#Alternate and null hypothesis

[seonghwacore]

[locusfandomtime]

Doing the maths: Grian's failure at getting a mending book

lots of talk about maths and probabilities below the cut! but there's a graph and simple explanation at the end if you want to get the gist of it and are bad at maths.

(I am still young and learning maths, critique/advice always welcomed)

What are the odds of getting a mending book in Minecraft?

(I am assuming Grian has been doing all his fishing with Luck of the Sea 3)

The probability of a mending book is actually a bit annoying to estimate. The Minecraft Wiki lists fishing up an enchanted book as 1.9% chance. This is for ANY enchanted book. The Minecraft wiki talks about how the chance of an enchantment being selected is calculated. Mending has a weight of 2. Using the table, mending has a probability of 2/135.

However, Grian is looking for any book with mending, not just a pure mending book. Additional enchantments are calculated in a different way, involving RNG, which means it won't be as easy to model. Due to this reason, I'll just be using the odds for a pure mending book throughout.

TLDR: a mending book has a 0.028..% chance (2/135*0.019*100)

Grian's Data

According to this screenshot, Grian has used a fishing rod 5679 times. This number may not be fully accurate, as it includes the times he's fished other players, rather than just fished for items, but it is a good estimate.

To help visualise this data, with a median waiting time between catches of 17.5 seconds, Grian has spent over 20 hours fishing so far! He may have a problem.

Is this statistically significant?

Hypothesis testing (p-value approach):

H0: p = 19/67500 (the null hypothesis - he has no mending books because of chance)

H1: p < 19/67500 (the alternate hypothesis - he has no mending books due to different odds)

5679 trials, 0 mending books

X ~ B(5679, 19/67500) (binomial distribution, 5679 tries with a probability of a mending book being 19/67500, where X is the number of mending books)

p(X=0) (what is the probability the number of mending books being 0)

p = 0.2021473392

Now, the point at which data becomes significant is subjective. For instance, you *could* get a million heads in a row flipping a coin, it's not impossible, but at a certain point, you can begin to say "okay there's something not normal about this". For this approach, the closer the p-value is to 0, the more evidence there is against the null hypothesis . The p-value here is far above a significance level of 0.01, or 0.05, or 0.1. There isn't a clear line between significant/non-significant, but this is answer is quite a bit far from 0

With this, I cannot reject the null hypothesis.

Personal conclusion: this is not statistically significant, Grian is just unlucky.

Are other values statistically significant?

Gem's proposed 9000: results in a p-value of 0.079... more significant than Grian's number but I don't imagine Mojang would be too concerned. As said though, it's all subjective.

I am bad at maths, what does all this mean?

Here is a graph, showing what number of mending books you might have after 5679 tries. The height of the bar represents the probability of getting that amount. The numbers at the top are the (rounded) numbers I used in my calculation

The pink column is 0 mending books - like what Grian has! As you can see, it is less likely than getting 1 or 2 books, but not too uncommon to happen.

End conclusion: Grian has bad luck. Like, not as hilariously bad as he thinks, but still bad. If he keeps going, chances are he will get a mending book, but I think he should probably stop fishing because at this point he has a problem.

[moralisist]

tutor armin

warnings: x fem reader!, college au, suggestive, lowk long 😭

math has forever been unkind to you. c’s and sometimes d’s would be a regular occurrence with math. you were an a+ student don’t get me wrong but math? it just never made sense.

your teacher tried to help you, but it’d anger her to the point of having to take breaks while teaching you just so she wouldn’t yell at you. how could a straight a student like you not get a concept that’s been taught for months now?

you were in a bind. your gpa would be perfect if it wasn’t for math and you didn’t know who to go to. it was also a bit embarrassing to ask someone else for help. however, your teacher would make sure you’d get the help you needed.

it was the end of a lecture in your statistics class. you were reviewing notes and looking through your text books but you were still so lost. you figured you’d just study more at home and begin to get up from your seat.

“ms. y/n and mr armin, can we chat?” your teacher asks you. you make eye contact with the blondie from across the room who was still packing up his things. you head to your teacher but you can still feel a pair of eyes on you.

“armin, i’d like to ask you for a favor.” your teacher asks him. he smiles. “yes of course, anything miss.” he seemed so polite. and he was quite handsome too. a cute round face with a jawline popping out whenever he clenched his jaw, his cheeks were naturally a bit rose, and short hair that framed his face quite nicely. his attire matched his vibe and it was so put together but clearly not trying too hard. and his eyes-

“so what do you say y/n?” miss asks. you look over to armin who has hopeful eyes. you have no idea what she asked but you decide to go for a safe answer.

“yes.” your teacher giggles. “well it’s settled! tomorrow and after every lesson, armin will tutor you!” your eyes widen just a bit while looking back at armin who was already looking at you. he smiles kindly like he always does.

“does 3 work for u tommorow?” he asks you. “yeah 3 is good.” you smile back.

it’s the next day and you’re sitting at your desk, taking notes but can’t help but glance at armin every once in a while. how come you never really noticed him? was he sitting here all this time? so many questions you had to ask and you were hopeful you’d get them answered by today.

