This video was very interesting. When I first looked over the article on the screen at the beginning of the video, I just accepted the statements presented without thinking about them. The ideas regarding causation he presented changed the way I interpreted the article. For example, the most powerful idea he presented for me related to the title: breakfast skipping causes obesity. All of the alternate options he presented (i.e. obesity causes breakfast skipping, other variables influencing data) caused me to rethink the original statement presented. This video will motivate me to rethink blanket statements, such as the one presented in the WebMD article, especially related to what variable actually caused what effect.
I found that the video on causation was similar to How To Lie with Statistics. It took a statement made by webmd and although they decided the sample population and variables were legitimate, they proved how there may not be any correlation between breakfast and obesity. I think that it was really interesting to see the different ways you could link obesity and other problems and that we shouldn't take everything at face value.
I thought this video was very helpful in separating the meanings of causality and correlation. It helps to point out that there are too many other factors in the experiment, from the article, to be sure that skipping breakfast can cause obesity. But that the two factors can be related by something else. I also agree with Jonny in that the video reminds me of How To Lie With Statistics. Both point out where misinterpretations of data can be and how to avoid them.
I thought this video was very interesting and I also thought of How to Lie With Statistics. Immediately after I saw the statement about not eating breakfast causing obesity I didn't even question it. I also have never considered the difference between causality and correlation. As the video explained, causality states a cause and effect while correlation shows a relationship between two things. After listening to the video, I became more aware of how the two factors of obesity and breakfast eating are not necessarily caused by each other but simply correlated. After watching the video, I think I will look at statistics and conclusions found by studies and not necessarily believe them until I look further into the overall study.
This video reminded me of our summer reading assignment with How to Lie With Statistics. I like that this video makes the viewer/listener actually think about what they read when it comes to studies, instead of blindly accepting everything in print. I also found that this particular video or lesson was very helpful in differentiating between causation and correlation, and why their differences are so important in statistics.
I enjoyed this video because I have personally always believed that everyone should eat breakfast to speed up their metabolism, so I got other ideas about that topic. It was interesting the way the described correlation, which made it easier to understand. I liked how they linked other possibilities to obesity to see the relations. Like everyone else, this video reminded me of How To Lie With Statistics.
I think this video was very good at distinguishing the difference between causality and correlation. The fact is that studies must not only claim causality, but more importantly prove causality. Without a relationship proven between two variables, there could likely be a correlation between the two variables or a lurking variable that affects the two other variables. Correlation means that there is no known cause and effect relationship, but rather that one variable increases while the other variable increases. If you are given a correlation, you can't assume the relationship of the variables without more knowledge. Similarly, there may be another variable that connects to the two variables, causing the two other variables to not have any sort of relationship. These topics were also brought up in "How to Lie With Statistics", and are an important concept to understand when looking a two variable data.
I thought that this video was interesting. It makes us think that there might be another reason behind what we are reading than what there appears to be. When i first saw the study I believed that not eating breakfast caused obesity until he showed that it was a correlation between them not causality.
Mr. Khan has a educated, but common sense way of thinking about the world. Most people, including myself, would not question a study seen on webmd, a reliable source. Khan helped me see that for two variable stats, there are also other lurking variables. He cleared up the differences between correlation and causality. Now I am able to recognize this important difference.
Mr.Khan helped me understand lurking variables in an easier way. He also showed me how if you have a source and it says something that you can put it into a different perspective and get a different result. Overall Khans video was very helpful in showing two variable statistics in a different way.
The video demonstrated a very important point that I, as well as many people, often overlook. It was helpful to remind myself that there may be hidden variables in any type of study, and conclusions drawn from seemingly obvious results may not be telling a true story. Although the video did a great job of teaching the difference between correlation and causality, I agree with one of the comments that said it did not take a 10-minute long video to demonstrate the point. Overall, however, it was a very comprehensive lesson that was a good reminder for me.
This video was great for clarifying and distinguishing the differences between causality and correlation. At a first glance in regards to two variable statistics or any other multiple variable scenario, it may appear that the variables have a cause and effect relationship, but in reality they are just related to each other by an underlying variable that isn't shown or expressed in the data. In all honesty i would probably have fell for this manipulation of data, like the examples and samples in the summer assignment, and from this video i have learned to try and overlook the facts or what the data shows and to try and see if there is another variable that comes into play before assuming one causes the other.
