LGBT Students Question Purpose of Life ua-cam.com/video/E-KW9tUETN4/v-deo.html “Jesus Didn’t Preach Christianity, but Islam!” ua-cam.com/video/qvBNViZG0Mk/v-deo.html
00:02 Statistics deals with the collection, analysis, and presentation of data. 02:48 Descriptive and Inferential Statistics 08:08 Understanding the difference between standard deviation and variance 10:47 Contingency table helps analyze relationship between two categorical variables 16:01 Hypothesis testing and P value 18:28 Interpreting P-values and Types of Errors 23:16 Understanding levels of measurement is crucial for data analysis 25:43 Different levels of measurement in data science 30:37 Measurement of interval level and true zero point in statistics 33:08 Levels of measurement in statistics 38:24 Understanding the T Test in Data Science 40:52 T Test answers if study duration of men and women is significantly different 45:37 Determining if null hypothesis is rejected using critical T value 48:03 Interpreting t-test results for independent samples 53:03 Using ANOVA for analyzing differences between groups 55:27 Understanding null and alternative hypothesis in population mean comparison 1:00:31 Two-way Anova tests the effects of two independent variables on a dependent variable. 1:03:03 Two-way Anova can answer three main questions about the factors' impact on the dependent variable. 1:07:49 Conducting two-way ANOVA for testing the influence of drug type and gender on blood pressure reduction. 1:10:10 Variance in a Two-Way Analysis of Variance 1:15:12 Calculating F values for factor A, B, or interaction 1:17:40 Repeated measures Anova tests for significant differences in dependent samples 1:22:29 How to calculate and interpret analysis of variance with repeated measures 1:24:50 ANOVA with repeated measures and Bonferroni post hoc test 1:29:44 Calculating F value and P value in ANOVA analysis 1:32:13 Comparing cholesterol levels across different diets and time points 1:36:57 Testing assumptions in ANOVA 1:39:20 Understanding hypothesis testing in Data Science 1:44:12 Nonparametric tests have fewer assumptions than parametric tests 1:46:47 Using rankings for Spearman's correlation and conducting T tests for independent samples 1:51:41 Analytical tests for normal distribution involve several procedures and interpreting the P value 1:54:16 P value is influenced by sample size 1:59:27 Lavine's test is used to test assumptions for hypothesis tests. 2:02:08 Testing for Equality of Variances and Nonparametric Methods 2:07:00 Interpreting Mann-Whitney U test results 2:09:36 Calculating man with U test and P value calculation 2:14:39 Wilcoxon test compares ranks of dependent samples 2:17:13 Calculation of Wilcoxon Test for rank sums 2:22:26 The cral Wallis test is a non-parametric counterpart of the single factor analysis of variance 2:24:47 Usage and assumptions of Crosstab Volis Test 2:30:05 Friedman test for analyzing differences between dependent samples 2:32:34 Dependent samples in statistics 2:37:28 Performing nonparametric test for analyzing response time differences 2:40:08 Analyzing response time differences at different time points 2:45:17 Kai Square test measures relationship between variables 2:47:44 Understanding Chi-Square Test Results 00:00 Understanding correlation analysis 2:55:39 Understanding Pearson correlation coefficient 3:01:01 Understanding Pearson and Spearman correlations in Data Science 3:03:28 Explaining the calculation of Spearman correlation using ranks 3:08:43 Correlation coefficient analysis and testing 3:11:14 Calculating Pearson correlation for nominal variables 3:16:04 Causality vs Correlation 3:18:39 Negative correlation implies lower body temperature with more head lice and higher body temperature with fewer head lice. 3:23:44 Regression analysis is crucial for predicting outcomes based on various factors. 3:26:17 Logistic regression is used for categorical dependent variables like yes or no. 3:31:16 Linear regression models help estimate relationships between variables. 3:33:44 Understanding error in regression models like Epsilon 3:38:51 Understanding the correlation in linear regression 3:41:21 Understanding F test in data analysis 3:46:23 Check for linear relationship and normal distribution in regression model 3:48:45 Multicollinearity can lead to unstable regression models 3:53:49 Interpreting regression coefficient for gender 3:56:30 Creating dummy variables from categorical data 4:01:28 Logistic regression estimates the probability of occurrence of a particular characteristic 4:04:02 Logistic Regression ensures values between 0 and 1 for predictions 4:09:17 K-means clustering algorithm steps 4:11:45 Determining optimal number of clusters using elbow method
@@Adiishresthaaa Yes, of course, she wants to sell her book, but I think it's ok, almost everybody wants to profit from his/her knowledge... I'd buy the book.
I just compelted less than 4 minutes of the entire 4 hours video and found that I'm already in love with the trainers explanation, classification of learning and the courage she gave before hand. I love this and will watch for the NeXT 2 years in my M.Sc (Applied Statistics). More comments on the fly. I love Statistics.
@@datatab Hi mam,can you please share which video has explaination regarding Complete Random Block Design...I have seen most of your videos but couldn't find this topic! Please shed some light upon this! Thanks
@@munchkin98phd17 We do not have a specific video for this! But it is very similar to a two way ANOVA except that a block is used instead of the second factor.
I am preparing for CHDA (Certified Health Data Analyst) certification and I found this is most useful for me to prepare for the exam. Thank you so much! It was we presented and explained very well.
Right now I'm at the reading 15 minutes and 41 seconds. The trainer is saying about Hypothesis Tests and Various types of Hypothesis tests. I love this video.
Her voice is great! not boring for statistics. I like how she pronounces words. It shows she is not reading directly from the paper; she's also on topic and understands each word she says. thank you
The lecture was really very organized, and it even seemed that every single item of information had been put in place with great thought. What's more, the high level of engagement has captured viewers by making difficult concepts easily apprehensible, thus encouraging active participation. Thank You!