“y/n!” armin walks over to you when it’s the end of your lesson. “where do you wanna study?” it was weird. it’s almost like he was excited.

“we can study in my dorm if you’re okay with that. i got some snacks yesterday too that we can share.” you say hoping it didn’t sound too flirtatious. “sounds great.” you both smile at each other, walking and making polite small talk on the way to your dorm.

you guys are sitting on your floor while he’s talking to you about null and alternative hypothesis. for the first time in a long time, things were starting to come together. armin made sure to go back to the basics and reviewed it with you so you could grasp it and he made sure to prepare you for the upcoming test. armin could see you becoming more confident in your answers and you were solving problems without his help.

you both decide to take a break and you guys are laying on your floor, talking each others ears off. he talked about his interests in books and history, while you shared about how hard you had to work in school and what arts you were into. armin loved talking to you about these things, the things that made him, him. he could never go to his friends about this stuff, it was too sappy for them.

as hours go by, you guys are indeed sharing the snacks you offered him and you and armin are already so close. you both are talking about deep desires and wants, while sharing your secrets, free of judgement. a comfortable silence falls between you two.

“i’m proud of you y/n. you did a really good job today.” you both are on your bed at this point, your guys’ body heat meshing although you guys are just next to each other. “thank you. and thank you for all your help armin. it means everything to me.” you look at him with bright eyes, your skin heating. armin stares at you again with those kind eyes.

he holds a part of your face in his hand, silently asking for permission. instead of waiting, you grab his face gently and kiss him. the kiss is soft and sweet. it’s filled with curiosity as your toungues are exploring each other and seeing what the other likes.

it wasn’t armins first kiss but you took control of the kiss as if it was. you were a fire he wasn’t used to but he loved it. it was so thrilling to him. you straddled his waist while continuing to attack his lips. you were getting more confident by the second seeing the way armin melted underneath you. it was all too much but the sensation was nothing like you’ve felt before. his kisses were comforting, the way he’d give you a peck on the lips when you guys would slow down and then he’d dive for more. you both loved everything about it.

armin pulls away from you, looking incredibly disheveled. “y/n, i really like you. but before we go further i wanna take you on a proper date, is that okay?” you smile at him and wrap your arms around his neck, laying on him. “that’s more than okay. i’d love that.”

armin had been tutoring you for the last couple days before the big test. you both were getting closer and closer as the days went by, learning more than you thought you could learn about him in such a short time.

it was finally the day of the test and you and armin were walking in together, it becoming your usual routine now. he stops you when you guys approach nearby because he can tell you’re nervous. he was an observant one, you noticed.

“don’t be nervous y/n. you’re gonna do great and you studied so hard and for so long.” you sigh, “okay and what if i don’t do well?”

“i’ll be there to help you study and we can cover the basics all over again if you’d like us to. i’m here for when you need me, and you’re gonna do great so don’t think like that.” he gives you a kiss on the cheek and then on the lips. “now let’s go in.” he leads you by holding your lower back and rubbing ur back up and down.

you finish your test and hand it in while your teacher looks at it briefly. “i haven’t graded it yet y/n, but it’s looking good. keep up the good work with armin.” you smile a big toothed smile while saying thank you and walk over to armin who finished his test a bit before you. you guys head out the class and you jump into his arms while smiling and talking about the fact armin might’ve landed you an a in math.

“you did all that work yourself! i’m so proud of you.” he hugs you even tighter. “i think you deserve a nice dinner huh?” he grips ur waist while he pulls you away from him to see your face. your smile was infectious.

“come, i’ll take you to your dorm so you can get ready. my smart girl needs all the time she wants so we can go later tonight, let’s say 6? i’ll come get you.” he grips your hand while walking to your dorm.

what would you have done without your super smart, super cute, and super dorky tutor of a future boyfriend?

a/n: requests r open!

[taweretsdagger]

jack's need to find the answer vs. juliet's need to look over the edge

lost's tragic, (probably) autistic doctors, part three

alright gang, let's put some analysis weight behind the word "tragic" in this series title :')

in part one, we discussed several similarities between jack and juliet through the lens of some autistic traits, and in part two we discussed how gender presentation/societal expectations could cause other autistic traits to show up differently in the two characters.

i don't have much more autism-specific analysis to add here, but will reiterate two points i brought up in parts one and two as they'll also be useful for understanding how these characters reach their respective tragic ends:

the metaphor of viewing jack and juliet's relationship like two mirrors facing each other

jack and juliet's shared desire/struggle to find belonging

so, first off: titles. the title of this installment, the title of this series. the title of "doctor." this is an essential title for both jack and juliet, and i do mean "essential" quite literally. this title drives not only their careers, but their personalities, their strengths and weaknesses, their problem-solving approaches, and so on.

their very essence is encapsulated in this title, but in the end, that doesn't tell us much about them on its own. we use the term "doctor" to refer to all manner of career pathways and advanced degrees. in her infinite wisdom, juliet makes this point clear when she counters being referred to as a doctor by saying "[she's] really more of a researcher."

so what's the difference, between a (medical) doctor and a researcher? despite all the possible implications of referring to someone with the title of doctor, i'd imagine most people would think of a medical doctor when i use that word. so let's look to the dictionary to understand the former.

while the definition of "doctor" sounds a bit nefarious...