This video is a great help in understanding the difference between causality and correlation. It shows that causality can be difficult to prove. There can often be lurking variables when collecting two variable data. Most of the time these two variables will show a correlation that is not difficult to see. This however does not imply that there is causality. I found this video to be very interesting and informative.
I found this video quite interesting. It helped clarify the differences between correlation and causality for me and I now understand them. I also learned that in any study there may be a plethora of hidden or lurking variables that might sway a survey or study one way or the other. This video really helped me understand these two concepts and I find the Khan videos really helpful.
After watching this video i thought about how many factors play into a certain situation or statistic. Its not just the two variables that are given that have an effect on the statistic, there are hidden variables as well as obvious ones. This video clearly defined correlation and casuality, showing how casuality can be hard to define/prove. Correlation shows how there are lurking variables and a relation two things may have could be corrupted by hidden variables. Also Khan helped me too look more into things, instead of just accepting what they say. Many people just read a statement and dont think twice about it, Khan shows how there is no than meets the eye in most situations.
This video was very helpful to me in understanding the difference between causation and correlation. As other students probably did, at the beginning of the video i believed that the statement WebMd made must be true by the facts they provided. It was interesting to see the other factors or hidden variables that could have been involved. Saying something causes something else to happen has to be a very definitive statement and this video will help me question possible hidden variables.
I thought the video was very interesting and at the same time very helpful. I didn't know the difference between causation and correlation, I thought it was all the same. It was interesting to see how many factors could play the role that webMD said was the reason for obesity. I learned that just because two things seem to be related n show a cause and effect does not mean that is true. The example in the video proves that and does a great job in explaining why, and what the difference it.
I thought it was a pretty cool video. I'm someone who would probably take whatever the article on web md said and just accepted it. I think it is resourceful of him to put a lot of thought into what the study is actually saying. I agree that it reminds me of How to Lie With Statistics. Although im sure the website is not trying to deceive people, I found many similarities to how using general terms can give false impressions. Over all I thought it was a good resource in our learning of statistics!
The video is helpful because it clearly explained the difference between correlation and causality . It really showed the difference when it used the webmd stat about obesity and how many different factors were can change any stat no matter how big or small. The videos are helpful in explaining things and then showing how it's used.
This video really helped me to better understand the difference between causality and correlation. Although I understood them before, I can now recognize and separate better. It also made me think more about underlying causes and reading into the data and information given more, rather than just immediately accepting it for what it is. It really makes you think about whats behind the data rather than just seeing it as numbers to graph and analyze.
I thought that this video was also very helpful. when i first read the article, i didnt think about any other variables that could cause these results. It helped me to understand that you always need to remember that there are hidden or lurking variables. i fully understand what a lurking variable is now because of the examples he presented that were all related to breakfast skipping causing obesity. this video clearly defined the difference between causality and correlation by stating that causality is hard to prove.
This video was extremely interesting and somewhat mind blowing. Usually I would think about scientific research as valid confirmation about theories, but after this article, I will now look at health facts much differently. Also, this video helped me understand how if there is a variable that could cause for 2 variables to occur, then the 2 variables could not be a cause and effect, but more just related. Not only does this video teach about causality and correlation, it also teaches us to over analyze statistical presentations in order to verify the underlying statements.
Like some other students have said, this video reminded me of "How To Lie With Statistics". When he first introduced the study I wasn't quite sure where the video was headed, and I was shocked at what he showed. I also didn't know the difference between causation and correlation. When I first read the WebMD statement I accepted it without hesitation, but now I will be more careful to consider what other factors could be involved.
I liked this video because it helped me better understand the difference between causation and correlation. I would never have thought of all the underlying factors that could make the blanket statement: "skipping breakfast causes obesity" not true. It also reminded me of How To Lie With Statistics because just like the book it exposed possible underlying factors.
