concatenations with a grouping column

Dear all, Can anyone tell me how I can concatenate by grouping a column?? For example I want to create a new variable (combination) which would include the following combinations: eg: Hawaii and Florida Hawaii and Florida and New York. Data set: id Destination gender 1 Hawaii Male 1 Florida Male 2 New York Male 3 Florida Female 3 Austin Female 3 Florida Female 4 Hawaii Female 4 New York Female

Within-factors ANOVA

I have three independent variables in a within-subjects experiment: 1) Size (Small/Large) 2) Disp (0/100/200) 3) Items (4/8) So, in total I have 12 test conditions. For each test condition, I'm taking multiple trials and the number of trials is unequal. When Items = 4, I take 10 trials. (6 test conditions) When items = 8, I take 20 trials. (6 test conditions) Now, what type of ANOVA should I perform on this data? I'm a first time SPSS user, so I'm unclear how to enter all the data in SPSS? Mainly, I'm confused how to enter data for different trials corresponding to the s

Deleting Characters from a String Variable

Hello: I have a string variable that begins with the name of the month followed by the date. For example, January 12/1/2010 March 4/3/1998 February 8/17/1990 .. .. .. What would be the simplest approach in SPSS to remove *only* the names of the months from each cell? So, sticking with the example, I want it to look like this: 12/1/2010 4/3/1998 8/17/1990 .. .. .. Any help would be appreciated! Ryan

OPENING DATA ERROR MSG

Hi, Iam having trouble opening an SPSS dataset . Half my data is opening however I am getting the following error msg Datasetmsg::cLass cl letDataMsg. Has anyone had this problem before? Using SPSS 15 Thnks, D

Formatting Tables with CIs

Hi all, I am using a weighted dataset and would like to make a table that looks like this, using variables "VAR1", "SEX and "RACE": VAR1 Excellent Very Good Good Fair Poor unweighted sample size=(TOTAL) Male % 21 38.8 26.1 11.9 2.2 95%CI (17.5-25.1) (32.6-45.4) (22.1-30.5) (8-17.3) (1.4-3.5) Female % 28.2 33.1 25 10.9 2.8 95%CI (20.7-28.7) (32.1-40.2) (21.4-29.1) (8.7-13.7) (2-3.9) Nonhispanic white 28.2 33.1 25 10.9 2.8 95%CI (20.7-28.7) (32.1-40.2) (21.4-29.1) (8.7-13.7) (2-3.9) African American 28.2 33.1 25 10.9 2.8 95%CI (20.7-28.7) (32.1-40.2) (21.4-29.1) (8

Means of imputations

Hi, I am working with a large database and need to produce a probability out of a logistic regression. I am dealing with a problem of missing data. I used the "multiple missing data values" module and chose to do 5 imputations (as is set by default). Now, when I run my muliple regression syntax which saves a probability, it naturally gives different values for each imputation level. I would like to use the mean of all those probabilities and copy it back in the original file so I would not have to deal with the imputed values which are per se of little interest. Is there a way a cou

Organizing a large data

Hello, I'm fairly new to SPSS (actually using PASW) and am working with a dataset that was a collaborative effort. It has over 1200 variables, and I am trying to reorganize the data so it is easier to perform analyses (i.e. actually be able to find the variables I'm interested in). Is there anyway to select and move variables/groups of variables without just clicking and dragging? I'm trying to find a way around dragging groups of variables from say position 50 to position 1100. Is there a more efficient way or do I just have to wait while I'm dragging it? Thanks!

