Chi Square Test of Independence | Statistics Tutorial #29| MarinStatsLectures

Chi Square Test of Independence: How to use Pearson's Chi Square Test of Independence to test if two categorical variables are independent or dependent?

► Pearson's Chi Square Test of Independence can be used to test if two variables are independent or dependent, and is often used with categorical data.

► The Chi-Square Test can also be used to test how well a particular distribution fits a set of observed data, and is referred to as Pearson's Goodness of Fit Test.

► The Pearson's Chi Squared test works by comparing the observed contingency table, to what the table would be expected to look like, if the null hypothesis is true, and X and Y are independent.

► While Chi-Square Test technically is referred to as a Non Parametric test, the assumptions and approach to the test look more like a parametric test.

► If the null hypothesis is rejected, this test tells us nothing about the strength or direction of association between X and Y, and we must use other measures of association to try and address this.

► While we show the formula and calculations, our focus is on the concepts of Chi-Square Test, not the calculations.

► ► Watch More:

Follow MarinStatsLectures

Our Team:
Content Creator: Mike Marin (B.Sc., MSc.) Senior Instructor at UBC.
Producer and Creative Manager: Ladan Hamadani (B.Sc., BA., MPH)

These videos are created by #marinstatslectures to support some courses at The University of British Columbia (UBC) (#IntroductoryStatistics and #RVideoTutorials for Health Science Research), although we make all videos available to the everyone everywhere for free.

Thanks for watching! Have fun and remember that statistics is almost as beautiful as a unicorn!

[marcoventura]

I hope many people could have a teacher like you, not only for the perfect explanation of statistics concepts but also for the calm and argumented way of reasoning as in the case of science vs fear and speculation. Thanks Mike Marin.

[sakhawat]

The final two minutes of this lecture was highly enlightening .

[karanahlawat]

Props to you for using the platform for shedding light on the scientific stand!

[anuragmukherjee]

This is my go-to Statistics Playlist, and god knows how many people I have shared this Playlist with (who want to learn DS of course).
You did god's work with this one Sir!

[yaweli]

Define someone who knows how to teach. This Instructor. Thank you for the video.

[clarity]

Thanks a lot, I finally know where that formula of (raw X column)/N comes from. You have saved me from cramming

[pokelytics]

Great video! Thank you for your courage to call out anti-vaxxing garbage. This messaging is even more important now with Covid.

[ApoorwVikramDwivedi]

The fact that he's writing in mirror image of letters and still making sense without a single mistake!!

[pradumnaawasthi]

This is a very informative series of lectures. Thankyou so much sir.

[raitup]

Amazing video! I not only learned how to calculate the expected values. I understood where they come from and probability concepts as well. As always, what a excellent videos. No doubt the best of youtube

[stephanschaefer]

Thanks Mike. Again very good explanation, like in all other videos of yours. First time that I do understand the concepts. I am a medic in clinical research. I wish I had had such course when I was a medical school. Can only recommend your teachings to anybody in clinical research. Thank you as well for the background information on Andrew Wakefield. I did not know. Very much appreciated.

[williamparsonage]

Dear Mike, Thank you for this amazing body of work. I have some success as a clinician researcher but with a very patchy base in my knowledge and understanding of statistical methods. Probably harking back to gaps in my high school maths and then clinical medicine education. I'm lucky enough these days to have access to, and help from, much wiser people to 'do may stats' for me. But I've become increasingly aware of the need to sort this out! Going right back to basics seemed like the only way. With no time to attend a proper course your lecture series has been a god-send (on the treadmill at 5am!)

One minor point of correction on this lecture... I'm pretty sure that the Wakefield paper was published (and retracted) by The Lancet and not NEJM. The NEJM has it's own issues (!) but I suspect that this is not one they would want incorrectly attributed to them. Not The Lancet's finest hour.

Best Wishes, and keep up the good work!

[nasongg]

3:23 Do you put dependent variable first and then independent variable next?

[claramccann]

Where did you get the number 0.1209 from?

[prabpharm]

Thank you so much for sharing the knowledge. Just curious, is it OK to simply use Fischer exact test, regardless of expected cell count, and avoid the chi-square test completely? Also please talk about how chi-squared is used for estimating goodness of fit, and homogeneity. Loved the kid at the end, he is sweet :-).

[uchennanwosu]

fantastic exposition, however, I have to watch it a couple times to digest the key points.

[fraidym]

How to convert chi square score of 2.28 to p-value??

[im_karamo]

hi prof, thanks for this great job. i have a question. i have two dataset each has binary outcome i want to compare the outcome between this two datasets to see which one has poor or good outcome. 10 independent variables in dataset 1 and 5 independent variables in dataset 2. but they all have the same outcome measure which is coded as dummy variable 0 &1. how can i determine which group has better outcome? can i just use their proportions values? need explanatioin thanks