I really like mathematics and am currently doing my masters. To make sure I have a backup plan in case I don’t end up in academia, I’m taking some courses in statistics and programming. I’m glad I found this channel!
@charlieivarsson20802 күн бұрын
Could you show how a mixed model is used to evaluate a pharmacological effect over time. Let's say a psychiatric drug at week 0, 3, 9 and 12? How do you tell if the difference is significant?
@luisa15512 күн бұрын
I have a question: in microbiology we work with strains, which are clones and genetically identical within a strain; same in Cancer research when we work with specific cell lines. If I understood you right, then the results are not independent if we use the same strain or same cell line for our biological assays?
@swavekbu49593 күн бұрын
The best kinds of researchers to consult with are either those who know nothing about statistics or admit no knowledge. Those who think they know something are much more difficult to deal with because almost every word that comes out of their mouth is incorrect. They have zero understanding of how much one has to work with and study this stuff for it to even begin to make sense. If they knew how much quantitative folks struggle with this stuff themselves, they wouldn't even try to talk stats. I've found that the smarter the researcher, the more they DON'T try to talk stats with you. The "less intelligent" folks often lack the humility to recognize they know nothing. Why? Because they think stats has something to do with SPSS.
@IsobelFrench4 күн бұрын
Where can I get the dataset used in this video please? Thanks!
@ghaiszriki79127 күн бұрын
As Einstein said: "If you can't explain it simply, you don't understand it well enough" Very clear and simply explained, thanks a million. 💚
@oriandon227 күн бұрын
i am a "pure" math phd that left academia and work as a data analyst currently. i have had this goal of working as a statistician for some place like the CDC, census bureau, bureau of labor stats -- is it really that bad?
@simonnylund5420Күн бұрын
I’m a ”pure” math masters student. I’m pretty sure you could make this kind of video for just about any profession.
@helghast2228 күн бұрын
love this
@ronburgundy97128 күн бұрын
This video was a helpful! Would you do video on maximum a posterior (MAP)?
@ast336210 күн бұрын
But we do fixed intercepts when we have categorial data modeled by dummy variables right? 14:45
@ohnoitseleri11 күн бұрын
Thanks for the tutorial but the music is really distracting
@LucaSubitoni11 күн бұрын
Is it possible to fit a Linear Mixed Effect model using a binary predictor (e.g. time factor: pre vs post) and then compute the significance of this factor? I read about the Satterthwaithe method which could be used to estimate the p value of the fixed model coefficients, is this correct?
@LucaSubitoni11 күн бұрын
Like the pre vs post must be paired
@nosaosawe31586 күн бұрын
Yes is the answer to your first question
@LucaSubitoni6 күн бұрын
@@nosaosawe3158 thank you very much
@sjrigatti11 күн бұрын
How is a mixed effects model with random slopes and intercepts different from just fitting 3 different linear models, one for each cluster?
@HarmonicaTool11 күн бұрын
My biggest problem with VIF is: Models can mostly deal well with collinearity if the sample size is large (not with perfect collinearity, off course). The formula for the VIF does not include the sample size at all, so rules of thumb such as VIF < 10 should really define for which sample sizes they are (kind of) valid. Am I wrong?
@HarmonicaTool11 күн бұрын
The practical explanation on how to do this is this video from a year ago: kzfaq.info/get/bejne/etqmpNyiueDTgYU.htmlsi=G97TUtFfmj2rkbc- ?
@MikkoHaavisto111 күн бұрын
She's such a pro! And, with a great awareness situational humor.
@luisa155112 күн бұрын
Your daughter is the cutest person ever...and so smart! I never imagined that such big and complicated concepts could be said so cute. She is the daughter of her father 😂. Thank you for explaining Maximum likelihood ❤😊 You are a great Padawan!
@gabewinterful12 күн бұрын
I wish this video was out four years ago when I started analyzing my phd data, but glad to see it before the defense so I have some more confidence in explaining the analysis I’ve done in simpler words 😊 thanks a lot!
@Salvador_Dali12 күн бұрын
if you normalize the data to observe the relative change e.g., i guess it makes sense to fix the intercept, right?
@nosaosawe31586 күн бұрын
I don't think so. The normalized data would still take difference intercepts for each covariate
@icupsy583012 күн бұрын
Thanks for your fantastic videos! The simpson's paradox often "solved" by adding an interaction term (X*cluster) in GLM and then conduct separate GLMs in each cluster in some psychological studies. Could you please help me clearify the differences between this method and HLM or MVM? Thanks!