@@datatab Haven't watched the video and I'm not a numbers guy. I'm just asking for my kid. Can this video be of any learning benefit to an 12 year old.
This is the best statistics class I have ever sat in. There is something about the crisp graphics and your reassuring voice that helps learn stats in bite-sized sessions. Thank you.
It helps a lot! Thanks!! we may come from different countries, speak different languages, not knowing each others, but what you have been doing means that humanity is still exist. Love from Indonesia!! You make another friend from Indonesia🤝
Main reason I love the internet is cuz I can study a whole topic in several hours and have a fairly good understanding to converse and ask more in depth about the field at hand.
I always find this page very useful and I like the Lecturer as well, She speaks very clearly and gets everything right inside my ears. I will love to meet Her one day personally and one on one. I will be very glad.
An excellent presentation of the required population's education about analytical models, logic, mathematics and data science. Especially the lecturer, who reaches a level of elite professionalism, I would easily certificate being able to handle and manage our societies future development, while being able to go to bed happily ever after, without worrying about the future of our children too much.
Hello, Dear, I joined your channel recently and your videos are helpful for statistics. I love your brief description with great examples and clear explanations. But now I want to ask one question and I hope, you will clarify it. The question is "What is the difference between multivariable and multivariate analysis".
Using this comment section as notes kindly don't mind ----> Important time lap for me 13:37 inferential statistics basic 34:57 T test ----> what to do after competing this video 1) explore Descriptive 2) explore p value 3) test for normal distribution 4) T value
The lecture was certainly very valuable and excellent, but the presentation was amazing. Can you tell me about the program used in this presentation work?
Hello from Brisbane. I will definitely be telling all my colleagues about you. Hoping to see lots of scientific papers with your name in the citation for years to come.
Summary notes: - [What are the key differences between descriptive and inferential statistics?](#related) - [How do you perform a hypothesis test?](#related) - [What is the significance of correlation analysis in statistics?](#related) Highlights: @00:01 Statistics provides essential tools for collecting, analyzing, and presenting data. This tutorial covers foundational concepts and statistical tests to help understand data analysis effectively. -Descriptive statistics summarize data sets, providing insights into sample characteristics without inferring broader population conclusions. This approach is fundamental in understanding collected data effectively. -Measures of central tendency and dispersion help describe data sets meaningfully. Understanding these concepts is vital for interpreting data distributions and variability effectively. -Inferential statistics enable conclusions about a population based on sample data, involving hypothesis testing and estimations. This is crucial for making predictions and decisions based on limited information. @15:13 Hypothesis testing is a method used to evaluate claims about population parameters based on sample data. It involves determining the likelihood of observed results under the assumption that a null hypothesis is true. -The null hypothesis posits that there is no effect or difference in the population. This hypothesis is tested against an alternative hypothesis to find evidence for change. -The P-value indicates the probability of observing a sample that contradicts the null hypothesis. A low P-value suggests that the null hypothesis may be rejected in favor of the alternative hypothesis. -Type I and Type II errors represent the risks in hypothesis testing. A Type I error occurs when a true null hypothesis is incorrectly rejected, while a Type II error happens when a false null hypothesis is not rejected. @30:10 Understanding the difference between ratio and interval measurement levels is essential for accurate statistical analysis. Ratio scales have a true zero point, allowing meaningful comparisons, while interval scales do not. -Interval scales, unlike ratio scales, do not have a true zero point. This limits their ability to express relative comparisons like one value being three times another. -A ratio scale measures quantities with a true zero, allowing for meaningful multiplication and division. This makes it possible to express one value as a multiple of another. -Examples of measurement types include nominal, ordinal, interval, and ratio. Understanding these levels helps in selecting the appropriate statistical tests for data analysis. 45:13 The significance level, usually set at 5%, helps determine whether to reject the null hypothesis based on the P value and T value calculations. If the P value is less than 0.05, we have enough evidence to reject the null hypothesis. -Understanding the difference between directed and undirected hypotheses is important in statistical testing. Directed hypotheses specify the expected direction of the difference. -The T Test is used to compare the means of two groups and determine if there is a significant difference between them. This is crucial in hypothesis testing. -ANOVA is an extension of the T Test that allows for comparison across more than two groups. It assesses whether there are statistically significant differences among group means. 1:00:29 Two-way ANOVA is a statistical method that examines the impact of two categorical variables on a dependent continuous variable. It allows for a deeper understanding of how these variables interact with each other. -The two-way ANOVA extends the one-way ANOVA by including two independent variables, allowing for more complex interaction analysis. This method can identify how multiple factors influence outcomes. -In two-way ANOVA, factors can include categorical variables such as gender or treatment type, each with different levels. Understanding these levels is crucial for accurately interpreting results. -Key assumptions for conducting a two-way ANOVA include normality of data, homogeneity of variance, and independence of observations. Meeting these assumptions is vital for valid results.
