patients among Nigerian children. Now, I've not been using much of R before this work. So I ran into an issue with my dataset. I have one on of my predictor variables to be continuous. When I declared its class in R as numeric, all values for that variable were overwritten as NAs. I can't start checking each cell because there are almost 11,000 observations. How do I fish out where the problem is?
Hi. Thanks for this. With these examples you're assuming you have the population sd? In practice would you just use your sample sd?
Hi! I have vids on this too. An example: ua-cam.com/video/DZbBrDw7Ha8/v-deo.html Using R: ua-cam.com/video/oNpfjcIf2Es/v-deo.html You're right that we almost never have the population sd in practice. Honestly, this is mostly just used to gently introduce sig testing since students are usually more comfortable with z than t at this point in their lives.
Interesting. I find it easiest to understand lambda as a rate constant as in the decay of a radioactive isotope - N = N_o x exp(-gamma x time).
Excellent. Thank you
new to me: you can to CTRL-1 to shift to the "code pane" and CTRL-2 to shift to the "console" pane
Oh cool!
Thank you
You can find materials supporting this vid (and others) at github.com/equitable-equations/youtube.
Thank you sir
Hey man, nice videos! I originally came to learn R but then started to speedrun calculus to remember it again. I like your videos a lot.
Thank you so much!!! Master student here after 11 years graduated from bachelor degree and never take any education after…recently all things should be corelated with statistic and Rstudio and I had to take repeat course this summer after not passed for data analysis 😢😢 it really helpful!!
Hii, i hope you can answer my quesiton i used stata to process my data... when I tried to use the normal distribution test using swilk, the result came not normally distributed (0,0000 significance T.T) so i tried the ln normal distribution option that came with swilk test in stata, and the significance when so high, def way above 0,05 but the problem is my data variable contains 0 and negative value, does this mean make the result invalid? or is it still valid ? I have return on asset ratio and non-performing loan as my variable hence there will be 0 and negative values.
Thank you very much!
F(y) ⁵ = [p(y)*y ]⁵ not y⁵?
Bro is literally saving me rn
I got you fam!
thanks super helpful!
You are the BEST!
Why make positive comments without a 👍? I wish there is a code that enables you to make a hundred likes.
Thanks!!
This was REALLY helpful! Thank you!
I can't believe that I'm saying this. But now I kinda love R!! I used to HATE R with every bit of my soul, that's largely because it's substantially different from other programming languages I'm used to (most importantly Python, I've always been team Python). But now, I know why R is pretty handy at times, not only for those who are unfamiliar with programming languages and only want to get the job done with simple code, but also for professionals who are tired of specifying every single little thing in their code/graph/... Thank you professor Andrew! I don't know if you realize it, but you do have a very unique way of illustrating concepts, and your approach on explaining the philosophy behind why R was designed the way it's designed really makes a huge difference. I'm really grateful to have found your videos, and I can't wait to finish this playlist (it's statistical programming with R btw) Speaking of playlists, why don't you collect your half-hour videos (the ones that you collect multiple concepts/functions) in R in one playlist so that you can deliver the highest value in the least number of videos with minimal repetition? I think that would be a good idea. I'm talking about videos like 'Learn R in 39 minutes', 'Data Wrangling in R in 27 minutes', 'Data Visualization with R in 36 minutes'. I wish you the best of luck!
Thanks! I love Python too and use it when it's the better tool for the job (which it sometimes is). I'm actually considering how to restructure my playlists now. Thanks for the input!
thank you so much for these valuable lessons!
Insightful, now you’ve pushed me to work on this dataset
I cannot thank you enough for making this video. Even though I was missing on some things I understood deviance and it's importance to the core. Thank you so much. Stealing the quote from the back ground, love you to the moon and back.
It's a book! www.amazon.com/I-Love-You-Moon-Back/dp/1589255518
Hi, Andrew, could you please make a tutorial for sample selection model? Thanks.
You can find materials supporting this vid (and others) at github.com/equitable-equations/youtube.