Search found 1473 matches

Go to advanced search

by GerineL
Tue May 10, 2016 9:27 am
Forum: SPSS for beginners
Topic: Regression logistic
Replies: 1
Views: 233

Re: Regression logistic

It is a different estimation method. With the forward method, you keep adding variables until no more improvement in the model is measured. With backward elimination, you start with all variables and eliminate until no more improvement is possible.
by GerineL
Tue May 10, 2016 9:15 am
Forum: Output
Topic: Which analyze tool?
Replies: 12
Views: 438

Re: Which analyze tool?

yes!
by GerineL
Tue May 10, 2016 9:13 am
Forum: Data input
Topic: How to perform ANOVA with two groups
Replies: 1
Views: 190

Re: How to perform ANOVA with two groups

If you run a repeated measures, I don't think you need a posthoc comparison:
You get a value for time (pre vs post measure overall), for group (anorexia vs fashion) and for time by group.
by GerineL
Tue May 10, 2016 9:08 am
Forum: Data input
Topic: Multiple variable input
Replies: 5
Views: 492

Re: Multiple variable input

without knowing what type of measures you have (e.g., are they on a scale level, binary or....) it is impossible to answer this question.
by GerineL
Tue May 10, 2016 8:50 am
Forum: General
Topic: Case Study Analysis Help
Replies: 1
Views: 284

Re: Case Study Analysis Help

the forum is not meant for help with homework.
by GerineL
Tue May 10, 2016 8:49 am
Forum: General
Topic: cronbach's alpha help!
Replies: 1
Views: 242

Re: cronbach's alpha help!

are you going to use the scale as 1 scale, or as 4 subscales?
If you use them as 1 scale, you want to know how reliable that measure is, hence, you compute alpha for the whole scale.
if you use subscales, you want to know how reliable each of the subscales is and you compute them separately.
by GerineL
Tue May 10, 2016 8:48 am
Forum: General
Topic: How to calculate correlation?
Replies: 2
Views: 279

Re: How to calculate correlation?

what level are the string variables/ are they categorical? how many categories? Do you need relations between these string variables as well?
by GerineL
Tue May 10, 2016 8:47 am
Forum: General
Topic: String count
Replies: 1
Views: 185

Re: String count

first use the count function to compute the number of x's , y''s and z's per row.
Then use aggregate to run analyses on those variables. (or just compute frequencies).
by GerineL
Wed Apr 20, 2016 9:29 am
Forum: Output
Topic: Which analyze tool?
Replies: 12
Views: 438

Re: Which analyze tool?

aaaahhhhh okay

mean can be calculated through descriptives
difference between groups, if it is interval and normally distributed, can be achieved via t-test.
by GerineL
Tue Apr 19, 2016 3:53 pm
Forum: Enhancing data
Topic: Imputation - non- and partial-responders, or partial only?
Replies: 2
Views: 253

Re: Imputation - non- and partial-responders, or partial only?

do you have anything to impute on / base the imputation on for those 400 cases? if not, I would say only for the others, but opinions may differ.
by GerineL
Tue Apr 19, 2016 3:51 pm
Forum: SPSS for beginners
Topic: What does a "." between a value and a variable stand for?
Replies: 5
Views: 277

Re: What does a "." between a value and a variable stand for?

sorry not clear on what you are trying to achieve, but maybe the if-function is what you are looking for.

provide some example pre - post manipulation data for a more detailled answer.
by GerineL
Tue Apr 19, 2016 3:50 pm
Forum: SPSS for beginners
Topic: how to generate list of combinations of income, state and age group
Replies: 3
Views: 197

Re: how to generate list of combinations of income, state and age group

okay to be honest I would do this in excel in like five minutes and then open it in spss. Be patient for an answer involving only spss.
by GerineL
Tue Apr 19, 2016 3:49 pm
Forum: Output
Topic: Which analyze tool?
Replies: 12
Views: 438

Re: Which analyze tool?

I am still confused. WHat do you mean by "mean number difference"?
by GerineL
Mon Apr 18, 2016 12:10 pm
Forum: Errors
Topic: "Tolerance = .000 limits reached" during hierarchical regression due to 1 control variable
Replies: 1
Views: 282

Re: "Tolerance = .000 limits reached" during hierarchical regression due to 1 control variable

This means that there is some redundency in your model.
Could it be that you have for instance a variable for country, and this perfectly corresponds to for instance GDP?
i.e., if country is 2, GDP is always 3?
by GerineL
Mon Apr 18, 2016 12:08 pm
Forum: SPSS for beginners
Topic: What does a "." between a value and a variable stand for?
Replies: 5
Views: 277

Re: What does a "." between a value and a variable stand for?

so if you use rename variables, the name of the variable is changed.
You should probably use something like recode

Code: Select all

recode r ("vrüst2"= "vrust2").
execute.

cron