Multiple Variable Bar Chart in SPSS and Excel
HTML-код
- Опубликовано: 6 июл 2024
- Multiple Variable Bar Chart in SPSS and Excel. This video is meant to illustrate how you can show multiple, equally-scaled variables on the y-axis of a multi-group bar chart in SPSS and Excel.
Thank-you so much for posting this video Dr. Baker. Clear, calm, and concise.
Thanks for documenting this procedure. For about three months I've been trying to figure out how to combine multiple variables on the X-axis, and now I know, plus you do it in a way that reveals the corresponding GPL syntax.
this was EXACTLY what I needed. thank you so much!
Yes thank you so much! I'm doing my final year thesis and this helped me out so much!
Thank you Dr. Baker! This was great!
Thank you ! it's really helpful
Thank you for this tutorial! I have a question: what version of SPSS were you using when making it?
THANK YOU!!!
tq so much, you literally save my life
Thanks for sharing a Nice Informative video.
Great tutorial.
Bloody saviour, thanks
Great tutorial,
I just have the problem that SPSS won't let me drag more than one variable on the y-axis. Any advice? :)
Ah man you're a life saver, been struggling with this program for ages
Thanks!
God bless you!!!!!
Can you please help me? This method worked for some of my categorical variables. For others, I can see the bars show in the preview mode, but when I click ok, in the output the bars do not show only the variable labels. Do you know what could be the problem?
At 5:55 How did you edit the label of the Axis?!?!?! I can't figure out how to do it.
Thank you very much for that video! However, the "multiple" drag and drop won't work for me (SPSS26 on Mac). I can select multiple variables, but as soon as I try to pull them over, just one variable is selected. All I want to compare is two grouped ordinal variables in one bar chart (Number of Antenatal visits during one pregnancy, one time in primipara and one time in multipara). But whatever I try, it just won't happen. I would be so happy, if you could help me out!
omg I have the same problem it's so very annoying on Mac
Only works with scale variables. Won't work with nominal. You can get around this with binary vars by coding positive as 1 and negative as 0, under these conditions, the mean represents a %, and then you can just rescale the values in the chart editor. Don't forget to change the variable type to scale.
@@TryNotToDieOmega Thanks for helping others out; I don't check the comments too often, and it was awesome seeing people helping each other!
@@TryNotToDieOmega I love you
@@TryNotToDieOmega thanks alot! wasted alot of time but finally :D
Thank you! Maybe copying it to Excel is a better way for me to make graphs!
Why i cannot add another Y??
Hi, when I create such charts for some variables I see the bars in preview but then when I click ok, I only see the variable names but no actual bars in the chart, what could be the problem?
I have the same problem and i don't know why.... Can anybody give a solution??
Hi: If these questions were asked on a Likert scale, then how is it the variables are coded as 'Scale'? Wouldn't they be ordinal values?
Brandon, this is a great question about measurement. First, let me say that you are strictly correct -- Likert scale questions are absolutely ordinal, not interval. In marketing research, as well as many other applied fields, we ASSUME subjective scales (like the Likert) are interval. The upside of making this assumption is that assuming interval allows you to compute averages, which then allows for a much wider array of statistical options at your fingertips. On the other hand, this assumption can get us in a lot of trouble if it is strongly violated (and, in a strict sense, it definitely is being violated!).
Now, this interval assumption isn't quite as bad as it looks on the surface. Statisticians have investigated the consequences of violating this interval assumption. In many cases it simply means you have less statistical power than you think, meaning you need a larger sample than traditional sample size calculations would tell you. Otherwise not too big of a deal. OTHER studies say violating this assumption fundamentally leads to large errors in interpretation.
This topic is given a nice treatment here: www.theanalysisfactor.com/can-likert-scale-data-ever-be-continuous/
I respect both sides of the issue, but in this particular video you see me making an interval (SCALE) assumption.
Very interesting video. It would be very help if you please give the data file for practice.
Is there an option of having the frequencies on the y-axis?
Hello i am conducting thesis....on employee job satisfaction on public and private sector banks it is comparative study and i collect the five point likret scale questionnaire from both sector . my question is how can i enter and analysis questionnaire response the two sector banks and made comparison by spss
My variables are dummy variable 0 and 1 , and 1 is the number that is counted, i have put it as a scale and worked, but i don't want mean, i want percentages for each variable in the Y-axis how can i do that?
If I understand your question correctly, in this instance the "mean" IS the percentage! If the "scale" numbers you're dealing with are strictly 0 and 1 values, the mean is directly interpretable as "percentage of respondents who selected the [whatever the option coded as 1 is]"
Great thanks im yoloyiny this on school
For some reason I can´t click "OK" and run it..
Hiiii respected sir, when I drag items to the Y-axis then the additional + sign is not visible. what do I do?
probably because your variables are not set as "scale" variables. they are probably set as nominal variables, causing the issue. See if that is the issue.
@@DrBakerSDSU Hi Dr Baker, I am having the same issue. Even when I switch to "scale" variables, it still won't allow me to add them. Any idea why?