Statistics for Data Science | Probability and Statistics | Statistics Tutorial | Ph.D. (Stanford)

Great Learning offers a range of extensive Data Science courses that enable candidates for diverse work professions in Data Science and other trending domains. The faculty team of the Data Science Courses comprises top academicians in Data Science along with many skilled industry practitioners from leading organizations that practice Data Science. Over 500+ Hiring Partners & 8000+ career transitions over varied domains.

One of the most critical aspects of the data science approach is our perception of getting the information processed. In developing insights from our accumulated data, we dig out the possibilities. And those possibilities are known as statistical analysis in Data science.
Statistics acts as a tool to gather, extract, analyze, and review data, which is an input to Data science techniques; hence, learning statistics is a baby step toward becoming a data scientist. Great Learning‘s Statistics for Data Science course is for beginners and professionals who want to upgrade their skills in data science domains and learn everything about statistical analysis.

🏁 Topics Covered:
Introduction - 00:00:00
1. Statistics vs Machine Learning - 00:02:22
2. Types of Statistics [Descriptive, Prescriptive and Predictive - 00:09:05
3. Types of Data - 01:50:45
4. Correlation – 02:46:02
5. Covariance – 02:52:33
6. Introduction to Probability – 04:26:55
7. Conditional Probability with Baye’s Theorem – 05:24:00
8. Binomial Distribution – 06:17:01
9. Poisson Distribution – 06:36:02

🔥Check Our Free Courses on with free certificate:

Here are the links for our other full course videos:

⚡ About Great Learning Academy:

ABOUT GL:
⚡ About Great Learning:
With more than 5.4 Million+ learners in 170+ countries, Great Learning, a part of the BYJU'S group, is a leading global edtech company for professional and higher education offering industry-relevant programs in the blended, classroom, and purely online modes across technology, data and business domains. These programs are developed in collaboration with the top institutions like Stanford Executive Education, MIT Professional Education, The University of Texas at Austin, NUS, IIT Madras, IIT Bombay & more.

[greatlearning]

🔹 Topics Covered:
Introduction - 00:00:00
1. Statistics vs Machine Learning - 00:02:22
2. Types of Statistics [Descriptive, Prescriptive and Predictive - 00:09:05
3. Types of Data - 1:50:45
4. Correlation – 2:46:02
5. Covariance – 2:52:33
6. Introduction to Probability – 4:26:55
7. Conditional Probability with Baye’s Theorem – 5:24:00
8. Binomial Distribution – 6:17:01
9. Poisson Distribution – 6:36:02

[carlosmontejo]

Absolutely the best video on statistics that I have found on YouTube - and I've viewed several such videos. I like that the professor explains a topic from many angles, has charisma, patience with class questions and includes many real-world examples. It's the perfect blend of theory and applied statistics.

[DhirajPatra]

He is really a great professor. I have been studying statistics since school and then using years for my profession. However, the way he teach and explain from one chapter to another chapter and subject is super. Thanks

[animeshkaushik]

Median : "Age of the avg person."

Mean : "Avg age of a person"

[josephtran]

Wow, what a great course with an awesome professor. He goes way beyond teaching the mechanics of statistics but makes distinctions and asks thought provoking questions that really help you crystallize in your head what you are trying to do.

[harshavardhanasrinivasan]

The way the professor teaches is simply mind-blowing . Full credits to the team who made the entire session free!.

[gururajgovindasamy]

As practicing design engineer in West Cost medical industry, I find Professor Dr. Sarkar way of explaining the most complex subject in a practical approach very rewarding and helps in right metal representation for long term understanding. Although I have taken similar courses in Stanford paying close to 2K plus USD came out even more confused and even gave up statistical approach . Thanks for sharing for free and hope this benefits the transition from Excel based modeling to Python and would highly recommend to any one working with data and design.

[greatlearning]

Guys, what else do you want to learn from us? Please do comment below

[greatlearning]

Here is our full course video on 'Machine Learning with Python':

[bhanukuchibhotla]

Fantastic course! For those who have a fear factor of stats and probability, this course will certainly will help allay those fears. Dr. Sarkar focused on concepts with perfect analogies which helps understand the subject better. Thank you Dr. Sarkar.

