Check Normality of the data in Excel

[rsoumitra]

Hi Guys,

Can anyone tell me how to check normality (Whether the data is normally distributed or not) of the data in excel. I have the data (sample) in rows. So I need to add column saying whether the data in each row is normal or not.

Could anybody help me with that?

Thanks,

rsoumitra

[oldchippy]

Hi Guys,

Can anyone tell me how to check normality (Whether the data is normally distributed or not) of the data in excel. I have the data (sample) in rows. So I need to add column saying whether the data in each row is normal or not.

Could anybody help me with that?

Thanks,

rsoumitra

Hi rsoumitra,

Not sure what you mean here, a sample of your "normal" data would help. But if you mean is the data a number or is it text, then you could use

=ISTEXT(A1) or

=ISNUMBER(A1)

oldchippy

[Carim]

Hi,

Take a look at the various functions of normal distribution ...

NORMDIST(x,mean,standard_dev,cumulative)

X is the value for which you want the distribution.

Mean is the arithmetic mean of the distribution.

Standard_dev is the standard deviation of the distribution.

Cumulative is a logical value that determines the form of the function. If cumulative is TRUE, NORMDIST returns the cumulative distribution function; if FALSE, it returns the probability mass function.


HTH
Carim

[nsv]

A scientific method which gives a certain confidence for the sample to be distributed in a certain way is not easily made and there is no standard solution in Excel. You will have to study the different methods, Kolmogorod-Smirnof, Shapiro-Wilk, etc. in a statistical handbook, but there is another way. If you can accept your own judgement of whether a line is straight or not, then simply plot the results in a probability chart.

Go to http://peltiertech.com/Excel/Charts/DummySeries.html , and find the "Simulated Probability Chart" example. Remember to download the Rob Bovey's XY Chart Labeler add-in as described in the introduction.
I have created myself a chart like this and find it very useful. I have also added a regressionline and if you calculate the correlation coefficient you have a kind of result of the test.