This video I found to be very interesting and very helpful in understanding the difference between causation and correlation. Often people and studies can mislead you by making you believe there is causation taking place, but in reality there is no causation and only correlation. After watching this video I believe I am more awake to the misconceptions that are being fed to me on a daily basis. I now know that just because to variables are shown they don't necessarily have to be caused by one another, and it can only be by chance that they both appear. I believe many people can use this relationship to trick others or mislead them into believing a relationship when there is none, and this Khan Academy video helped display how this can happen.
Along with many of my classmates, I found this video very helpful and it definitely reminded me of "How to Lie With Statistics." The lurking variable is another reason that we cannot take all statistics at face value, and we should think about what unseen factors may be affecting data before drawing conclusions. Also, this helped me differentiate between causation and correlation especially since I hadn't thought about the differences before.
I found this video to be interesting and helpful. It helped me understand the difference between correlation and causality. Although two variables have a correlation, this does not mean that they have causality. As a result of this, an experiment that can not prove causality can not be interpreted in the same way as one that does in fact prove causality between two variables.
I found this video very helpful and I think that Mr. Khan is excellent at explaining complicated ideas in a simple manner. This helped me to gain a better grasp on causation and correlation and how they are quite different. I had always assumed that major sites like WebMD could be trust wholeheartedly, but Khan revealed that lurking variables are found in many places.
Mr. Khan's videos are always very helpful and informative and this video on casualty and correlation was no exception. I appreciated the way he took the time to explain the difference between the two, and how they are not always related like we sometimes tend to think they are. Khan pointed out, as in his WebMD example, that not every sample of data is completely accurate. The other variables and factors that lie behind the data point on the scatter plot should always be considered when looking at a study such as this.
I thought that this video was very informative. I really liked how he went into detail when explaining the difference between the two and how they are not always related. the video helped me understand and get a better grasp on what exactly causation and correlation are and how they differ. we should think about what unseen factors may be affecting data before drawing any kind of conclusion
This video was very interesting. When I first looked over the article on the screen at the beginning of the video, I just accepted the statements presented without thinking about them. The ideas regarding causation he presented changed the way I interpreted the article. For example, the most powerful idea he presented for me related to the title: breakfast skipping causes obesity. All of the alternate options he presented (i.e. obesity causes breakfast skipping, other variables influencing data) caused me to rethink the original statement presented. This video will motivate me to rethink blanket statements, such as the one presented in the WebMD article, especially related to what variable actually caused what effect.
ReplyDeleteI found that the video on causation was similar to How To Lie with Statistics. It took a statement made by webmd and although they decided the sample population and variables were legitimate, they proved how there may not be any correlation between breakfast and obesity. I think that it was really interesting to see the different ways you could link obesity and other problems and that we shouldn't take everything at face value.
ReplyDeleteI thought this video was very helpful in separating the meanings of causality and correlation. It helps to point out that there are too many other factors in the experiment, from the article, to be sure that skipping breakfast can cause obesity. But that the two factors can be related by something else. I also agree with Jonny in that the video reminds me of How To Lie With Statistics. Both point out where misinterpretations of data can be and how to avoid them.
ReplyDeleteI thought this video was very interesting and I also thought of How to Lie With Statistics. Immediately after I saw the statement about not eating breakfast causing obesity I didn't even question it. I also have never considered the difference between causality and correlation. As the video explained, causality states a cause and effect while correlation shows a relationship between two things. After listening to the video, I became more aware of how the two factors of obesity and breakfast eating are not necessarily caused by each other but simply correlated. After watching the video, I think I will look at statistics and conclusions found by studies and not necessarily believe them until I look further into the overall study.
ReplyDeleteThis video reminded me of our summer reading assignment with How to Lie With Statistics. I like that this video makes the viewer/listener actually think about what they read when it comes to studies, instead of blindly accepting everything in print. I also found that this particular video or lesson was very helpful in differentiating between causation and correlation, and why their differences are so important in statistics.
ReplyDeleteI enjoyed this video because I have personally always believed that everyone should eat breakfast to speed up their metabolism, so I got other ideas about that topic. It was interesting the way the described correlation, which made it easier to understand. I liked how they linked other possibilities to obesity to see the relations. Like everyone else, this video reminded me of How To Lie With Statistics.
