Skewness and Kurtosis with SPSS Tutorial (SPSS Tutorial Video #11)

In this video, I show you how to determine and interpret the SKEWNESS and KURTOSIS of a distribution. These are two useful metrics for describing the shape of a distribution. I also give you a chance to try and to it yourself.
This SPSS tutorial series is designed to teach you the basics of how to analyze and interpret the results of data using SPSS. I will cover everything from the very basics of the main windows within SPSS, to manipulating data, to running and interpreting meaningful analyses like t-tests, ANOVA, regression, and many more, and visualizing results.
The data file used in this video can be found here: drive.google.c...
Video tutorial and walkthrough of the data file used in this video: • Introduction to Data F...
SIMULATION data file used in this video can be found here: drive.google.c...
Playlist of video covering INTUITION for statistics and data science: • Data Intuition
Video mentioned showing how to create and interpret QQ-plots: • QQ Plots with SPSS Tut...
All the SPSS tutorial videos are in this playlist: • SPSS Tutorials
Learn more about who I am and why I'm doing this here: • Data Demystified - Who...
Follow me at:
LinkedIn: / jeff-galak-768a193a
Patreon: / datademystified
Website: www.jeffgalak.c...
Equipment Used for Filming:
Nikon D7100: amzn.to/320N1FZ
Softlight: amzn.to/2ZaXz3o
Yeti Microphone: amzn.to/2ZTXznB
iPad for Teleprompter: amzn.to/2ZSUkNh
Camtasia for Video Editing: amzn.to/2ZRPeAV

[@lilydarcy8394]

Thank you for the clear explanation! I completely forgot how to calculate skewness and kurtosis on SPSS. 😅

[@user-zf9lp3cb1c]

Thanks a lot. its really help me. its really really different from what general Indonesian RUclipsr I see explain

[@liekev.6133]

Great video, very clear explanation! I have 3 variables with a too high curtosis (according to literature should be between -2 en 2). How can I fix that? Have been trying to apply LogLinear Transformation, but that only seems to make things worse.. Any tips?

[@lukebreedon3028]

How do you find the skewness and kurtosis for say half of the statistics of one variable?

[@omerashahnawaz6933]

Hi
Thankyou so much for explaining everything so simply. I have a question that can skewness and kurtosis be applied on likert scale?

[@DataDemystified]

Glad you found it useful. And yes, you can!

[@omerashahnawaz6933]

Thank you so much.

[@peterwestfall6924]

Kurtosis does not measure flatness or peakedness at all. You can have infinitely peaked distributions with low kurtosis (e.g. beta(.5,1)), and you can have distributions that appear perfectly flat-topped over nearly all the data with infinite kurtosis (eg .9999U(0,1) + .0001Cauchy).
Kurtosis measures tail weight (or outlier propensity) only. The only reason that high kurtosis distributions appear "peaked" is because the outliers stretch the horizontal scale, as in your graph. In other words, kurtosis measures the outliers, not the peak.
Reference:
"Kurtosis as peakedness: 1905 - 2014. RIP", The American Statistician.

[@leonvdb8388]

The higher the skewness number the higher the bars in the graph?

[@DataDemystified]

The higher the skewness, the more of a tail the graph has.

[@leonvdb8388]

@@DataDemystified thank you!

[@petertucker5878]

Are there thresholds that we can use to say that data is normal using these? i.e. how to decide whether we can then go on and treat the data as normally distributed

[@DataDemystified]

Best bet is to use a test of normality (descriptive stats~> explore ~>plots (tests for normality)