(verb) change the content or appearance of (a document or picture) in order to deceive; falsify.

...we can apply a more neutral connotation to understand this profession as one of diagnosing, and ultimately fixing. making right.

sound like anyone we know?

meanwhile, research takes a different mindset. every null hypothesis you prove false leads to several new alternative hypotheses. you're never really done, because there isn't "one answer" in research. it takes keen observation, and intellectual stamina/humility, and a willingness to try. a willingness to ask "why," rather than to solely insist on understanding "how."

in part two, i discussed juliet's pattern of impulsive behavior (such as chugging the juice richard gives her at the airport) in the context of autistic meltdowns. i also think this tendency is what makes her such a good researcher. while on the surface juliet might seem like an obvious "woman of science," she is clearly willing and able to take things on faith. this also differentiates her from jack as a character; despite their many similarities, juliet does not possess jack's need to understand or identify the answer.

in fact, in the flashback scene we get of juliet as a child in the season five finale, she makes the opposite claim very explicitly:

"i don't want to understand!"

as two of my favorite juliet understanders (hehe) (@lost-inanotherlife and @ginawankenobi) have pointed out, there is also a gendered/self-deprecating element to the way juliet's career is introduced to us. being a surgeon isn't "superior" to being a researcher; both are necessary roles in the medical sciences and come with their own difficulties. but more societal reverence is generally ascribed to the practice of surgery, and it's a role people might be more likely to associate with traits like leadership and strength, at least as compared to the slower, quieter, messier practice of research.

"i'm not a leader, mr. alpert; i'm a mess."

we left off part two with juliet just having displayed some excellent leadership skills... notably, while performing surgery on jack. by the end of season four, we'll see jack finally getting rescued (with only five of his people with him), and juliet missing out on yet another chance to escape the island. we see jack failing to live up to the promise he made her, and we already know that this failure (among other things) is going to drive him into a deep depression within a few years.

meanwhile, juliet gets a new life on the island, making good on the bad hand she got dealt. she has friends, a job free from the baggage of her traumatic experiences with ed and ben, and, as i mentioned in part two, it seems likely that as sawyer ascends to a position of leadership within the dharma initiative, juliet would operate as his advisor and confidant (like many women do with their male, leader partners in societies where women cannot occupy leadership positions themselves, which seems to be the case for dharma). she has experience living in the barracks and an insider's understanding of the "hostiles," both of which would constitute valuable insight for dharma's head of security.

as discussed in part one, jack's projection of his desire to belong onto juliet is ultimately what enables his (woefully brief) "golden age" as the crash survivors' leader at the end of season three. however, juliet's ability to find belonging and esteem within dharma is not reliant on jack or any projection of her own issues onto him. AND, jack is absolutely Going Through It back in the real world, once more projecting his desire to return to the island ONTO juliet as a sort of remix of his need to save her (which of course, is really jack's need to save himself). but this time, juliet doesn't need or want saving. our two mirrors are out of balance. when they reunite, that imbalance presents as tension that has nowhere to climb but up.

as soon as the gang returns, juliet clocks where things are going. this is shown largely to us through the scene in which she's watching jack and kate out the window and sawyer asks her "what's on TV?"

i won't spend too much time discussing the significance of this scene overall, but would be remiss not to reference this incredible series for those who yearn to sink their teeth into it as much as i do.

for the purposes of this post, what's most crucial in understanding this scene is putting it in context of our mirror metaphor. if our two mirrors are out of balance, maybe all the "meat" of the light and energy that was previously bouncing back and forth between them is starting to coalesce within jack, giving juliet an opportunity to become a spectator to a dynamic in which she used to be a more active participant. (also, what is a television but a "black mirror?")

before long, this tension crashes in the form of our first jack/juliet collision, when she confronts him after he refuses to help save ben and calls out the hypocrisy and projection in his stated reasons for returning to the island.

okay, now let's move on to the bomb :')

the period between the scene of juliet's confrontation of jack and the moment when she decides she's going to help him detonate the hydrogen bomb is difficult to analyze, since like most people i really didn't appreciate the return of a love triangle with kate. three years have passed, and these are grown adults. it's just really difficult for me to buy as a viewer, and the lost writers themselves have admitted it wasn't their best moment. but i'm going to give the canon events as much credence as i can within the analytical framework we've established in this series.

juliet is insecure, and prone to self-destruction when things are getting out of hand. we know this. we also know that she can see the beginning of the end of the life she and sawyer have built in dharma. rather than her next "meltdown" coming about specifically due to her jealousy of kate, i think it's more likely a result of losing so much control and agency so quickly. i think she's also engaging in a fair bit of projection/externalization of that loss of control onto sawyer, sort of like her own version of what jack did when he externalized his fear of the appendectomy onto kate in season four.

