AW: I am complete new to PSPP and have some questions

[Stefan Layer]

Hello David, John and Jason!

thanks a lot for your fast answers.

I am very happy to have found an active mailing list,

where I can get answers.
I have to study the answers more in detail,

i might have some addtional question on how to ADD new datas to a

file already in PSPP.
I am hoping that I will be sucessful, but I will test it after the weekend.
I just want to send my thankfullness back to you.

---> DAvid: This is interesting, the thing with winking and twinkeling. 
                 I am not a native english speaker, but I was assisted by a native, american english speaker. 
                 She was fine with twinkeling. I think there are differences in regional dialects...
                 Thanks for your comment!

Greetings

 

sTefan

---

Von: David Nasatir [mailto:address@hidden
Gesendet: Freitag, 30. September 2011 23:11
An: Stefan Layer
Betreff: Re: I am complete new to PSPP and have some questions

On 9/30/2011 2:09 AM, Stefan Layer wrote:

Questions:
1. I need help in interpreting the statistical result number.
This is most due to a basic lack in memory to my statistical classes more than 25 years ago.

But also - ich couldnt find an explanation.  

 

For example the results of a simple survey about the ability of twinkling...
(isnt that sweet...)

I do not know, but I suspect the proper English word might be "winking", rather than twinkling.  To wink, a person shuts one eye for a moment.  To twinkle, a light source varies in intensity rapidly.

a) For "my eyes" there is the strange result, that people form Northamerica
are more likely to be able to twinkle only on the right side,

versus people from europe more on the left.

As others my have pointed out, a crucial bit of information is missing ... what is the nature of the sample?  If the samples from North America and from elsewhere are each truly random samples (very difficult and very expensive to obtain) then testing for the statistical significance of the difference in the percentages makes sense.  If they are not truly random samples, it is not clear quite what the computation of statistical significance means.

I understand the first 3 lines of percentages - but not the last line - the fourth one.
b) Can anybody give me an mathematical explaniation

The table presents four numbers in each cell. The first number is the actual frequency of cases that have the attributes that define the cell.  The second number is the percentage that the frequency in that cell represents of the total number of observations in all the cells in the row.  The third number is the percentage that the frequency in that cell represents of the total number of cells in all the rows in that column.  The fourth number represents the percentage that the frequency of cases in that cell represents of the total number of cases in the population.

c) I also do not know how to interpretate correctly the last information package

about "Statistics". Is there an anybody to tell me more about that?

About the only useful statistic in this case is Pearson Chi Square .  This represents the "average" difference between the observed frequency in every cell and what would be the frequency to be found in each cell if, in fact, there was absolutely no relationship between Kontinent and Twinkle. Chi square really only has an interpretation when it has the value of zero.  In this case chi square is greater than zero, but so close to zero that it would be possible to obtain a chi square this large or larger just by chance alone due to random sampling from the population.

In essence, the numbers you present can not be used to justify the statement that there is a difference in the eye preference depending upon the continent from which the observed individual comes.


Hope this helps a little bit.

David

 

2. If I will get more additional answers of this survey, how can I add the new cases easily

and automaticly from an Excel-file or an csv-file...?

3. I dont know, how to put the Syntax-Infos (with SPSS syntax) into PSPP...

 

 

Thanks a lot for an answer

Stefan

 

Stefan

_______________________________________________
Pspp-users mailing list
address@hidden
https://lists.gnu.org/mailman/listinfo/pspp-users