@Lello99111 күн бұрын
An interaction term is different from a random effect on several levels: First, they serve two different purposes: an interaction term is needed when you're primarily interested in checking whether the effect of your predictor X is different (or remains significant) for different clusters. A significant interaction tells you that the effect of X varies significantly across the cluster's levels. Typically, when you find a significant interaction, you don't discuss the main effect of X (it's biased by definition) and you proceed by doing what can be called simple effect analysis or simple slope analysis. Namely, you measure the effect of X at each level of your cluster. So, if you have 3 clusters, you end up with 3 parameters and significance levels: Ex.: the effect of X for cluster 1 is b=0.5, p < .001, for cluster 2 is b=0.2, p = .07, and so on. Mixed effects don't do such a thing. They're not meant to check if the effect of X varies across clusters, or at least they don't give you a significance level for it (you can test the significance of random effects using likelihood ratio tests or other statistical methods to compare models with and without specific random effects, but it's a different thing). The extent to which the effect of X varies across clusters (variability) is incorporated into the model's random structure. Mixed models estimate the average effect of X across all clusters, while accounting for random variations in intercepts and slopes, which is way more informative than GLMs if you're interested in the main effect. Usually, clusters are participants' IDs, so way higher in number as opposed to what you'd use in a GLM with an interaction term. I hope this is helpful, and @Quant Psych approves =)
@user-qy9fc9kb5x12 күн бұрын
Hello! Thank you for your video! Greetings from Chile :) That said, I have studied mixed models a bit and I still don't understand why someone would want a fixed intercept or a fixed slope. I know that if you assume the effect is always the same (like calorie consumption and weight gain), you could use a fixed slope. OK. But anyway, if you use random slopes in this situation, these slopes should be really similar, so it wouldn't make such a big difference, right? Why don't we just use random slopes and random intercepts all the time? If they are similar for each group, it will be OK, and if they are different for each group, great, we modeled it. Is there any advantage of a fixed slope over a random one?
@QuantPsych12 күн бұрын
Yes, there's an advantage. You're estimating one less parameter, save one degree of freedom, your standard errors shrink, and the model is easier to estimate. If you can fix it, always fix it.
@user-qy9fc9kb5x12 күн бұрын
@@QuantPsych Crazy. Thanks for your answer
@swavekbu495912 күн бұрын
I warn researchers sometimes that their model is severely mis-specified, their parameter estimates are biased, and their model is grossly misleading to the point that it may have been more ethical to not run the model at all or they should at minimum report the weaknesses of their approach (and the statistical method they used) in their discussion. They don't care. Not one bit. They don't care about what's ethical in the use of statistics. If it gets published (reviewed by reviewers who don't care one bit either and don't know any better), that's all that matters. Publication mill factory. Just list it on the CV and everyone is happy. And if you bring up vital statistical or philosophy of science concerns about their research even in a very friendly way, you're just being "theoretical" according to them because they have no chance of understanding the argument even if you water it down significantly. Lonely? Very. You just have to walk away. Trying to teach a clinician that because they used a "causal model" does not by itself imply X "causes" Y in their data is just an exercise in frustration. Philosophy of science 101, and these researchers with 30-page CVs filled with garbage can't grasp it and just think you're being a stickler or difficult. They have never once thought about the limitations of statistical modeling in their lives because they are too busy filling their CVs with SPSS-generated BS and playing the publication game.
@QuantPsych12 күн бұрын
Well said!
@nordicmetal861412 күн бұрын
Very good teamwork in this video! Even for non native english speaker it was quite clear. Thanks!
@QuantPsych12 күн бұрын
Thanks!
@candicekoolhaas434313 күн бұрын
This is SO awesome! She is so smart and she is an extremely engaging speaker!
@QuantPsych12 күн бұрын
Yes she is :)
@palvinderbhatia394113 күн бұрын
Wowww, your explanations are just awesome
@zimmejoc13 күн бұрын
I've been waiting for an explanation about MLE like this for over 20 years. Most people just say, "we'll use MLE and let the computer worry about the details." Well, I wanted the details. Now I got them. They won't help me take over the tristate area, but maybe I can use them for evil some other way.
@QuantPsych12 күн бұрын
Just build an MLE-inator!
@zimmejoc12 күн бұрын
@@QuantPsych BEHOLD! The MLEinator. It designs an inator most likely to successfully take over the tri state area. What do you think of that, Perry?