daniel is the physicist in the group, but his reasoning for detonating the bomb really has nothing to do with science at all. instead, his "variable" theory is wound up entirely in his grief over losing charlotte. but i imagine in part based on the credibility of his expertise, jack is able to latch onto the idea of the bomb as a "scientific" solution to all his problems. hit the reset button, and try again. simple enough! for juliet though, i don't think precise reasoning and rational defense of the bomb as a solution is a necessary part of her decision equation. it's another moment of her self-destructive impulsivity colliding with the island's forces and will, just like when she chugged the juice.

once juliet changes her mind about the bomb, our mirrors appear to be back in sync. however, the tension is still there, and still plenty dangerous--even explosive. *especially* when you enter a hydrogen bomb into the equation (even just the core). at least one of them is going to have to die in the process; there's just way too much potential energy and it's resonating between them too rapidly.

two things are particularly interesting to me about how the incident itself plays out: for one, juliet is DRAGGED over the edge of the swan abyss, but in the end she DECIDES to let go of sawyer's hand and let herself fall. and then when she wakes up underground later, she DECIDES to detonate the bomb herself.

for those first few dragging moments, all her morbid curiosity comes back to haunt her, and i'm sure she saw every juice-chugging-adjacent moment of her life flashed before her eyes. but she still accepts her fate, and still uses the last remnants of her physical strength to see through their mission to the bitter end.

secondly, jack ends up having to take the bomb detonation on faith. he drops it down the chasm, but everything that happens after that is out of his hands. he had no idea whether it had detonated on impact, and would have had no idea that their fate was left up to juliet if she hadn't lived long enough to tell sawyer what happened.

jack begins the experiment with the bomb, but juliet becomes the catalyst necessary to finish it. in doing so, she also becomes the catalyst of jack's transformation from a man of science into a man of faith, since he HAS to let go of her. he failed to save her multiple times, and then he got her killed. that's that. there's nothing he can do to change it. and at the same time, he's lost his second mirror. he can't project onto juliet, he can't project onto kate, he can't project onto anyone. he has to embody all the energy that once had been shared--however unevenly--and i'd argue that this is a key element in jack learning that he does, indeed, have what it takes. that's a lot to hold, maybe more than he's ever tried to hold before.

(one thing about juliet, she had what it took. imo, you don't smash a hydrogen bomb with a fucking rock if you don't have what it takes.)

jack doesn't die during the incident, but in a way he's been dead ever since he got up on that bridge. in part, the bomb was another manifestation of his suicidality. the cataclysm of juliet's demise gives jack a reason to stay alive, at least long enough to accept the role as the island's protector, kill the man in black (with a crucial assist from kate), and halt the island's destruction. he ends up underground just like juliet, doomed just like juliet, but his experience of that doom couldn't be more different. he's laughing, bathed in incandescent light, and learning something new about himself.

and the parallel differences don't end there: juliet dies in sawyer's arms, comforted by the belonging she craved for so long and finally found, even if only for a short while. meanwhile, jack dies alone (well, almost... thank god for vincent <3). both of them go out looking content, but their contentedness is sad to us for disparate reasons.

so, we could call all of season six a last gasp gifted to jack by juliet, but within that series of events there's another, subtler last gasp for which he has her to thank.

to close this series out, let's talk about our beloved appendectomy, one more time.

all things considered, jack's a pretty lucky duck. he gets a life-saving 2-for-1 on this surgery. REALLY not a bad deal, for a procedure performed on the beach by torchlight, by someone who's "really more of a researcher."

not only does juliet save jack's life by performing the surgery itself in season four, but the absence of jack's appendix is what allows him to survive long enough after being stabbed by the man in black to save the island (and, therefore, the world). otherwise, he would've bled out too quickly, and everything would've fallen into ruin.

that pesky little vestigial organ almost killed our hero twice, and both close calls are staved off by the surgical skills of a woman who doesn't even totally consider herself a doctor, let alone a leader! i mean, talk about misplaced insecurity! when they meet up in that church i very much hope that jack took the opportunity to tell juliet how much of a hero she was in her own right, and how little he could've accomplished without her expertise and determination. and in case he didn't, I'M gonna do a little projecting of my own and beam that message into the universe for juliet to pick up on!!!

thank you so so much for reading along everyone! :) i hope you enjoyed this extended look into the minds and lives of two very fucked-up people who are very destined to be divorced from one another <33

(speaking of, let me tag in what i consider the spiritual successor to this series, or @obsessivedaydreamer's jack/juliet flash-sideways fic, "Across Our Great Divide." a true masterpiece, and very necessary reading to understand our repo divorcees!!!!)