1:17:13 Repeated measures ANOVA is used to determine if there are statistically significant differences between three or more dependent samples. It extends paired samples T-Test, allowing analysis across multiple conditions or time points. -The null hypothesis in repeated measures ANOVA states there are no differences in means across different time points or conditions. The alternative hypothesis suggests there is a significant change. -Assumptions for repeated measures ANOVA include normality and sphericity of the data. These can be tested using QQ plots and Mauchly's test, respectively. -Calculating repeated measures ANOVA involves estimating sums of squares and mean squares for treatment and residuals. The F value is derived from these calculations to assess significance. 1:31:29 Mixed model ANOVA is a statistical method that analyzes data with both between-subject and within-subject factors. It helps determine how different factors affect dependent variables over time. -Understanding between-subject and within-subject factors is crucial for mixed model ANOVA. Between-subject factors involve different groups, while within-subject factors involve repeated measures on the same subjects. -Mixed model ANOVA can identify interaction effects between factors. This means it can determine whether the impact of one factor varies depending on the level of another factor. -The assumptions of mixed model ANOVA include normality, homogeneity of variances, and independence of observations. Each assumption ensures the validity of the statistical results obtained. 1:45:33 Understanding the differences between Pearson and Spearman correlations is crucial for effective data analysis. Pearson uses raw data, while Spearman relies on ranked data, impacting their applications. -Pearson correlation is appropriate for linear relationships and normally distributed data. It calculates the linear relationship between two continuous variables using their raw scores. -Spearman's rank correlation is nonparametric, making it useful for ordinal data or non-normal distributions. It assesses the strength and direction of the relationship between two ranked variables. -Hypothesis testing often requires checking assumptions like normality and equal variances. Using tests like the T-test or Mann-Whitney U test can help determine significant differences between groups. 2:00:38 The video explains Lavine's test, which evaluates the equality of variances between groups using calculated test statistics and P-values. It also discusses implications for hypothesis testing based on P-values. -A smaller P-value indicates that the null hypothesis of equal variance can be rejected. If the P-value is greater than 0.05, the null hypothesis is not rejected. -When data does not meet normal distribution assumptions, nonparametric methods like the Mann-Whitney U test can be employed. This test evaluates rank sums rather than mean differences. -The video demonstrates how to perform the Mann-Whitney U test with practical examples. It highlights differences in methodology compared to traditional T-tests for independent samples.
2:15:43 The Wilcoxon test is utilized to compare the central tendencies of two dependent samples when normal distribution cannot be assumed. It evaluates whether there is a significant difference between paired observations in a population. -The null hypothesis of the Wilcoxon test states that there is no difference in the central tendencies of the dependent samples. The alternative hypothesis asserts that a difference exists. -In cases where normal distribution is not present, the Wilcoxon test ranks the differences between paired observations. This method is crucial for analyzing non-normally distributed data effectively. -Calculating the Wilcoxon test involves determining the rank sums of positive and negative differences. The test statistic W helps to assess whether these sums are approximately equal, which is essential for hypothesis testing. 2:32:17 The Friedman's test is a nonparametric statistical method used to determine if there are significant differences between three or more related groups. It analyzes ranked data rather than raw values, making it suitable for non-normally distributed datasets. -The Friedman's test is often used in situations involving repeated measures, such as assessing the same subjects over different time points. This highlights its relevance in analyzing dependent samples. -Understanding the null hypothesis in the Friedman's test is crucial; it posits that there are no significant differences among the dependent groups being analyzed. This hypothesis guides the interpretation of results. -The test results include a Chi-square value and a P-value, which help determine whether the null hypothesis can be rejected based on the significance level. A greater understanding of these values is essential for correct interpretation. 2:45:59 The video explains how to analyze the relationship between gender and newspaper preference using the Chi-Square test. It demonstrates how to interpret and calculate the test results effectively. -The Chi-Square test helps determine if there's a significant relationship between categorical variables. It compares observed frequencies in a contingency table to expected frequencies. -Using statistical software like DataTab simplifies the Chi-Square test process. The software automatically calculates results, making it easier for users to interpret their data. -The assumptions for the Chi-Square test include having expected frequencies greater than five. If these assumptions are met, the results can be considered valid. 3:01:04 Understanding the difference between Pearson and Spearman correlation coefficients is crucial in statistical analysis. While Pearson measures linear relationships, Spearman evaluates monotonic relationships using ranks instead of raw data. -Pearson correlation requires both variables to be normally distributed to interpret the significance of its coefficient correctly. If normality is violated, results may not be reliable. -Spearman correlation is beneficial when data does not meet the assumptions of normality. It assesses relationships based on ranks, making it more robust for non-parametric data. -Kendall's tau is another nonparametric alternative that can be preferred over Spearman when dealing with tied ranks. It assesses the ordinal relationship between two variables effectively.
3:16:22 Understanding the distinction between causality and correlation is crucial in statistics. Causality implies a direct cause-and-effect relationship, while correlation merely indicates a relationship between two variables. -Correlation does not imply causation; it can often stem from common causes affecting both variables. An example is the correlation between ice cream sales and sunburn incidents. -Causality requires specific conditions to be established, including a significant correlation and a chronological sequence of events. These conditions help in determining true causal relationships. -Regression analysis is a powerful tool in statistics that allows for understanding relationships between variables. It can help predict outcomes based on independent variables. 3:31:13 Linear regression is a statistical method used to predict the value of a dependent variable based on the value of one or more independent variables. It utilizes the least squares method to find the best-fitting line through the data points. -The dependent variable in this context is the length of hospital stay after surgery, while the independent variable is the age of the patient. This relationship helps in optimizing hospital resources. -Calculating the coefficients of the regression model involves statistical programs, but it can also be done manually through correlation and standard deviation calculations. This method aids in understanding the relationship between variables. -Multiple linear regression expands on simple linear regression by allowing the consideration of multiple independent variables to predict a dependent variable. This is particularly useful in fields like social research and market analysis. 3:46:17 It's essential to check for linear relationships and normality in regression analysis to ensure meaningful interpretation of coefficients and predictions. This helps avoid larger-than-expected prediction errors. -Graphical methods like histograms and QQ plots are useful for checking normality of data distributions, ensuring that assumptions for regression analysis are met. These techniques provide visual insights into data behavior. -Homoscedasticity is crucial in regression, indicating constant variance of residuals across values, which ensures reliable error predictions. A lack of this condition can lead to inaccurate model interpretations. -Multicollinearity can distort regression results by making the effects of independent variables hard to distinguish. Diagnosing it through tolerance or VIF values helps maintain model stability and interpretability. 4:01:21 Logistic regression is a statistical method used for predicting the probability of a categorical dependent variable based on one or more independent variables. It is particularly useful in scenarios where the outcome is binary, such as disease susceptibility or voting behavior. -In medical research, logistic regression helps identify which factors, such as age, gender, and smoking status, influence disease occurrence. It enables researchers to understand the probability of a patient developing a specific illness. -The logistic regression function limits predicted values to a range between zero and one, making it suitable for binary outcomes. This is achieved through the logistic function, which transforms linear combinations of predictors. -The K-means clustering technique is introduced as a method for discovering hidden patterns in data. It groups data points into clusters based on their characteristics, enhancing data analysis and interpretation.