Combining 2 variables to 1

Hello everyone, I am a frequent SPSS user who is getting in troubles with a special question. I am having a data file with visitors to a clinic that might have a link between eachothers visit: My datasets look simplified like this: Visit | Partner 101 | 104 102 | 103 103 | 102 104 | 101 So person with visit 101 is having a relation with person with visit 104. 102 with 103 etc. Now I would like to give each couple an unique identifier like: Visit | Partner | Couple 101 | 104 | 1 102 | 103 | 2 103 | 102 | 2 104 | 101 | 1 So all co

Is Smartviewer still called smartviewer

I'm referring to the tool that allowed you to open and view output files created in earlier versions of SPSS. Used to be called SmartViewer, or something similar. What's it called now, and does anyone know whether it is part of the standard SPSS install DVD? John

statistical task related : please I need help

Hi all, My question is statistical task related. the objective is to know what the factor (between x and z : both are categorical variables)) that have more impact on Y (explicative variable). I had performed ANOVA on this way : model : Y= x z x*z the interaction is significative. P (x) <0.0001 P(z) < 0.0001 P(x*z)=0.005 What is the next step to do in order to detect the factor that have more impact on Y btween (x and z) ? If this is not clear please send me an email? I am waiting for help. thanks,

chi square

Hello! I have the following data set where I scored for each seed if it was germinated or not. If I want to know if I have different germination between the two lines depending on the treatment, is it right to make a cross tab using "germination" as layer and "treatment" and "line" in row and column respectively? What for do you use then the option "non parametric" + "chi square"? Thanks! Mara LINE SEED TREATMENT GERMINATED Mutant 1 1 0 Mutant 2 0 0 Mutant 3 1 0 Mutant 4 1 0 Mutant 5 1 0 Mutant 6 0 0 Mutant 7 1 0 Mutant 8

Einstein's Biggest Blunder - - Wasn't??

Einstein's Biggest Blunder - - Wasn't?? a bit more light about it (click link) http://www.amperefitz.com/einsteins.blunder.htm Enjoy, Fitz

Randomly recoding cases within 30 variables (according to counts within the variables)

In a data set with 1000 cases and 30 variables (all with values of 1, 0, and missing), I want to recode a random selection of 1's and 0's so that, WITHIN EACH VARIABLE, the count of 1's equals the count of 0's. I have only a limited knowledge of SPSS syntax and can't figure out how to do this. I would be so grateful for any advice. The data look something like the following (except with 1,000 cases and 30 variables). As in the real data set, in this small one, the difference in the count of 0's and 1's varies across variables. In var1, there are two 0's and one 1 (therefore one

Check is var exists and create it if it does not

Hey all, Is there a way to check if a VAR exists (or does not exist) and create it if it does not exist. I have a script that someone else wrote that uses a variable called WEIGHT. Currently this variable is not in the dataset so I have created a constant COMPUTE WEIGHT = 1. I am afraid I will forget about this line of code sometime in the future when the variable actually does exist in the dataset and is someone other than 1. Is there a way to attach a condition to this so that the COMPUTE statement is run only if the variable does not already exists? TIA, Lance

Converting string values with the wrong decimal separator into numric values

Hi, I have a large dataset with blood sample results as string variables due to a possible outcome of <0,01 (not my choice - the lab send me the results in an excel spreadsheet formatted this way) .. I've recoded the variable (REPLY.1) into a new one (REPLY.1N) where <0,01 => 0 and all other values are the kept. This to get rid of the "<". However, when I use: recode REPLY.1 (convert) into REPLY.1N. execute. to get numeric values only the 0's (zeroes) are kept. All other values (eg. 1,24; 5,10; 0,32 etc.) are listed as missing. I suspect it is because the decimal separat

How do I cite SPSS now?

I have a grant application due tommorow and it suddenly occured to me that I really don't know how to cite the program anymore (AMA style - in text, not the bibilo). Is it PASW Statistics v. 17.0.3 (SPSS: An IBM Company). Seems a bit awkward but I don't really care. I just want it to be correct. Also....I would need a citation for the data entry author. Marc

Need help with SPSSINC MODIFY TABLES

Hi, When I run the following syntax following a CORRELATION command it works fine,changing format/colour in the Significance cells of the output table: SPSSINC MODIFY TABLES subtype="'Correlations'" SELECT= "Sig. (2-tailed)" DIMENSION= ROWS LEVEL = -1 PROCESS = PRECEDING /STYLES APPLYTO=DATACELLS TEXTSTYLE=BOLDITALIC BACKGROUNDCOLOR=253 204 138. However, I want to do this conditionally; when I replace the /STYLES line with: /STYLES APPLYTO="x<.05" Nothing in the table changes, and I get the error message: "Error: empty string for float()". The table does include some