[distantlaughter]

Fic title: The Scientific method

A 5+1 fic where each item is a step of the scientific method. The hypothesis being tested of course is "does X like me" or something like that. I chose Eduardo Quaresma and Ivan Fresneda:

1 . Question: "What are Ivan's feelings toward me?" Eduardo asks this question because, well, they do play the same position (rightback) and are both vying to start over the other, so maybe they don't necessarily have to be best buddies, but Eduardo 's a nice guy, he's never done anything wrong to Ivan so why is Ivan a bit distant from him?

2. Background Research: Eduardo spends a week just observing Ivan, who he hangs out with, what he laughs at, how he plays, what he eats, what he likes...

3. Hypothesis: Null hypothesis--Ivan does not like Eduardo; Alternative hypothesis (the thing that must be proven)--Ivan does like Eduardo. Of course, the twist is that the true hypothesis and question being asked is what are *Eduardo's* feelings toward Ivan

4. Experiment: The independent variable is Eduardo, and the dependent variable is Ivan. Eduardo starts trying to get closer to Ivan, sitting next to him on the team bus, eating with him in the cafeteria. Sending him videos on Instagram and seeing which ones Ivan likes. Manipulate the independent variable and record the changes, if any, in the dependent variable.

5. Analysis: Analyze the data you've collected i.e. the big reveal. The season's over and Eduardo's not really any closer to coming to a conclusion on whether or not Ivan likes him but he's pretty sure about his own feelings now. But they end up going to the same island for vacation and drunken sex ensues

6. Conclusion: Decide whether to reject or accept the null hypothesis. The morning after... and a happy ending? Probably yes ;P

[luxe-pauvre]

So here's the dirty secret about p-values in science. When scientists report p-values, they're doing something a bit like the prosecutor did in reporting the chance of an innocent person matching the fingerprint from the crime scene. They would like to know the probability that their null hypothesis is wrong, in light of the data they have observed. But that's not what a p-value is. A p-value describes the probability of getting data at least as extreme as those observed, if the null hypothesis were true. Unlike the prosecutor, scientists aren't trying to trick anybody when they report this. Scientists are stuck using p-values because they don't have a good way to calculate the probability of the alternative hypothesis.

Carl T. Bergstrom & Jevin D. West, Calling Bullshit: The Art of Scepticism in a Data-Driven World

[max1461]

Extremely annoying discourse habit that I encounter from certain people is going "people always say that [received notion] is false, but I'm not sure there's evidence for this. Therefore, (I will at least provisionally believe that) [received notion] is true", when there's neither any more evidence for [received notion] nor is there a sensible reason to take [received notion] as your null hypothesis. It feels like such a frustrating abuse of the language of skepticism by people who want to believe narratives society has taught them. It's especially frustrating when people do this piling on to a chorus of voices supporting [received notion] against a minority supporting ¬[received notion], where it is such that even though [received notion] and ¬[received notion] are equally ill-evidenced and neither should be advocated, ¬[received notion] is frankly pulling the discursive century of gravity closer to the truth by making people aware that [received notion] is not necessarily or self-evidently true, that its supporters must in fact defend it from credible alternatives.

I guess that last part is why it really bothers me. The habit I'm referring to is abuse of the language of skepticism in such a way that it distracts from the fact that certain very popular ideas have not defended themselves adequately. Which is the exact opposite of what skepticism should be used for. I know that we are all a bit discourse poisoned by people advocating strongly for silly things because of second opinion bias, but this does not mean that defaulting to first opinions is any better as a heuristic!

[elsandifer]

In Whovian Feminism's initial review way back of Deep Breath, she criticizes;

"Clara had clearly been through quite a lot throughout this episode and was disconcerted by the change in the Doctor. When she said “I don’t know who the Doctor is anymore,” she was very justified in doing so. But the focus was entirely on reassuring the Doctor. Matt Smith’s cameo was sweet, but ultimately it was about convincing Clara that she should remain with the Doctor because her fear was not as great as his. I can’t even begin to tell you how mad this made me. Clara was put in danger and abandoned several times by the Doctor; she was afraid by how unreliable this new Doctor seemed. But instead of confronting this problem, Clara is simply guilted for not accepting the Doctor as he is."

What do you think of this critique? I find it to be convincing if anything, but I'd be happy to read any alternative viewpoints as well since I very much like the scene overall.

I think that it's something of a mistake to view not accepting the new Doctor as a possibility that the show is seriously entertaining. Fundamentally, there's an enormous amount of narrative gravity pulling towards Clara deciding to trust him. You could write it a different way—there's arguably enough to justify a serious schism with the Doctor here. But "the companion accepts the Doctor" is the null hypothesis. It doesn't require much in the way of justification. Even when you introduce the possibility of its rejection (and I'll point out that Madame Vastra has spent all episode telling Clara she's being an ass, so this possibility is never given much weight) you don't really have to do much to accept it after all. "Oh look, one more Matt Smith scene" is more than enough.

[mvishnukumar]

What are some challenging concepts for beginners learning data science, such as statistics and machine learning?

Hi,

For beginners in data science, several concepts can be challenging due to their complexity and depth. 