Really Don’t know How to Thank You❤❤.But You have Opened my eyes in a very meaningful way.Never the statistics was so much fun for me.I was always struggling in Data analysis.
This lecture clearly is for non mathematicians. In the last century I learned all this in school, but even with mathematical proofs which were all left out here.
I've been following your video posts. You made me confident before my students. A simple way to present technical jargons!!! I haven't bought the book going they the free sample one can tell it's worth a penny!!!
I am greatful to this good and elaborate explanation of statistics. This is Gem in my oncoming research work analysis for my MSc. Immunology. Thank you mum.
Well explained the essentials of the concepts and principles of statistics and related subjects. Thanks for posting this important and informative lesson!
If you like, please find our e-Book here: datatab.net/statistics-book
Haw I purchased the pdf of Book kidney help
@@PrinceKumarPatel-f4g You can just by it online here: datatab.net/statistics-book
@@datatab what is the price of this e book
hi, is there any way to get it for free?
actually i have limited resources.
is it?
LGBT Students Question Purpose of Life
ua-cam.com/video/E-KW9tUETN4/v-deo.html
“Jesus Didn’t Preach Christianity, but Islam!”
ua-cam.com/video/qvBNViZG0Mk/v-deo.html
I still can't believe material like this is available for free..... thanks a lot from Chile!!!!
00:02 Statistics deals with the collection, analysis, and presentation of data.
02:48 Descriptive and Inferential Statistics
08:08 Understanding the difference between standard deviation and variance
10:47 Contingency table helps analyze relationship between two categorical variables
16:01 Hypothesis testing and P value
18:28 Interpreting P-values and Types of Errors
23:16 Understanding levels of measurement is crucial for data analysis
25:43 Different levels of measurement in data science
30:37 Measurement of interval level and true zero point in statistics
33:08 Levels of measurement in statistics
38:24 Understanding the T Test in Data Science
40:52 T Test answers if study duration of men and women is significantly different
45:37 Determining if null hypothesis is rejected using critical T value
48:03 Interpreting t-test results for independent samples
53:03 Using ANOVA for analyzing differences between groups
55:27 Understanding null and alternative hypothesis in population mean comparison
1:00:31 Two-way Anova tests the effects of two independent variables on a dependent variable.
1:03:03 Two-way Anova can answer three main questions about the factors' impact on the dependent variable.
1:07:49 Conducting two-way ANOVA for testing the influence of drug type and gender on blood pressure reduction.
1:10:10 Variance in a Two-Way Analysis of Variance
1:15:12 Calculating F values for factor A, B, or interaction
1:17:40 Repeated measures Anova tests for significant differences in dependent samples
1:22:29 How to calculate and interpret analysis of variance with repeated measures
1:24:50 ANOVA with repeated measures and Bonferroni post hoc test
1:29:44 Calculating F value and P value in ANOVA analysis
1:32:13 Comparing cholesterol levels across different diets and time points
1:36:57 Testing assumptions in ANOVA
1:39:20 Understanding hypothesis testing in Data Science
1:44:12 Nonparametric tests have fewer assumptions than parametric tests
1:46:47 Using rankings for Spearman's correlation and conducting T tests for independent samples
1:51:41 Analytical tests for normal distribution involve several procedures and interpreting the P value
1:54:16 P value is influenced by sample size
1:59:27 Lavine's test is used to test assumptions for hypothesis tests.
2:02:08 Testing for Equality of Variances and Nonparametric Methods
2:07:00 Interpreting Mann-Whitney U test results
2:09:36 Calculating man with U test and P value calculation
2:14:39 Wilcoxon test compares ranks of dependent samples
2:17:13 Calculation of Wilcoxon Test for rank sums
2:22:26 The cral Wallis test is a non-parametric counterpart of the single factor analysis of variance
2:24:47 Usage and assumptions of Crosstab Volis Test
2:30:05 Friedman test for analyzing differences between dependent samples
2:32:34 Dependent samples in statistics
2:37:28 Performing nonparametric test for analyzing response time differences
2:40:08 Analyzing response time differences at different time points
2:45:17 Kai Square test measures relationship between variables
2:47:44 Understanding Chi-Square Test Results
00:00 Understanding correlation analysis
2:55:39 Understanding Pearson correlation coefficient
3:01:01 Understanding Pearson and Spearman correlations in Data Science
3:03:28 Explaining the calculation of Spearman correlation using ranks
3:08:43 Correlation coefficient analysis and testing
3:11:14 Calculating Pearson correlation for nominal variables
3:16:04 Causality vs Correlation
3:18:39 Negative correlation implies lower body temperature with more head lice and higher body temperature with fewer head lice.
3:23:44 Regression analysis is crucial for predicting outcomes based on various factors.
3:26:17 Logistic regression is used for categorical dependent variables like yes or no.