Grouping by date

Hi, Im new to SPSS so if anyone can point me in the right direction I'd be very grateful. I have a data set that is arranged as: Date Result 11.01.99 20 11.01.99 21 11.01.99 19 12.01.99 5 12.01.99 6 12.01.99 5 etc What I would like to do is group the data by date and then calculated descriptive statistics for each day: i.e is there an easy way to do this automatically? I have my data stored in a database so could issue multiple queries on the DB for each day . cheers Craig

Rank Variables

I have a list of 40 variables and a score for each respondent for each variable. How can I create a rank for each respondent and each variable, similar to the MS Excel formula "=RANK(C1,$C1:AP1)" Matthias

[python] running macros in python, spss.Submit

Hey all, Using python to zip a file. I typically have a macro at the top of my syntax file that defines the working directory. I'm trying to run that macro in python so I can zip a file. Can you run a macro through spss.submit? Another issue. I can create the zipfile if I put the entire path inside the parens. But the zipfile is not compressed. It is the same size as the original file. If I create a python file (i.e. run.py) in the directory and run the python script the zipfile is created and is compressed. Is there a particular reason why running within the BEGIN PR

Combining information from duplicate cases into one case

Hi I have a problem with a very large dataset containing information on blood samples acquired at different dates/times in 4500 patients. As more samples are provided per patient the total number of entries is apprx. 14000. What I need to do is to join information from multiple rows with the same unique identifier into one "case" with information on all samples. I need to do this in order to merge the information with another dataset with cases identified by the same unique ID. Example: What I have: ID Result Sample date 010160 1.3 010209 12.30 010160 2.9 010209 22:30 1

Data within a time period

I am working with a large healthcare data set and was trying to calculate the variation between POC blood glucose values and serum blood glucose values and how it=92s affected by Hct. For each of the tests I have a patient ID #, test date/time and value. However I have 1000 patients, 20,000 Hct values, and 50,000 serum blood glucose values and 90,000 POC blood glucose values. What I am trying to do is find all instances in which all 3 fall within the same 30min time period. But I am not sure how to even begin. Thanks, Charles

compute concat permutations python

Hay all, i am computing a new set of variables of all combinations from four sets of variables. DEFINE !CreateVar() VECTOR A = A1 to A3. VECTOR B = B1 to B2. VECTOR C = C1 to C2. VECTOR D = D1 to D2. !DO !i = 1 !TO 3 !DO !j = 1 !TO 2 !DO !k = 1 !TO 2 !DO !L = 1 !TO 2 COMPUTE !CONCAT("PERM",!i,!j,!k,!L) = sum(A(!i),B(!j),C(!k),D(!L)). !DOEND !DOEND !DOEND !DOEND EXE. !ENDDEFINE. !CreateVar. I am trying to better understand the python integration with SPSS. It would probably take me anywhere from two to four days with lots of cigarettes and more than a couple of

languages for syntax and documentation

On the Statistics Without Borders list we are starting a discussion about developing statistical capacity in developing countries. Does anybody know the link to find out what languages the SPSS syntax can be in and what languages the documentation is available in? Is there a link to prices for versions available in education in developing countries that _allow the use of syntax_? Soapbox: I consider it very poor pedagogy to rely solely on the GUI. Art Kendall Social Research Consultants

Center Text using SPSSINC MODIFY OUTPUT

I've been trying to figure out how to use MODIFY OUTPUT to center and bold the text of page titles. This command seems to run but the text does not change? How do I correct the syntax below? SPSSINC MODIFY OUTPUT TEXTS /IF OUTLINETITLE= "Page Title" PROCESS=PRECEDING /REPLACE ITEMTITLEREGEXP= "<center><b>\\1</b></center>". TIA, Lance