Here are some of the most common challenging concepts in statistics and machine learning:

Statistics:

Probability Distributions: Understanding different probability distributions (e.g., normal, binomial, Poisson) and their properties can be difficult. Knowing when and how to apply each distribution requires a deep understanding of their characteristics and applications.

Hypothesis Testing: Hypothesis testing involves formulating null and alternative hypotheses, selecting appropriate tests (e.g., t-tests, chi-square tests), and interpreting p-values. The concepts of statistical significance and Type I/Type II errors can be complex and require careful consideration.

Confidence Intervals: Calculating and interpreting confidence intervals for estimates involves understanding the trade-offs between precision and reliability. Beginners often struggle with the concept of confidence intervals and their implications for statistical inference.

Regression Analysis: Multiple regression analysis, including understanding coefficients, multicollinearity, and model assumptions, can be challenging. Interpreting regression results and diagnosing issues such as heteroscedasticity and autocorrelation require a solid grasp of statistical principles.

Machine Learning:

Bias-Variance Tradeoff: Balancing bias and variance to achieve a model that generalizes well to new data can be challenging. Understanding overfitting and underfitting, and how to use techniques like cross-validation to address these issues, requires careful analysis.

Feature Selection and Engineering: Selecting the most relevant features and engineering new ones can significantly impact model performance. Beginners often find it challenging to determine which features are important and how to transform raw data into useful features.

Algorithm Selection and Tuning: Choosing the appropriate machine learning algorithm for a given problem and tuning its hyperparameters can be complex. Each algorithm has its own strengths, limitations, and parameters that need to be optimized.

Model Evaluation Metrics: Understanding and selecting the right evaluation metrics (e.g., accuracy, precision, recall, F1 score) for different types of models and problems can be challenging.

Advanced Topics:

Deep Learning: Concepts such as neural networks, activation functions, backpropagation, and hyperparameter tuning in deep learning can be intricate. Understanding how deep learning models work and how to optimize them requires a solid foundation in both theoretical and practical aspects.

Dimensionality Reduction: Techniques like Principal Component Analysis (PCA) and t-Distributed Stochastic Neighbor Embedding (t-SNE) for reducing the number of features while retaining essential information can be difficult to grasp and apply effectively.

To overcome these challenges, beginners should focus on building a strong foundation in fundamental concepts through practical exercises, online courses, and hands-on projects. Seeking clarification from mentors or peers and engaging in data science communities can also provide valuable support and insights.

[man-and-atom]

If lawmakers are serious about fighting climate change, they must design climate-friendly legislation that cannot be exploited by anti-development activists.

I don't know how to tell you this…

Any attempt to mark some essential distinction between “legitimate” environmentalists and “anti–development activists” is bound to fail. Anyone who has read through the controversies of the 1960s and 1970s — for instance @atoms4ca here on Tumblr — can tell you that the opposition to nuclear energy, the defining characteristic of the Green movement, the one thing they are unwilling to give up, even in the face of the threat of climate catastrophe? Was founded on the desire to deny industrial civilization a sustainable energy source.

It’s NIMBY all the way down. The founders of “Friends of the Earth” looked at California and though “it would be awful if more people were here, and this State can’t support more people without electricity, and nuclear is the only reasonable option to supply that, so let’s oppose it.” Simple as that. And the Sierra Club, which had been saying “Atoms not Dams”, trying to accommodate development with minimal harm to the environment, saw money flowing to these radicals, and followed suit.

The CEQA process, just like the NEPA process, has been from the beginning and is being abused, because it was created to be abusable. There are few or no scientific or other objective standards attached to the Environmental Impact Statement process, and the “null hypothesis” alternative presented is generally a completely unrealistic one. “What happens if we don’t allow this power plant, or mine, or other project” is typically answered with “nothing”, not with an acknowledgement that the power, or minerals, or whatever will have to come from somewhere.

[max1461]

Look, I just don't buy that people's stated beliefs are a very consistent guide to understanding or predicting their actions. I mean, it's an idea that has some intuitive currency, but that doesn't mean it's true or even that it should be our null hypothesis. Our null hypothesis should probably be "no correlation", and I think obviously we have enough evidence to reject that. But that doesn't mean that we can default to "strong correlation"! In particular, I think if you just like, interact with people, it becomes obvious that they say things they don't believe and believe things they don't say all the time. They act based on vague gut feelings and justify it with some narrative later. They bullshit, say whatever is convenient in the moment, thinking only about how it sounds and not what it means. They also say things they actually mean, but it can be very hard to tell which things are which (sometimes intentionally!). Often there is no sharp dichotomy. People just do shit and say shit, those things aren't necessarily connected to each other.

This doesn't mean that people's stated beliefs are no guide to their actions, obviously that's not true either. I mean, duh. If you go through life just ignoring the content of what people say you won't make it very far. And I think "I take people's word for what they believe, and assume that their beliefs are reflected fairly literally in their actions, unless I'm given strong reason not to" is, for what it's worth, a really good heuristic—better than most alternatives. But the thing about using a heuristic profitably is that you have to recognize that it's a heuristic, you can't actually conflate it with ground truth. And the ground truth, again, seems to me to be that people just do shit and say shit a lot. Guess it depends on who you're spending time with. But like, enough people do this that you have to take it into account.

