Lesson - Statprob-1
Lesson - Statprob-1
LESSON - STATPROB 1
For this is sinasabi rito na same concept lang daw yung data mining and big
data. So bakit sinasabing same concept lang sila? So basically, big data kasi
means it’s mass volume of data or information so bulk talaga siya either
structured or unstructured data. While data mining naman is it talks about
recognizing the pattern from a large dataset. For example is in a healthcare,
there are a lot of medical records about their patients when it comes to
diseases so what data mining do is that it helps the data scientist to recognize
the pattern from those records so that they would be able to know what are the
similarities between those diseases so that they will be able to create a
medicine for it. So need niyo lang tandaan dito is sinasabing same concept
daw ang dalawang ‘to.
LESSON - STATPROB 2
combined it is the prediction and the cause and effect of a situation then the
prescriptive analytics talk about not just predicting but also suggesting for an
alternative course of action. Machine learning is a branch of AI. Example is the
sales dept. predicted that they will have low sales this month, thats the
predictive. Then they learned the cause of it since the effect is already about
low sales then they discovered it was because of their sudden increase in
prices so that’s the causal. Then the marketing department suggested that they
should change their marketing strategy to avoid this sudden low sales and
that’s the prescriptive. Then since they want to be able to finish this task
immediately, they will ask for a help on a machine learning or an AI for their
work to be more convenient. Remember that when it comes to this machine,
they just follow a certain pattern so that they will be able to execute a certain
task.
LESSON - STATPROB 3
For Andrew Gelman
Dito naman is sinasabi niyang hindi raw statistic ang pinaka importante sa data
science. Kasi even earlier, I keep mentioning that data science and statistic are
just the same based from the statement of other professor but then here is
kaya niya nasabing hindi ito pinaka importanteng part kasi when we heard
word data, what comes to our mind are either statistic or information. but then
it’s not just about statistic, to be able to be a great data scientist you must have
other skills like when it comes to coding or how to work with databases since
those are included in data science. It’s not just about analyzing statistics, since
here statistic for him is just another tool to be able to do data science but then
it’s not the most important tool or skill.
Normally, when people analyze data (which is like looking at pieces of the
puzzle), they try to explain what they see in the puzzle. They might say, "This
piece is blue, so it goes with the sky." This helps them understand what's
already there in the puzzle.
Now, imagine you have a different kind of puzzle. Instead of just explaining
what's already there, you're trying to find pieces that fit together in a special
way. You're not just saying, "This piece is blue, so it goes with the sky." You're
saying, "If I put these pieces together, I can see a picture of a tree."
That's what this person means when they say data science is different from
traditional data analysis. Data science doesn't just explain what's already in the
data, it tries to find patterns that help predict what might happen in the future.
It's like trying to predict what the finished puzzle will look like before you even
put all the pieces together. It looks for patterns that can help people make
decisions or take actions based on what might happen next.
DATA SCIENCE
LESSON - STATPROB 4
Statisticians and mathematicians were some of the first people to work on
figuring out how to analyze and make sense of large amounts of data.
However, as data science has grown, it's also borrowed ideas and methods
from other fields, like computer science, information theory, and even areas
like psychology and sociology.
So, when we say data science is interdisciplinary, we mean that it brings
together ideas and techniques from lots of different fields to help us
understand and work with data in new and powerful ways.
LESSON - STATPROB 5
Data scientists use advanced analytical techniques like machine learning, deep
learning, and text analytics to derive insights from data and build predictive
models. So yung mga ‘to kasi is more on AI related siya, ginagamit siya ng mga
data scientist para mas ma analyze nila yung data and ma predict nila yung
future outcomes ng data or malaman nila yung pattern kaya need nila ng
analytical techniques
R language
So ito po is designed specifically designed for statistical analysis and data
visualization. Platform independent din siya kaya pwede siya magamit kahit
saang operating system and free software rin ito.
Phyton Language
So we all know what phyton is because of MIL, phyton is versatile so mas
preferred ‘to ng mga programmer compared to other language since mas
simple siya and mas madali maintindihan.
SAS LANGUAGE
LESSON - STATPROB 6
ito naman ay prominent statistical analysis tool widely used in commercial
analytics
Statistic
So basically as I’ve said earlier, statistic is related to data science. It’s also
about learning an information about something. Statistic help us especially
business owners in making decisions for their business through the help of
statistician.
STATISTICIAN
yung sinasabing applied statistic dito is about application of gathered data to
real life situation. most statistician may problem solving skills since hindi lang
dapat related to technology and skills na meron ang statistician since they r the
one who help businesses to properly read the gathered data and make
decisions
SAMPLE VS POPULATION
let's pretend you have a huge bucket filled with your favorite toys. That big
bucket with all your toys inside is like the population – it's every single toy you
have.
Now, let's say you want to know which toys are the most popular among your
friends, but you can't ask everyone because there are so many friends! So, you
decide to ask just a few of your friends which toys they like the best. The toys
that your friends picked and told you about, that's your sample.
So, the population is all the toys in your big bucket, and the sample is just the
few toys your friends told you they liked. You use the sample to understand
what toys are popular among all your friends, even though you can't ask every
single friend about every single toy.
Descriptive Stat
Inferential stat
LESSON - STATPROB 7
Alright, imagine you have a big jar of cookies, but you can't eat all of them. So,
you take a few cookies out to taste, and based on how those cookies taste, you
guess what all the cookies in the jar might taste like. That's kind of like
inferential statistics!
We use inferential statistics to figure out if what we find in our small group is
likely to be true for the whole group. For example, if we find that the cookies
we tried are sweet, we might guess that most of the cookies in the jar are
sweet too.
Scientists and researchers use fancy math methods, like the t-test or analysis
of variance, to help them make these guesses. It's like using special tools to
help figure out what all the cookies in the jar might be like, even though we
can't taste all of them.
LESSON - STATPROB 8