Cronbachs Alfa

[AnonymBruker]

Hei - er det noen som kan statestikk her som kan hjelpe meg med en oppgave?

 

I would like to run a Cronbachs alfa test (or similar if you have an alteriour suggestion) to include it in my reliability part. (using SPSS)

I have a mixture of variables – Nominal, Ordinal and scale.
Which have a whole range of diferent ranges in values. Some variables have 0-1, others have 1-5, while others go from 0-14000. None are similiarly kategorized. Like, sex is a 0-1. Work hours range pr week from 0-30. A satisfactory question ranges from 1-5, rent payed ranges from 500- 13000… etc..

I’ve kategorized rent, and when I lump them all togheter in SPSS – Cronbachs alfa I get a Cronbachs Alfa of around ,500.

BUT – I have a feeling this is quite pointless? Because of the state of the values – is this so, is Cronbachs Alfa usless – how would I explain that I can’t use Cronbachs Alfa? My corriculum states that it is restricted to indexes – But I can’t quite understand what this means by “indexes”. Certainly we have an index of questions that all aim to answer an underlying question – but it’s not an index where all numbers are grouped simillarilly – so i am unsure what it means… Can’t I use it ?

 

Takker og bukker veldig for svar

Anonymous poster hash: a63c0...550

[AnonymBruker?]

Hi, i actually have no clue on this topic, but i figured id ask some questions to you then maybe you realize the answer urself even if i dont =)

 

Ive put my random babble in a spoiler , while you wait for someone who have a clue to answer  

 

You say you want to find some reliability of something. Im assuming you want to find out if the people who answered the poll actually read the questions, or just selected some random choises to get the test done fast (so the answers are not reliable?)

The way you can do that is to ask 2 questions that relate to the same subject, and there should be a high correlation between the answers for these two questions. High correlation in the answers will mean that there is a high reliability that the answers were given correct. Low correlation between the answers of the two questions means ppl didnt bother reading the questions before answering (or were trying to fake it, but failed)

You say u "kategorized rent" im assuming then you just took answers to the 1 question in. But its not really possible to find out if somone answer sincerely from just asking 1 question

Do you have any questions where you would expect a high correlation in the answers? Like "do you live at home" and "how much do you pay rent" then you can give "at home" value 0 and"not at home value 1. And if the rent payed was greater than 0 you can give that the value 1 , and if 0 give it the value 0.

Now youd expect a big correlation in the answers of these two cases because theyre asking the same question just differently. If you geta low correlation in these answers, its not a very reliable test... i think =)

Btw, if you dont get an answer here go ask on another popuar forum here in Norway, the nerd density there is alot higher than here : http://www.diskusjon.no/index.php?showforum=241

 

 

 

 

Anonymous poster hash: fu420...v69

Endret 5. april 2014 av AnonymBruker?