@zimmejoc13 күн бұрын
I was dying to make a comment on the last one. Tell her that she did AWESOME! Her energy is a chip off the ol' block
@QuantPsych12 күн бұрын
Thanks! She'll love to hear that :)
@zimmejoc12 күн бұрын
@@QuantPsych until she becomes a teenager.
@taranaferdous285814 күн бұрын
I do not see the felxplot in r package. Is it removed?
@QuantPsych12 күн бұрын
No, you have to install from github.
@taranaferdous285814 күн бұрын
OMG!!! I am watching it over and over, especially the part where you moved your face video! HaHaHa. Hilarious. =)) Thank you so much for making this so easy to understand!!! And fun! :))
@QuantPsych14 күн бұрын
Glad you enjoyed it!
@anne-katherine116916 күн бұрын
Incredibly cute and smart! I wish I had already liked maths when I was little haha, it helps with life
@luizgualmeida16 күн бұрын
Great video again! BTW, Live class link is broken
@QuantPsych15 күн бұрын
Ah, Thank you. It should be working now.
@damaranaidoo985516 күн бұрын
Hi there, I am looking into the RF analysis for my MSc thesis but I am struggling a bit, I am looking at the effect of various environmental variables (Predictor variables) on a binomial response variable (absence/presence), the data is non-linear, and is somewhat skewed, I have tried to run a glm and a gam analysis but both models are not good fits and are underfitting the data. Do you think a RF analysis with the glm would be more appropriate in this case?
@yashagrahari16 күн бұрын
First 100K views. Congrats! Keep it on.
@QuantPsych14 күн бұрын
Thanks!
@yashagrahari16 күн бұрын
Matt Parker : Stand-up Mathematician Your daughter : Stand-up Statistician. :)
@QuantPsych15 күн бұрын
They should collaborate
@lorenzosenglish393916 күн бұрын
Hello Mr. Dustin! I'm an undergrad, soon Master's student and your youtube content has been an amazing learning experience! Thank you! Is there any chance you could do something about multivariate meta-analysis models? Like expanding on random vs mixed models used for meta-analyses? Thank you again!!
@QuantPsych15 күн бұрын
Possibly, but it's not my area of expertise.
@anasbitar127017 күн бұрын
Great explanation! Thank you!
@RUJedi17 күн бұрын
As a stats instructor for business majors, this is one of the best, lightweight, and enjoyable explanations I've seen on KZfaq for MLE. Great job!
@QuantPsych15 күн бұрын
Wow, thank you!
@caviper117 күн бұрын
Muy good!
@antipro8517 күн бұрын
Great video! How were the likelihood's calculated from the table?
Impressive video! I wish I was that smart at her age (and I have my PhD in math now)! She is going places.
@le940217 күн бұрын
Great Video. Thanks for the nice and funny explanation! Regards
@Finger_Lock_17 күн бұрын
Hey, as an applied stats student I just wanted to tell you that your videos are very helpful for additional information or a different angle on some topics we discuss in class. Last video with your daughter was great btw, she did so well. I think you could make it into a series, and by the time she finishes highschool she'll basically be a doctor in statistics lol
@QuantPsych17 күн бұрын
Ha! Great idea :)
@KarlaOrozcoTorres20 күн бұрын
This video is great! Thank you! You just made me not give up! Do you have a video explaining the interactions between categorical variables and how to interpret the results in an ordered logisitic regression. Or do you have especial sessions to guide this particular cases? I am studying factors associated households food insecurity, and have special interest if the household gender has an effect on the outcome and other variables.
@godsaves845720 күн бұрын
You are just amazing in explaining this complex topic, thank you.
@QuantPsych20 күн бұрын
Glad it was helpful!
@derekcaramella873022 күн бұрын
How have I not found this channel sooner! Amazing stuff, binge watching this channel
@Sam-tg4ii23 күн бұрын
5:39 how would the model be different if we have a 1 before the fix effects and/or before the random effects? Thank you
@QuantPsych20 күн бұрын
It wouldn't be different at all. The 1 is always implied and you have to explicitly remove it (i.e., by typing -1)
@Sam-tg4ii20 күн бұрын
@@QuantPsych Thank you for the response. Your videos have been tremendously helpful to me.
@dabi970223 күн бұрын
incredible, I`m so impressed! A very smart girlie :)
@jishanzaman342124 күн бұрын
Gem of Stat in this Era
@saranshgupta379725 күн бұрын
Great Video.. I'm a rookie in statistics, just completed my Masters in Stats, coming from a different background. This might be a great heads up to what I CAN face in the industry.