3:31:16 Linear regression models help estimate relationships between variables.
3:33:44 Understanding error in regression models like Epsilon
3:38:51 Understanding the correlation in linear regression
3:41:21 Understanding F test in data analysis
3:46:23 Check for linear relationship and normal distribution in regression model
3:48:45 Multicollinearity can lead to unstable regression models
3:53:49 Interpreting regression coefficient for gender
3:56:30 Creating dummy variables from categorical data
4:01:28 Logistic regression estimates the probability of occurrence of a particular characteristic
4:04:02 Logistic Regression ensures values between 0 and 1 for predictions
4:09:17 K-means clustering algorithm steps
4:11:45 Determining optimal number of clusters using elbow method
Thank you!
Thank you for the table of contents.
Wonderful.
Based TY
this is amazing , thank you so much
The world is still exists because of people like you. Thanks a ton for this lecture. God bless you.
no she is sellinng her course and book
@@Adiishresthaaa whatever might be her intentions this course has helped me a lot
@@Adiishresthaaa Yes, of course, she wants to sell her book, but I think it's ok, almost everybody wants to profit from his/her knowledge... I'd buy the book.
As a matter of fact, I already bought the book and it is an excellent book by the way, it is helping so much in my university studies.
@@Adiishresthaaa So? Why should she deprive herself of what she rightfully deserves?
I just compelted less than 4 minutes of the entire 4 hours video and found that I'm already in love with the trainers explanation, classification of learning and the courage she gave before hand. I love this and will watch for the NeXT 2 years in my M.Sc (Applied Statistics). More comments on the fly. I love Statistics.
I can perfectly hear her voice in my head during exams. Honestly it helps so much. Thank You!
Stats
1. A sample -- descriptive
2. Population -- inferential
4:58 measure of central tendency
💥
It is something very special that you have created to educate us. Absolutely Great Efforts. Thank you very much.
It's my pleasure! Many thanks for your nice feedback! Regards, Hannah
@@datatab Muchas gracias por tanto esfuerzo para nosotros aprender mas, DIOS te bendiga y te guarde de todo mal, bendiciones amiga.
@@juangs1168 Many thanks for your nice feedback!
@@datatab Hi mam,can you please share which video has explaination regarding Complete Random Block Design...I have seen most of your videos but couldn't find this topic! Please shed some light upon this!
Thanks
@@munchkin98phd17 We do not have a specific video for this! But it is very similar to a two way ANOVA except that a block is used instead of the second factor.
I am preparing for CHDA (Certified Health Data Analyst) certification and I found this is most useful for me to prepare for the exam. Thank you so much! It was we presented and explained very well.
Glad it is helpful : ) Regads Hannah
@dhanusu11 please is there a course or program on certified health data analyst you took to be able to CHDA exam? Kindly share.
@dhanusu please can you share more on the CHDA program
Right now I'm at the reading 15 minutes and 41 seconds. The trainer is saying about Hypothesis Tests and Various types of Hypothesis tests. I love this video.
I finally finished it it took me 3 days, on an off. Comprehensive enough for my doubts.
Hii
Das ist ein ganz ganz tolles Video. Ich nehme gerade meinen ersten Statistik Kurs in Psych und war endlos verzweifels. Danke vielmals.
Her voice is great! not boring for statistics. I like how she pronounces words. It shows she is not reading directly from the paper; she's also on topic and understands each word she says. thank you
The lecture was really very organized, and it even seemed that every single item of information had been put in place with great thought. What's more, the high level of engagement has captured viewers by making difficult concepts easily apprehensible, thus encouraging active participation. Thank You!
Many many thanks for your nice feedback!!! Regards Hannah
Splendid, I'll save this video in my playlist and share it with friends.
My plan 30 mins per day till I digest and understand all statistics
❤❤
Greate : ) Thanks!
@@datatab Haven't watched the video and I'm not a numbers guy. I'm just asking for my kid. Can this video be of any learning benefit to an 12 year old.
I am a statistics student, and I learned a lot of info thinks ❤❤
Glad it was helpful!
you are one of the best teacher on internet
This is the best statistics class I have ever sat in. There is something about the crisp graphics and your reassuring voice that helps learn stats in bite-sized sessions. Thank you.
Outstanding work! Absolutely to-the-point and simple to understand. Grateful!
Glad it was helpful!
Cảm ơn bạn!
THANKS A MILLION🌟🌟 ...sending love and appreciation from a second year psychology student❤❤
Not gonna lie, just trying to refresh some stuff and ive been on ur channels all afternoon! take my upvote
Many thanks!!! Regards Hannah
Thanks!
I need to say thanks you!!!! Regards Hannah
A comprehensive and clear concepts illustrated teaching video of statistics. Thank you so much for producing it.
Glad you enjoyed it and thanks for your nice feedback!!! Regards Hannah
A heart felt thank you from Ethiopia!
You just saved my master thesis, this channel is amazing
If you master thesis was saved by this video then you probably shouldn’t be given a masters in anything…
@@jeffclark5268 Gee Jeff, not having a very good day now have you ?
I think you have saved my project. I cannot thank you enough! Keep going with the video!
I needed this for my PhD thesis. Thank you. I need to abdorb incrementally 😊
It helps a lot! Thanks!! we may come from different countries, speak different languages, not knowing each others, but what you have been doing means that humanity is still exist. Love from Indonesia!! You make another friend from Indonesia🤝
Main reason I love the internet is cuz I can study a whole topic in several hours and have a fairly good understanding to converse and ask more in depth about the field at hand.
At last, a clear and simple tutorial. Thank you very much
Glad you liked it!
Your book is very good and complete!!! Congrats! Prof. Luis Vidal, epidemiology dept, school of medicine, ufrj, rio de janeiro, brazil.