[faisalIqbal_AI]

00:02 Statistics forms the basis of all data science concepts
02:09 Different approaches in statistical and machine learning thinking
06:39 Understanding data questions for analysis
08:51 Understanding the three-step process of descriptive, predictive, and prescriptive analysis.
13:18 Self-driving cars should stop for pedestrians without sudden braking
15:28 Doctors use data analytics to recommend blood tests based on symptoms.
19:38 Blood samples from different parts of the body vary due to asymmetry
21:32 Blood sugar testing and interpretation
25:45 Descriptive analytics aims to understand certain things about data to reach conclusions more rigorously.
27:47 Understanding the implications of ranges and thresholds in statistics
31:53 Understanding customer characteristics and product market fit in business.
33:51 Understanding data preparation and visualization in Python
38:13 Understanding the calculations for descriptive statistics
40:22 Determining a representative value for a variable.
44:44 Understanding probabilities and descriptions
47:27 Understanding mean and median in statistics
51:43 Understanding the concept of Right skewed data distribution.
53:35 Understanding skewness in data
57:51 The book explains concepts but not coding syntax.
59:35 Statistics is important for data science but choose your battles wisely.
1:04:08 Variance measures the variability of data.
1:06:17 Gauss's victory in the argument over the use of mean absolute deviation
1:10:41 Bank balances are rarely equal to your actual average bank balance.
1:12:59 The range and interquartile range are important measures of dispersion in statistics.
1:17:14 Storing real data requires metadata, adding complexity to data storage
1:19:18 Histograms visually represent data distribution
1:23:14 Data is often transformed to fit specific algorithms and needs
1:24:54 Struggle between doing the right thing and the wrong thing in data science.
1:28:59 Understanding histogram and box plot in data analysis
1:31:12 Understanding box plots and whiskers in statistics
1:35:55 Box plot for numerical data and cross tab for categorical data
1:37:53 Data description and analysis for statistics
1:42:20 Univariate analysis focuses on studying one variable at a time
1:45:28 Understanding histograms as a visual tool for data distribution
1:49:54 Fitness variable can be treated as an ordinal categorical variable.
1:52:16 Data can be misinterpreted as a different type, e.g. a number being analyzed as a category.
1:56:41 Using statistics to understand future customer behavior
1:59:10 Understanding the concept of distributions in statistics.
2:03:05 Statistics involves abstracting away from the data to estimate the underlying true distribution.
2:05:05 Understanding the concept of sampling variability.
2:08:38 Understanding distribution and density functions.
2:10:47 Using statistics to make strategic decisions
2:14:59 Estimating population mean with uncertainty
2:16:56 Understanding variation and prediction in statistics
2:20:56 Sampling more data helps understand unknown distributions
2:22:52 Challenges of utilizing big data for making efficient use of information
2:26:40 Statisticians make assumptions about data distributions to simplify calculations.
2:28:35 Different industries have their own favorite distributions based on their data form.
2:32:28 Understanding the importance of model generalizability
2:34:26 Estimating unknown population parameter using mean or median
2:38:33 Heavy tail distribution impacts mean and median differently.
2:40:39 Understanding the concept of mode in statistics
2:44:43 Exploring bivariate analysis and correlation
2:46:53 Understanding pairs of observations and calculating the average
2:52:24 Covariance measures the relationship between X and Y.
2:55:04 Price and profit have a positive correlation.
2:59:02 Normalization of units for statistical analysis is critical.
3:01:17 Correlation measures the linear relationship between variables.
3:06:42 Low correlation means no relationship between variables
3:08:59 The relationship between height and weight in healthy individuals
3:13:21 Correlation measures the relationship between variables.
3:15:16 Heat maps provide visual representation of correlation and relationships between variables
3:19:43 Regression has 3 uses: descriptive, predictive, and prescriptive
3:22:06 Explaining regression analysis and interpretation of regression coefficients
3:27:03 Understanding statistical quality assessment in data science
3:29:19 Hypothesis testing helps determine the predictive power of variables in the model.
3:33:44 Beta 1 provides flexibility for better model fitting.
3:36:05 Prediction and forecasting in statistics
3:40:37 Describing the nature of the relationship between variables using linear regression
3:42:54 Visualization can be done in multiple dimensions in Python for data summarization.
3:47:37 Finding the best line to describe data points.
3:50:17 Linear regression minimizes the sum of square distances from the data.
3:55:00 Machine learning algorithms aim to come closest to the expected output based on the input.
3:56:55 Algorithms in data science compare predictions with actuality to minimize distance.
4:01:01 Algorithm generalization through test validation
4:02:48 Measuring correctness and closeness is essential for predictive models
4:06:36 Estimating A and B through minimization
4:09:02 Linear regression and the calculation of the line equation
4:13:31 Using equations for descriptive analysis
4:15:23 Learning statistical computations and calculations.
4:22:12 Understanding the units in linear regression
4:24:49 Importance of normalizing numbers in hypothesis testing
4:28:24 Distinguishing between experimental and observational studies
4:30:28 Importance of designing experiments
4:34:26 Calculating the probability of multiple defects
4:36:43 Calculating the probability of at least two defective parts in a sample space.
4:41:44 Independence in probability allows for multiplication of probabilities
4:43:49 Probability and Statistics Laws
4:49:09 Analyzing the chances of selling children's books to three potential buyers
4:51:09 Click through rate measures the percentage of people who click on an ad after seeing it.
4:54:56 Probability is a number between 0 and 1, representing the likelihood of an event.
4:56:49 Wave function collapse in quantum physics
5:01:21 Probability of events occurring together and independently
5:04:05 Understanding joint probability and conditional probability
5:08:27 Understanding set theory and the multiplication rule in probability theory
5:11:06 Understanding independence and probability
5:15:39 Calculating the probability of getting two adjacent seats on a flight without pre-booking.
5:17:49 Conditional and marginal probability explained with an example
5:22:28 Understanding marginal and conditional probabilities
5:24:52 Probability of spam given words is used to determine if an email is spam or not.
5:29:55 Bayes' theorem is central to machine learning
5:32:09 Bayes' theorem is a foundation for supervised learning
5:36:05 Probabilistic way of thinking in data science
5:38:16 Teaching a computer to have a sense of value and make decisions similar to humans.
5:42:25 Learning system provides probabilities, decision is up to you
5:44:23 Threshold for answering questions based on certainty
5:48:07 Evolution of information transference in the computing world.
5:50:11 Calculating probability of HIV given positive test
5:55:38 Understanding the 95% accuracy of a test
5:58:11 Probability and statistics in disease testing
6:02:57 Implications of multiple tests on probability
6:04:57 Bayes' theorem helps in understanding the probability of an event given certain conditions.
6:09:38 Calculating the probability of spam given the presence of congratulations.
6:12:26 Probability of an email being spam based on the presence of specific words
6:16:55 The binomial distribution counts the number of successes out of n trials.
6:19:47 Probability distribution of accounts paying on time
6:24:26 Understanding the binomial distribution for calculating probabilities
6:26:47 Understanding the concept of combinations
6:31:28 Probability of timely payments in a business context
6:33:48 Calculating the probability of bill payments for business revenue estimation.
6:37:40 Calculating probability for future bill payments
6:39:44 Understanding the concept of Target P and its application in various scenarios.
6:43:48 Calculating the probability for a given range using computational reasons
6:46:07 Understanding the normal distribution and its implications in probability and statistics.
6:50:51 Using statistical principles to estimate average and standard deviation without access to data.
6:52:44 Calculating probability using normal distribution
6:58:48 Mean and standard deviation can be used to make assumptions about the data distribution.
7:01:16 Normal distribution is often used as an assumption based on the central limit theorem.
7:05:20 Understanding the importance of differentiating between business and tech questions in data science.
7:07:19 Importance of normality in calculations and reliability of numbers
7:11:27 Achieving Six Sigma for high quality production

