[Blindmath] statistical formulas

[Arielle Silverman]

Ryan,
Is the covariance the same thing as the cross-product? The formula you
gave looks similar to the formula I learned for computing something
called the cross-product, which goes in the numerator of the
correlation formula. The denominator is the product of the variances
or sums of squares of X and Y.
I believe there are several different ways to compute correlation
coefficients by hand. I used to know how to do it but it's been five
years since I've learned it so I don't quite remember. Also your
instructor or textbook might favor one specific formula. In general,
what I would suggest is to email your instructor for the online course
and ask them to send you the formula in words or simple math symbols
as Ryan did. I have done this a few times and will likely do it again
since I am taking structural equation modeling with a textbook in
Daisy format. Screen readers and Daisy players cannot read Greek
letters and sometimes have trouble with equations in PDF format, but
they should be able to read an equation that is written in the body of
an email message or in a Word doc.
BTW, if you are allowed to use a computer to calculate Pearson's r, it
is very easy to do in Excel.
You might also try posting your question to the new NFBNet social sciences list:
www.nfbnet.org/mailman/listinfo/social-sciences-list_nfbnet.org
Best,
Arielle

On 10/23/12, Ryan Thomas <rlt56 at nau.edu> wrote:
> Yes, it's the product of the deviation from the mean in each variable
> summed.  It looks like
>
> sum from i = 1 to n of (xi-xbar)*(yi-ybar) where xbar and ybar are the
> means.  I'm not sure what you mean by raw scores versus deviations.
> You can get around not computing the covariance by using some of the
> other identities which may avoid the deviations, but it's not very
> difficult if you use some computer application anyway.
>
> On 10/23/12, Kathy Roskos <kroskos at cox.net> wrote:
>> Thanks for the help.  I am really dense where math is concerned.  What
>> exactly do you mean by the covariance?  Do I use deviation scores and
>> figure
>>
>> the variances for both  X and Y and multiply them together?
>>
>> I have read  that you can use raw scores or deviation scores to figure
>> correlations.  Which method is easiest?
>>
>> Kathy
>> Please excuse my ignorance.  I have  ----- Original Message -----
>> From: "Ryan Thomas" <rlt56 at nau.edu>
>> To: "Blind Math list for those interested in mathematics"
>> <blindmath at nfbnet.org>
>> Sent: Tuesday, October 23, 2012 8:01 AM
>> Subject: Re: [Blindmath] statistical formulas
>>
>>
>>> For random variables X and Y, the correlation coefficient r is the
>>> covariance between x and y divided by the product of the variances of
>>> X and Y.  Depending on what statistics you're in there are other
>>> identities dealing with sum of squared regression and other terms.  I
>>> hope that's helpful though.
>>>
>>> On 10/23/12, Kathy Roskos <kroskos at cox.net> wrote:
>>>> I am new to this list.  I am taking a statistics class online and am
>>>> having
>>>> trouble getting jaws to read the formulas.  Does anyone out there know
>>>> about
>>>> calculating r values for correlational data?
>>>>
>>>> any advice would be appreciated.
>>>>
>>>> Kathy
>>>> _______________________________________________
>>>> Blindmath mailing list
>>>> Blindmath at nfbnet.org
>>>> http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
>>>> To unsubscribe, change your list options or get your account info for
>>>> Blindmath:
>>>> http://nfbnet.org/mailman/options/blindmath_nfbnet.org/rlt56%40nau.edu
>>>>
>>>
>>> _______________________________________________
>>> Blindmath mailing list
>>> Blindmath at nfbnet.org
>>> http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
>>> To unsubscribe, change your list options or get your account info for
>>> Blindmath:
>>> http://nfbnet.org/mailman/options/blindmath_nfbnet.org/kroskos%40cox.net
>>
>>
>> _______________________________________________
>> Blindmath mailing list
>> Blindmath at nfbnet.org
>> http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
>> To unsubscribe, change your list options or get your account info for
>> Blindmath:
>> http://nfbnet.org/mailman/options/blindmath_nfbnet.org/rlt56%40nau.edu
>>
>
> _______________________________________________
> Blindmath mailing list
> Blindmath at nfbnet.org
> http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
> To unsubscribe, change your list options or get your account info for
> Blindmath:
> http://nfbnet.org/mailman/options/blindmath_nfbnet.org/arielle71%40gmail.com
>