ReplyDeleteI think this video was very good at distinguishing the difference between causality and correlation. The fact is that studies must not only claim causality, but more importantly prove causality. Without a relationship proven between two variables, there could likely be a correlation between the two variables or a lurking variable that affects the two other variables. Correlation means that there is no known cause and effect relationship, but rather that one variable increases while the other variable increases. If you are given a correlation, you can't assume the relationship of the variables without more knowledge. Similarly, there may be another variable that connects to the two variables, causing the two other variables to not have any sort of relationship. These topics were also brought up in "How to Lie With Statistics", and are an important concept to understand when looking a two variable data.
ReplyDeleteI thought that this video was interesting. It makes us think that there might be another reason behind what we are reading than what there appears to be. When i first saw the study I believed that not eating breakfast caused obesity until he showed that it was a correlation between them not causality.
ReplyDeleteMr. Khan has a educated, but common sense way of thinking about the world. Most people, including myself, would not question a study seen on webmd, a reliable source. Khan helped me see that for two variable stats, there are also other lurking variables. He cleared up the differences between correlation and causality. Now I am able to recognize this important difference.
ReplyDeleteMr.Khan helped me understand lurking variables in an easier way. He also showed me how if you have a source and it says something that you can put it into a different perspective and get a different result. Overall Khans video was very helpful in showing two variable statistics in a different way.
ReplyDeleteThe video demonstrated a very important point that I, as well as many people, often overlook. It was helpful to remind myself that there may be hidden variables in any type of study, and conclusions drawn from seemingly obvious results may not be telling a true story. Although the video did a great job of teaching the difference between correlation and causality, I agree with one of the comments that said it did not take a 10-minute long video to demonstrate the point. Overall, however, it was a very comprehensive lesson that was a good reminder for me.
ReplyDeleteThis video was great for clarifying and distinguishing the differences between causality and correlation. At a first glance in regards to two variable statistics or any other multiple variable scenario, it may appear that the variables have a cause and effect relationship, but in reality they are just related to each other by an underlying variable that isn't shown or expressed in the data. In all honesty i would probably have fell for this manipulation of data, like the examples and samples in the summer assignment, and from this video i have learned to try and overlook the facts or what the data shows and to try and see if there is another variable that comes into play before assuming one causes the other.
ReplyDeleteThis video is a great help in understanding the difference between causality and correlation. It shows that causality can be difficult to prove. There can often be lurking variables when collecting two variable data. Most of the time these two variables will show a correlation that is not difficult to see. This however does not imply that there is causality. I found this video to be very interesting and informative.
ReplyDeleteI found this video quite interesting. It helped clarify the differences between correlation and causality for me and I now understand them. I also learned that in any study there may be a plethora of hidden or lurking variables that might sway a survey or study one way or the other. This video really helped me understand these two concepts and I find the Khan videos really helpful.
ReplyDeleteAfter watching this video i thought about how many factors play into a certain situation or statistic. Its not just the two variables that are given that have an effect on the statistic, there are hidden variables as well as obvious ones. This video clearly defined correlation and casuality, showing how casuality can be hard to define/prove. Correlation shows how there are lurking variables and a relation two things may have could be corrupted by hidden variables. Also Khan helped me too look more into things, instead of just accepting what they say. Many people just read a statement and dont think twice about it, Khan shows how there is no than meets the eye in most situations.
ReplyDeleteThis video was very helpful to me in understanding the difference between causation and correlation. As other students probably did, at the beginning of the video i believed that the statement WebMd made must be true by the facts they provided. It was interesting to see the other factors or hidden variables that could have been involved. Saying something causes something else to happen has to be a very definitive statement and this video will help me question possible hidden variables.
ReplyDeleteI thought the video was very interesting and at the same time very helpful. I didn't know the difference between causation and correlation, I thought it was all the same. It was interesting to see how many factors could play the role that webMD said was the reason for obesity. I learned that just because two things seem to be related n show a cause and effect does not mean that is true. The example in the video proves that and does a great job in explaining why, and what the difference it.
ReplyDeleteI thought it was a pretty cool video. I'm someone who would probably take whatever the article on web md said and just accepted it. I think it is resourceful of him to put a lot of thought into what the study is actually saying. I agree that it reminds me of How to Lie With Statistics. Although im sure the website is not trying to deceive people, I found many similarities to how using general terms can give false impressions. Over all I thought it was a good resource in our learning of statistics!