Hi Prof
why is this the best channel on the entire UA-cam? Definitely buying your book.
Absolutely foundational and wicked awesome! Awesome Tutorial.
I watched the lecture in one sitting...very informative for statistics students 🎉
I like the way you explaining. you are far more better than my National Institute of Technology, Trichy professors. thanks you for this video.👍
I have to admit that i am addicted to your videos 😇 that i had the brave to watch this comprehensive course
Thank you 😊 💓 for the most comprehensive course 😢🙏
the six key Components of Inferential statistics
1. Hypothesis
2. Population and Sample
3. Hypothesis testing
4. P- Value
5. Significance
6. Errors
13:44
This is simply one of the BEST video about statistic. So easy to understand
You literally saved my life! Thank you so much.
You have a very easy going and calm approach towards teaching.
it is so easy to understand the complex terms and equations...great help..thankuuu
Thank you for the wonderful tutorial video summarising the entire statistics.
I always find this page very useful and I like the Lecturer as well, She speaks very clearly and gets everything right inside my ears. I will love to meet Her one day personally and one on one. I will be very glad.
An excellent presentation of the required population's education about analytical models, logic, mathematics and data science. Especially the lecturer, who reaches a level of elite professionalism, I would easily certificate being able to handle and manage our societies future development, while being able to go to bed happily ever after, without worrying about the future of our children too much.
Thank you very much for this material. Greetings from the Panama Canal!!!
So simple way of explaining. Amazing. Thanks for all your efforts
Glad you liked it!
Hello, Dear, I joined your channel recently and your videos are helpful for statistics. I love your brief description with great examples and clear explanations.
But now I want to ask one question and I hope, you will clarify it. The question is "What is the difference between multivariable and multivariate analysis".
i have no enough words to express how much i'm thankful to you sir ^^
Wow, you are simply superb. You made even the complex statements so easy to understand and remember.
You are the best teacher I have ever seen.
Using this comment section as notes kindly don't mind
----> Important time lap for me
13:37 inferential statistics basic
34:57 T test
----> what to do after competing this video
1) explore Descriptive
2) explore p value
3) test for normal distribution
4) T value
I love your accent!!!!! So engaging, pls do not change it
Thank You! This is a great help for board exam preparation for psychometrician!, so, helpful❤
Glad it was helpful! : ) Regerds Hannah
Great Statistical Explanation. Thank you ❤❤❤
This is one of the amazing videos that I have ever watched. Well explained with both graphical and analytical examples. Great Job indeed💪💪💪💪💥
Glad you liked it! Many thanks! Regards Hannah
Excellent lecture. As good as is humanly possible.
This video is a great and excellent public service
7:49 we use Greek letter mu, μ , to denote population mean, so correct formula for sigma
I love your simple presentations!
Very smooth explanation.. simply superb. Loved it. Statistics is no more boring and scary!
Great start , after a few minutes I feel the information is well delivered, formulated and spot on topic !! I will keep watching
2nd nite and now 45 minutes into this video plus a glass of wine. T Tests may need a second replay of the video to understand them.
The lecture was certainly very valuable and excellent, but the presentation was amazing. Can you tell me about the program used in this presentation work?
Thank you from the bottom of my heart!
Thanks for your nice feedback! Regards Hannah!
Thanks for the enlightenment, one of the best video on statistics so far
U are awesome in teaching and in ur attitude 😊😊
So nice of you! Thanks for your feedback! Regards Hannah
Hello from Brisbane. I will definitely be telling all my colleagues about you. Hoping to see lots of scientific papers with your name in the citation for years to come.
Thank you for taking the 4 hrs long trouble for us, it was needed badly. ❤
Summary notes:
- [What are the key differences between descriptive and inferential statistics?](#related)
- [How do you perform a hypothesis test?](#related)
- [What is the significance of correlation analysis in statistics?](#related)
Highlights:
@00:01 Statistics provides essential tools for collecting, analyzing, and presenting data. This tutorial covers foundational concepts and statistical tests to help understand data analysis effectively.
-Descriptive statistics summarize data sets, providing insights into sample characteristics without inferring broader population conclusions. This approach is fundamental in understanding collected data effectively.
-Measures of central tendency and dispersion help describe data sets meaningfully. Understanding these concepts is vital for interpreting data distributions and variability effectively.
-Inferential statistics enable conclusions about a population based on sample data, involving hypothesis testing and estimations. This is crucial for making predictions and decisions based on limited information.
@15:13 Hypothesis testing is a method used to evaluate claims about population parameters based on sample data. It involves determining the likelihood of observed results under the assumption that a null hypothesis is true.
-The null hypothesis posits that there is no effect or difference in the population. This hypothesis is tested against an alternative hypothesis to find evidence for change.
-The P-value indicates the probability of observing a sample that contradicts the null hypothesis. A low P-value suggests that the null hypothesis may be rejected in favor of the alternative hypothesis.
-Type I and Type II errors represent the risks in hypothesis testing. A Type I error occurs when a true null hypothesis is incorrectly rejected, while a Type II error happens when a false null hypothesis is not rejected.
@30:10 Understanding the difference between ratio and interval measurement levels is essential for accurate statistical analysis. Ratio scales have a true zero point, allowing meaningful comparisons, while interval scales do not.
-Interval scales, unlike ratio scales, do not have a true zero point. This limits their ability to express relative comparisons like one value being three times another.
-A ratio scale measures quantities with a true zero, allowing for meaningful multiplication and division. This makes it possible to express one value as a multiple of another.
-Examples of measurement types include nominal, ordinal, interval, and ratio. Understanding these levels helps in selecting the appropriate statistical tests for data analysis.