[jamesstewart]

James Stewart
Enjoyed Dr. Sarkar statistics for data science course he described many areas that are now trending in businesses and private industries. I copied and write down many of the ideas and applications for descriptive, predictive, and prescriptive applications. I also enjoyed his input for book learning with Python and other books as well as many of the problems he solved using Python and R programming.

[namelastname]

love how engaging the teacher makes this

[kashif_iftekhar]

3:08:30 BMI is actually Weight/(Height)^2, where height is in meters and weight in kilograms

[sushantrauthan]

the best lecture till date i've ever heard i've read engineering statistics but the way sir conducts his lectures speaks volumes about his experiance while dealing with newbies, this lecture should be standard procedure for absolute intermediates like me who have a little bit of knowledge but are transitioning into advanced levels. Thank you Great Learning for this amazing tutorial hope you upload some more...

[alpham]

Dr Sarkar is brilliant!! His style is captivating and makes foreign concepts so much easier to understand. Which video would you suggest for those not familiar with python? I've watched the first 35mins but now he's gone into Python and I don't think I'm ready to continue watching the rest just yet.

[SBhupendraAdhikari]

Very easy explanation, I can watch this many times instead of watching a movie or web series, seems like someone narrating a beautiful story

[lathaananthapadmanabhan]

A good teacher is a worthy citizen of this world, best creator. Excellent.

[algo_trader]

Wonderful content and presentation, I feel like I missed Dr.Sarkar sir all these days. Thanks to greatlearning team for these lectures. It will be great if a video is made up on time series Analysis also. Thanks team for all your effort and introduce to us the great professor Dr.Sarkar sir.

[rohitsaka]

This was really the best course I Did, Learned alot and earned the certificate of completion as well.Thank you so much Great Learning for this Beautiful content and Dr.Abhinanda Sarkar Sir is the best is explaining things.Thank you very much @GreatLearning