ReplyDeleteThe video is helpful because it clearly explained the difference between correlation and causality . It really showed the difference when it used the webmd stat about obesity and how many different factors were can change any stat no matter how big or small. The videos are helpful in explaining things and then showing how it's used.
ReplyDeleteThis video really helped me to better understand the difference between causality and correlation. Although I understood them before, I can now recognize and separate better. It also made me think more about underlying causes and reading into the data and information given more, rather than just immediately accepting it for what it is. It really makes you think about whats behind the data rather than just seeing it as numbers to graph and analyze.
ReplyDeleteI thought that this video was also very helpful. when i first read the article, i didnt think about any other variables that could cause these results. It helped me to understand that you always need to remember that there are hidden or lurking variables. i fully understand what a lurking variable is now because of the examples he presented that were all related to breakfast skipping causing obesity. this video clearly defined the difference between causality and correlation by stating that causality is hard to prove.
ReplyDeleteThis video was extremely interesting and somewhat mind blowing. Usually I would think about scientific research as valid confirmation about theories, but after this article, I will now look at health facts much differently. Also, this video helped me understand how if there is a variable that could cause for 2 variables to occur, then the 2 variables could not be a cause and effect, but more just related. Not only does this video teach about causality and correlation, it also teaches us to over analyze statistical presentations in order to verify the underlying statements.
ReplyDeleteLike some other students have said, this video reminded me of "How To Lie With Statistics". When he first introduced the study I wasn't quite sure where the video was headed, and I was shocked at what he showed. I also didn't know the difference between causation and correlation. When I first read the WebMD statement I accepted it without hesitation, but now I will be more careful to consider what other factors could be involved.
ReplyDeleteI liked this video because it helped me better understand the difference between causation and correlation. I would never have thought of all the underlying factors that could make the blanket statement: "skipping breakfast causes obesity" not true. It also reminded me of How To Lie With Statistics because just like the book it exposed possible underlying factors.
ReplyDeleteThis video I found to be very interesting and very helpful in understanding the difference between causation and correlation. Often people and studies can mislead you by making you believe there is causation taking place, but in reality there is no causation and only correlation. After watching this video I believe I am more awake to the misconceptions that are being fed to me on a daily basis. I now know that just because to variables are shown they don't necessarily have to be caused by one another, and it can only be by chance that they both appear. I believe many people can use this relationship to trick others or mislead them into believing a relationship when there is none, and this Khan Academy video helped display how this can happen.
ReplyDeleteAlong with many of my classmates, I found this video very helpful and it definitely reminded me of "How to Lie With Statistics." The lurking variable is another reason that we cannot take all statistics at face value, and we should think about what unseen factors may be affecting data before drawing conclusions. Also, this helped me differentiate between causation and correlation especially since I hadn't thought about the differences before.
ReplyDeleteI found this video to be interesting and helpful. It helped me understand the difference between correlation and causality. Although two variables have a correlation, this does not mean that they have causality. As a result of this, an experiment that can not prove causality can not be interpreted in the same way as one that does in fact prove causality between two variables.
ReplyDeleteI found this video very helpful and I think that Mr. Khan is excellent at explaining complicated ideas in a simple manner. This helped me to gain a better grasp on causation and correlation and how they are quite different. I had always assumed that major sites like WebMD could be trust wholeheartedly, but Khan revealed that lurking variables are found in many places.
ReplyDeleteMr. Khan's videos are always very helpful and informative and this video on casualty and correlation was no exception. I appreciated the way he took the time to explain the difference between the two, and how they are not always related like we sometimes tend to think they are. Khan pointed out, as in his WebMD example, that not every sample of data is completely accurate. The other variables and factors that lie behind the data point on the scatter plot should always be considered when looking at a study such as this.
ReplyDeleteI thought that this video was very informative. I really liked how he went into detail when explaining the difference between the two and how they are not always related. the video helped me understand and get a better grasp on what exactly causation and correlation are and how they differ. we should think about what unseen factors may be affecting data before drawing any kind of conclusion
ReplyDelete