45:13 The significance level, usually set at 5%, helps determine whether to reject the null hypothesis based on the P value and T value calculations. If the P value is less than 0.05, we have enough evidence to reject the null hypothesis.
-Understanding the difference between directed and undirected hypotheses is important in statistical testing. Directed hypotheses specify the expected direction of the difference.
-The T Test is used to compare the means of two groups and determine if there is a significant difference between them. This is crucial in hypothesis testing.
-ANOVA is an extension of the T Test that allows for comparison across more than two groups. It assesses whether there are statistically significant differences among group means.
1:00:29 Two-way ANOVA is a statistical method that examines the impact of two categorical variables on a dependent continuous variable. It allows for a deeper understanding of how these variables interact with each other.
-The two-way ANOVA extends the one-way ANOVA by including two independent variables, allowing for more complex interaction analysis. This method can identify how multiple factors influence outcomes.
-In two-way ANOVA, factors can include categorical variables such as gender or treatment type, each with different levels. Understanding these levels is crucial for accurately interpreting results.
-Key assumptions for conducting a two-way ANOVA include normality of data, homogeneity of variance, and independence of observations. Meeting these assumptions is vital for valid results.
1:17:13 Repeated measures ANOVA is used to determine if there are statistically significant differences between three or more dependent samples. It extends paired samples T-Test, allowing analysis across multiple conditions or time points.
-The null hypothesis in repeated measures ANOVA states there are no differences in means across different time points or conditions. The alternative hypothesis suggests there is a significant change.
-Assumptions for repeated measures ANOVA include normality and sphericity of the data. These can be tested using QQ plots and Mauchly's test, respectively.
-Calculating repeated measures ANOVA involves estimating sums of squares and mean squares for treatment and residuals. The F value is derived from these calculations to assess significance.
1:31:29 Mixed model ANOVA is a statistical method that analyzes data with both between-subject and within-subject factors. It helps determine how different factors affect dependent variables over time.
-Understanding between-subject and within-subject factors is crucial for mixed model ANOVA. Between-subject factors involve different groups, while within-subject factors involve repeated measures on the same subjects.
-Mixed model ANOVA can identify interaction effects between factors. This means it can determine whether the impact of one factor varies depending on the level of another factor.
-The assumptions of mixed model ANOVA include normality, homogeneity of variances, and independence of observations. Each assumption ensures the validity of the statistical results obtained.
1:45:33 Understanding the differences between Pearson and Spearman correlations is crucial for effective data analysis. Pearson uses raw data, while Spearman relies on ranked data, impacting their applications.
-Pearson correlation is appropriate for linear relationships and normally distributed data. It calculates the linear relationship between two continuous variables using their raw scores.
-Spearman's rank correlation is nonparametric, making it useful for ordinal data or non-normal distributions. It assesses the strength and direction of the relationship between two ranked variables.
-Hypothesis testing often requires checking assumptions like normality and equal variances. Using tests like the T-test or Mann-Whitney U test can help determine significant differences between groups.
2:00:38 The video explains Lavine's test, which evaluates the equality of variances between groups using calculated test statistics and P-values. It also discusses implications for hypothesis testing based on P-values.
-A smaller P-value indicates that the null hypothesis of equal variance can be rejected. If the P-value is greater than 0.05, the null hypothesis is not rejected.
-When data does not meet normal distribution assumptions, nonparametric methods like the Mann-Whitney U test can be employed. This test evaluates rank sums rather than mean differences.
-The video demonstrates how to perform the Mann-Whitney U test with practical examples. It highlights differences in methodology compared to traditional T-tests for independent samples.
2:15:43 The Wilcoxon test is utilized to compare the central tendencies of two dependent samples when normal distribution cannot be assumed. It evaluates whether there is a significant difference between paired observations in a population.
-The null hypothesis of the Wilcoxon test states that there is no difference in the central tendencies of the dependent samples. The alternative hypothesis asserts that a difference exists.
-In cases where normal distribution is not present, the Wilcoxon test ranks the differences between paired observations. This method is crucial for analyzing non-normally distributed data effectively.
-Calculating the Wilcoxon test involves determining the rank sums of positive and negative differences. The test statistic W helps to assess whether these sums are approximately equal, which is essential for hypothesis testing.
2:32:17 The Friedman's test is a nonparametric statistical method used to determine if there are significant differences between three or more related groups. It analyzes ranked data rather than raw values, making it suitable for non-normally distributed datasets.
-The Friedman's test is often used in situations involving repeated measures, such as assessing the same subjects over different time points. This highlights its relevance in analyzing dependent samples.
-Understanding the null hypothesis in the Friedman's test is crucial; it posits that there are no significant differences among the dependent groups being analyzed. This hypothesis guides the interpretation of results.
-The test results include a Chi-square value and a P-value, which help determine whether the null hypothesis can be rejected based on the significance level. A greater understanding of these values is essential for correct interpretation.
2:45:59 The video explains how to analyze the relationship between gender and newspaper preference using the Chi-Square test. It demonstrates how to interpret and calculate the test results effectively.
-The Chi-Square test helps determine if there's a significant relationship between categorical variables. It compares observed frequencies in a contingency table to expected frequencies.
-Using statistical software like DataTab simplifies the Chi-Square test process. The software automatically calculates results, making it easier for users to interpret their data.
-The assumptions for the Chi-Square test include having expected frequencies greater than five. If these assumptions are met, the results can be considered valid.
3:01:04 Understanding the difference between Pearson and Spearman correlation coefficients is crucial in statistical analysis. While Pearson measures linear relationships, Spearman evaluates monotonic relationships using ranks instead of raw data.