This isn't about anything in particular, it's just that "of course we should take people's stated beliefs more-or-less literally when trying to predict their actions or understand their motivations" is a refrain I hear around here a lot as if it's self evident. And I think it's not only not self evident, it's like, actively misleading. Out of politeness and respect, among other reasons, I believe in basically taking people at their word. But you should probably maintain a pretty high prior that any given thing being said is kind of a little bit bullshit so that you aren't caught off guard when it inevitably happens. And, more importantly, if you're reasoning about large populations or large bodies of speech, you should be prepared for a bunch of it to be kinda bullshit. Because it will be.

[nursingwriter]

¶ … Kershaw, T. et al. (2011). The Skinny on Sexual Risk: The Effects of BMI on STI Incidence. AIDS and Behavior, 15. 7 Oct 2011; 1527-38.  https://www.paperdue.com/customer/paper/kershaw-t-et-al-2011-98238#:~:text=Logout-,KershawTetal2011,-Length1pages My research topic deals with a unique segment of the population and how that population is dealing with a specific behavior that is heath threatening. Specifically, my research question asks what are the impacts of a relationship with a child's father and how these relationships affect teenage single mothers and their occurrence of sexual transmitted diseases. Kershaw et al. (2011) suggested that there was a relationship between body mass index (BMI), obesity and sexually risky behaviors. The purpose of their study was "to determine whether BMI among 704 young mothers (ages 14 -- 25) related to STI incidence and sexual risk. We examined the effect of BMI groups (normal weight, overweight, and obese) at 6 months postpartum on STI incidence and risky sex (e.g., unprotected sex, multiple partners, risky and casual partner) at 12 months post-partum, (p.1527). Null Hypotheses Risky sexual behavior and BMI have no correlation in young mothers. Alternative Hypothesis Evidence suggests that obese young mothers my have less sex and fewer partners which reduces their rate of STDs. Sampling Procedures The data was gathered using a sub-analysis of a large randomized control group of 1047 pregnant young women. The data was collected from the assessments at the given time intervals. Independent/Dependent Variable The BMI was used as the dependent variable and STD occurrence was used as the independent variable. Alpha Level Alpha coefficient was not used in the statistical models of this study. Outcome The results of this study support the importance of the association between BMI and sexual risk, and suggest the need for sexual risk prevention and weight loss programs among young mothers. Questions and Personal Design -How important is BMI to overall health? -Is there a difference in the severity of STD/STI's, if so how does that affect the importance of the study's outcome. Designing a study for my topic would require assigning the independent variable STD occurrence and the dependent variable would be that mother's relationship status with her child's father. References Kershaw, T. et al. (2011). The Skinny on Sexual Risk: The Effects of BMI on STI Incidence. AIDS and Behavior, 15. 7 Oct 2011; 1527-38. Read the full article

[angstmongertina]

I do want to add that the argument isn’t just about MRIs. The paper argues for the importance of multiple testing corrections, which is relevant in far more science than just imaging analysis. That’s something that can happen in any field in which tests are being performed. The MRI example is just one such case.

This essentially comes down to what we mean when we say statistically significant. If you think back to your science classes, you may remember learning about null and alternate hypotheses when performing an experiment, or designing a test. The idea is that the null is sort of the "default," and our goal with our experiments, much of the time, is see if the null hypothesis is false. You may hear it as "reject the null." Typically, we feel comfortable rejecting the null at p<0.05. This means that there is a 5% chance that any differences we're seeing in our data compared to what we expect is entirely by chance. In other words, it's pretty unlikely that the results we're seeing are by chance, so instead we can think "well, maybe there's an actual difference."

Now, that's great for one test. But let's say we're doing 100 tests. And each one rejects at p<0.05. And let's assume that all of them truly have no difference. Well, based on our cut-off for our p value, on average, we would expect 5 of those 100 tests to reject, even though there is no true difference. This is what's called a false positive, and is a danger whenever we're doing tests like this. There's always a chance that we find an association that isn't real. But, we do our best to try and limit them.

Now back to the dead salmon. As a disclaimer, I don't work with imaging data, so anyone who actually does imaging analysis, feel free to correct me, but as I understand it, when you're looking at MRIs, you're looking at tons and tons of small regions, and looking for associations between them and the stimulus. Essentially, you're doing tons and tons of tests. And if you continue to use the same cut-off of 0.05, you're going to end up with quite a few false positives. Which is what happened in the dead salmon study. If I recall correctly, they found a region with association in the optic area of the fish brain, indicating that the very dead fish can still see things. Which is clearly impossible, since the fish is dead. Instead, what was happening was that a cluster of tests just so happened to be false positives in a way that might make it appear as though there was an association with that region of the brain. And since the fish was dead and should not have any brain activity, that was very clearly a case of false positives.

