On Tue, 2 Mar 2021 05:40:00 -0800 (PST), Morgan Kagande

*Post by Morgan Kagande*can someone explain if reliability is tested using one variable at a time of it has to relate to the independent variable.

You may have to re-phrase this question.

Your SUBJECT line is, "Negative Cronbach's alpha."

Cronbach's alpha is a coefficient of "internal reliability," and

it is a function (essentially) of the average correlation. It is

larger for a larger number of items in the scale with the same

average r. It can be negative when you have negative correlations.

Apha shows the expected reliability (reproducibility) of a scale

score which is computed as the sum of items listed.

Where do negative alphas come from? -- SPSS Reliability does

not know about "reversed scored" items; you need to be sure

that all variables which you pass to the Reliability program

are scored so that low numbers always represent "low" on

whatever you label the scale. (To fix: Scores may be "reflected"

by subtraction -- X in the range of 1-4 becomes X_rev in the

range of 4-1 after you subtract from 5). The resulting matrix

of correlations will be (almost entirely) positive values.

So, you might pass to Reliability a list like, Var1, Var2_rev,

Var3_rev, Var4 to Var10.

There is no "independent variable" in the Reliabilty analysis, so

that question is a puzzle.

And, "one variable at a time"?

The SPSS program can show statistics on individual variables,

like "alpha when item is deleted" or multiple R with other

variables. The MR isn't useful if the N of cases is not larger

than the number of variables.

*Post by Morgan Kagande*My alpha value continue to be negative even if i have tried putting uniform responses to every respondents

? I don't understand, at all. I can't figure a word to finish the

sentence which makes it make any sense, either.

*Post by Morgan Kagande*Does the alpha value also get to be affected by bigger sample sizes

No.

--

Rich Ulrich