-Pearson correlation requires both variables to be normally distributed to interpret the significance of its coefficient correctly. If normality is violated, results may not be reliable.
-Spearman correlation is beneficial when data does not meet the assumptions of normality. It assesses relationships based on ranks, making it more robust for non-parametric data.
-Kendall's tau is another nonparametric alternative that can be preferred over Spearman when dealing with tied ranks. It assesses the ordinal relationship between two variables effectively.
3:16:22 Understanding the distinction between causality and correlation is crucial in statistics. Causality implies a direct cause-and-effect relationship, while correlation merely indicates a relationship between two variables.
-Correlation does not imply causation; it can often stem from common causes affecting both variables. An example is the correlation between ice cream sales and sunburn incidents.
-Causality requires specific conditions to be established, including a significant correlation and a chronological sequence of events. These conditions help in determining true causal relationships.
-Regression analysis is a powerful tool in statistics that allows for understanding relationships between variables. It can help predict outcomes based on independent variables.
3:31:13 Linear regression is a statistical method used to predict the value of a dependent variable based on the value of one or more independent variables. It utilizes the least squares method to find the best-fitting line through the data points.
-The dependent variable in this context is the length of hospital stay after surgery, while the independent variable is the age of the patient. This relationship helps in optimizing hospital resources.
-Calculating the coefficients of the regression model involves statistical programs, but it can also be done manually through correlation and standard deviation calculations. This method aids in understanding the relationship between variables.
-Multiple linear regression expands on simple linear regression by allowing the consideration of multiple independent variables to predict a dependent variable. This is particularly useful in fields like social research and market analysis.
3:46:17 It's essential to check for linear relationships and normality in regression analysis to ensure meaningful interpretation of coefficients and predictions. This helps avoid larger-than-expected prediction errors.
-Graphical methods like histograms and QQ plots are useful for checking normality of data distributions, ensuring that assumptions for regression analysis are met. These techniques provide visual insights into data behavior.
-Homoscedasticity is crucial in regression, indicating constant variance of residuals across values, which ensures reliable error predictions. A lack of this condition can lead to inaccurate model interpretations.
-Multicollinearity can distort regression results by making the effects of independent variables hard to distinguish. Diagnosing it through tolerance or VIF values helps maintain model stability and interpretability.
4:01:21 Logistic regression is a statistical method used for predicting the probability of a categorical dependent variable based on one or more independent variables. It is particularly useful in scenarios where the outcome is binary, such as disease susceptibility or voting behavior.
-In medical research, logistic regression helps identify which factors, such as age, gender, and smoking status, influence disease occurrence. It enables researchers to understand the probability of a patient developing a specific illness.
-The logistic regression function limits predicted values to a range between zero and one, making it suitable for binary outcomes. This is achieved through the logistic function, which transforms linear combinations of predictors.
-The K-means clustering technique is introduced as a method for discovering hidden patterns in data. It groups data points into clusters based on their characteristics, enhancing data analysis and interpretation.
I just finished the lecture. I found it very helpful. Thanks once again
Thank you so much for making it so simple and digestible! Really liked it!
Glad you liked it!
Wow....4 hours video and for the first time the German accent doesn't scare me
: ) Thanks
@@attribute-4677 Thanks : )
Yooooooo 😭
😂😂woe yeah that was great one
Fun fact : English is from Germanic language family
thank you tonsssssssssssssssssss. God bless You, for explaining so simply - with animations.
Love the way you teach simple and crisp
You hold the world on your back like Atlas, thank you! Great video 🥳
Really Don’t know How to Thank You❤❤.But You have Opened my eyes in a very meaningful way.Never the statistics was so much fun for me.I was always struggling in Data analysis.
This is really a good tutorial into the subject
You have produced something truly unique in order to teach us. Absolutely Great Efforts. Many thanks for it.
This lecture clearly is for non mathematicians. In the last century I learned all this in school, but even with mathematical proofs which were all left out here.
This was soo helpful. Thank you. 😊
Glad it was helpful! Regards Hannah
Girl, you’re awesome. Thanks for the great content!
I love this video which help me sort up those definition ,thanks so much!!!!
Pretty useful for my studying. Thanks a lot❤
Glad to hear that! Thanks for your feedback! Regards Hannah
The lecture is very helpful in all aspects. Thank you.
Many thanks!!!
Honestly this is one of the best videos i find in youtube on this subject.Thank you so much.
Wow. I really appreciate this. I have learned a lot
I've been following your video posts. You made me confident before my students. A simple way to present technical jargons!!! I haven't bought the book going they the free sample one can tell it's worth a penny!!!
Excellent video. Very clear and exceptional illustrations. The result of a lot of work without a doubt.
I am greatful to this good and elaborate explanation of statistics. This is Gem in my oncoming research work analysis for my MSc. Immunology.
Thank you mum.
Can you please explain briefly on your research work and how have you planned to use statistics in this? I am curious on immunology
wow fantastic and fabulous lectures. great job with mastering the subject.
This is better than my college year. 😅 Weew! Thank you so much.
Thank you very much for such a great tutorial. Complex topics very easily explained❤❤
Glad it was helpful! : ) Regards Hannah
you are an angel with a german accent ❣❣❣ amazing !!
fantastic fantastic fantastic video!!! 😍👌🏻 🏆
You teach better than my professors at my university
Well explained the essentials of the concepts and principles of statistics and related subjects. Thanks for posting this important and informative lesson!
Thank you so much for this!! Super helpful. Love from India❤
Many thanks for your nice feedback!!!!
Great tutorial! Very well explianed!
Glad it was helpful! Thanks and Regards, Hannah
Absolutely Great Efforts, thank you
Very simple and excited video. Thanks alot 😊😊
Very clear - thank you.