Statistical Analysis with Excel-Chapter9
Measures of Central tendency(Mean, median, mode) is a great way of summarizing but statisticians cannot rely on them as they do not give all the information of the data.
Now comes Measures of dispersion:
Variance
STandrad deviation
Range
If I have two groups with heights of students 48,48,48,48,48 and second group with heights 50,47,52,46,45 the mean of both groups is same.
How to then tell the dismmilarity between them is to examine the deviation.
Variance: how far/close is the values from the mean.In other words Average of squared deviation of each data point from the mean.
If I do not square the deviation then the average of deviations will be zero so use squared ,trick from Algebra.
Although I am calculating the population variance ,we also have formulas for sample variance.
For Sample:
VAR.S
VARA
For population:
VAR.P
VARPA
Using the same data from Ukraine-Russia war,Russia equipment lossess.
Calculating Variance for aircraft and helicopters.
I already explained in the last chapter how we are transforming the raw data formatting the pivot table to get the fields.
VARPA
Why sample variance is important and is needed although you have formula for population variance?
As a mathematician you need to always know the reason of existence as it will help you in the application of these techniques.
Believe me when I studied statistics, I never knew the reason.
I as an Analyst have big data /population but cannot do my Analysis on it so I take sample data calculate its statistics to infer for the population based on the sample mesurements.
Standard Deviation:
We already have variance then why standard deviation We want a measurement that is more intuitive and have same unit as the original values.
STDEV.P
STDEVPA
STDEV.S
STDEVA
STDEVIF
STFEVIFS
I will just practice and use only one formula but not others listed above as we do not want you all to get bored with simple techniques.So explore them on your own.