So, what can we do? Well, multiple testing corrections is essentially a method that can be used to combat this. There are a few different ways to adjust the p-value, or otherwise control how many false positives you get, but the basic idea is that when you're doing many tests, like in the case of MRIs, or other studies like Genome Wide Association Studies, it's very very important to adjust the p-value, so you don't end up with a bunch of false-positives. And any scientists performing multiple tests should be wary of these kinds of results. It's not always as easy to tell as when we're looking for brain activity in a dead fish, but the results can be equally unrealistic.

In summary, please check how many tests you're running and perform multiple testing corrections accordingly, even if you're not working with MRIs. False positives don't care about what field you're in. They come for all.

one of the best academic paper titles

[literaturereviewhelp]

The managements are spending a lot of resources in empowering its employees in order to boost their competence. Employee empowerment involves conscious policy decision to develop workforces and engage them in more decision-making practices (Luttrell, Quiroz & Bird, 2007, p. 7). This study argues that the empowerment is an unrealistic concept and explores the reasons companies have not fully implemented the employee empowerment to enjoy the perceived advantages. Most organizational managers perceive employee empowerment as a strategic approach for cultivating and improving the employees’ potential by building their capacity to make a decision (Royal Pharmaceutical Society, 2011) Although proponents of employee empowerment consider it as an essential practice of recognizing the importance of all workers in the organization, there are many challenges associated with the empowerment practices thus making it impossible to attain the objectives (Rochford, 2010, p. 57). The management empowers employers in order to have more competent workforce. In so doing managers can devote routine issues to the workers and have more time to engage in strategic issues that are beyond the scope of worker in addition, it ensures quick decision making even in the absence of top managers. Also, empowerment or workers can motivate the workers and improve productivity (Rochford, 2010, 173). Finally, employee empowerment enables managers to reduce work-related stress by reducing the scope of activities they have to handle each day (Luttrell et al. 2007, p. 10). However, despite the perceived advantages of employees empowerment companies have continued to experience challenges with practical implementation of the empowerment practices. The success of employee empowerment is a mutually inclusive practice that should involve both workers and the management.   OR Compare and contrast the findings from the histograms and from the tests with level and logarithmic specifications. H0: sample is not distributed normally H1: sample is distributed normally Decision: Probability value is less than 0.05significance level. Therefore we reject the null hypothesis and accept the alternative hypothesis. i.e. price variable is normally distributed Probability value is less than 0.05significance level. Therefore reject the null hypothesis and accept the alternative hypothesis. i.e. log price variable is also normally distributed Thus, the results of histogram and Kolmogorov-Smirnov test are consistent. Variable Description Combined K-S Value 1. dist Weighted distance to 5 employment centers 0.000 2. ldist Logarithm of weighted distance to 5 employment centers 0.016 H0: sample is not distributed normally H1: sample is distributed normally Decision: Probability value is less than 0.05significance level. Therefore reject the null hypothesis and accept the alternative hypothesis. i.e. dist variable is normally distributed Probability value is less than 0.05significance level. Therefore reject the null hypothesis and accept the alternative hypothesis. i.e. log-dist variable is also normally distributed Histogram showed the distribution of dist variable as skewed to the left. However Kolmogorov-Smirnov test yields a normal distribution. . Mean value of rooms in the given sample is 6.28. Accordingly there are 278 houses with number of rooms bellow the average (sample A) and 228 houses with number of rooms above the average (sample B). Hence the total observations in two samples are different. Therefore we have to conduct unpaired two sample t-test. Mean Difference -8918.208 t-statistics -12.3611 P-value H0: diff=0 0.0000 H1: diff < 0 0.0000 H2: diff > 0 1.0000 Decision: Probability value of H0 is less than 0.05 significant level. Therefore reject H0 which states there is no statistically significant difference between the mean price of houses having rooms less than average and more than average. (ii) houses below and above the average value for nox; Average nox value of the given data set is 5.549. There are 292 observations in the above average category while there are 214 observations in the below average category. Therefore unpaired, two-sample t-test with equal variances can be used. Mean Difference 6199.578 t-statistics 7.9261 P-value H0: diff=0 0.0000 H1: diff < 0 1.0000 H2: diff > 0 0.0000 Decision: Probability value of H0 is less than 0.05 significant level. Therefore we reject the null hypothesis which states mean price of houses which are situated in lower nitrous oxide levels are not statistically different from those houses situated in higher nitrous oxide areas. (iii) Houses below and above the average value for crime.   Read the full article

[bloomingbiz]

Data Mining YouTube Viral Video Keywords 2025

March 11, 2025 Research Questions: 1.   What are to top trending key words for video titles? 2. What are the top 5 video categories? 3.  Is there evidence of video maturation cycle? Null Hypothesis H0: YouTube videos have no maturation process, the engagement is random. Alternative Hypothesis H1: YouTube videos have a maturation process, engagement is NOT random. The above Word Cloud is…