# Discovering Statistics

## Information

This is a group for users of my textbooks (and anyone else really) to discuss the books, post questions and so on.

Members: 265
Latest Activity: Jan 29

## Discussion Forum

### Missing Variables3 Replies

Hello all, I have data that goes as follows:"if you did____, fill out section A. if not, fill out section B"For those who filled out section A, there is a lot of empty spaces in the SPSS spreadsheet…Continue

Started by Lindsey Chesus. Last reply by Lindsey Chesus Dec 23, 2015.

### Pattern Matrix not showing up (Factor Analysis)7 Replies

Hello,I ran a factor analysis, and the pattern matrix is coming up as:Pattern Matrix aa Rotation failed to converge in 25 iterations. (Convergence = .000).What does this mean and how can I fix it? I…Continue

Started by Lindsey Chesus. Last reply by Lindsey Chesus Dec 15, 2015.

### Adjusted error bars for repeated measures designs

I've been slowly working my way through Discovering Statistics Using R.  I just got to chapter 9 - comparing means.I've been reading the section on creating adjusted error bars for repeated measures…Continue

Started by Gavin Revie Sep 4, 2015.

### Problem with factors in line graphs (Chapter 4 of DSUR)1 Reply

I've been working through Discovering Statistics Using R.  I'm using R version 3.2.0, run through the latest version of R Studio.  I've noticed a few errors which I imagine you're already aware of…Continue

Started by Gavin Revie. Last reply by Gavin Revie May 26, 2015.

## Comment Wall

Comment by Kim Zachon on January 29, 2016 at 18:20
I was wondering if anyone on the discovering statistics forum could help with my question of how to formally report parameter estimates of a covariate of an ANCOVA?
The  research questions of my dataset are whether there is an initial visual processing deficit in
developmental coordination disorder? And if so does a visuo-motor training programme improve these skills in the same way as it does for typically developing adults?
I have run an ANCOVA (with the IVS of group and training, DV as score on visuo-processing task) to investigate whether age is a covariate. I need to formally report the parameter estimates of the covariate (age) and have been struggling to find guidance on how to formally report this in all of the textbooks and internet resources I have been using.
I have currently reported it like this: (b=32.442 [22.077,22.077]p<.001) but I am unsure whether I need to include the degrees of freedom, and if this is the correct way of reporting
the confidence intervals
Comment by Cathy Evans on November 24, 2014 at 17:49

Stories of African American Graduates of Online Doctoral Programs Needed!

Cathy Evans, a doctoral student at Walden University, is conducting a study.  African American doctorate recipients who attained a doctorate from online doctoral psychology programs at Title IV privately operated for-profit, online institutions that practice open admission (FPCUs), within the past five years, are needed to share their experiences and knowledge of completing an online doctoral psychology program at an FPCU.  The study seeks to explore the academic achievement of African American students who completed online doctoral programs and attained a doctorate in psychology at Capella University, Walden University, the University of Phoenix, or the University of the Rockies.

Invest a little time from your schedule by contributing your knowledge to an emerging body of knowledge.

To participate, you must be (a) African American and (b) must have attained a doctorate in psychology from an FPCU within the past 5 years.  The time, involved, will consist of the following:

• One nonpaid 60- to 90-minute in-depth interview: face-to-face, live chat, Skype, OR  telephone, and
• The time you spend reviewing, your interview summary.

Comment by Sally Ransom on February 6, 2013 at 16:29

Hi all,

I'm very pleased to let you know that SAGE has recently set up a new Facebook page about all things Andy and Discovering Statistics, where we'll be posting news, free stuff, photos, videos, competitions and more. We've just posted the second video in our Ask Andy Anything series which is well worth a watch! Hope you can join us over there:

Comment by Charles C Moller on February 4, 2013 at 19:03

I'm sorry that I posted a new discussion item as a comment to this thread. I now understand where it should have gone.

Comment by Charles C Moller on February 4, 2013 at 17:43

Hi,

I am new to R and am learning using DSUR. On page 78 it is suggested that we load a package called DSUR in order to have handy the functions in the book. The current DSUR package is not compatible with R v 2.15.2. Do we simply cut and paste from the book's website? Is there a new DSUR package out there that I have missed?

All the best,

C Moller

Comment by Sinfree Gono on October 11, 2012 at 18:16

Thanks Katie. Have sent to the group hoepefully with luck i will get some hints.

Comment by MJ on May 22, 2012 at 12:33

Hi everyone,

I am doing ROC Curve analysis to establish cut-off points for a scale. I calculated Youden's index to establish cut-off points, however to my despair, the Youden's index is equal for two of the scores:

Let's say my subjects could score between 10-20 on a scale and the Youden's index is the highest at 124.5 for scores 15 and 16 on this scale. I wonder what would be the best cut-off: 15 and 16?!
obviously sensitivity is higher on one score and the specificity for the other

Comment by Henry Steel on May 22, 2012 at 8:43

Dear Andy and All

I have a question about data transformations. Consider the following explanation written by Andy:

“As such, transforming the data won’t change the relationships between variables (the relative differences between people for a given variable stay the same), however, it does change the differences between different variables (because it changes the units of measurement). Therefore, even if you have only one variable that has a skewed distribution, you should still transform any other variable sin your data set if you’re going to compare differences between that variable and others that you intend to transform.”

My concern is the following: I understand Andy's argument about changing the units of measurement, but what will happen if you transform a variable that is normal? Will it become skewed? If so, what is the use then of transforming the skewed variable(s)? Maybe I am missing something. Looking forward to some advice.

Best wishes

Henry

Comment by Rafael Garcia on May 1, 2012 at 22:48

Mutasem,

There's a decent description of post hoc tests here: http://pages.uoregon.edu/stevensj/posthoc.pdf

In short, different post hoc tests scale the F-ratio differently. Depending on how the F-ratio is distributed, you may end up with n.s. contrasts (common in Scheffe's method).

Comment by Mutasem Akour on May 1, 2012 at 22:27

Hello

I wonder how is it possible to get a significant omnibus F in one-way ANOVA, and getting no significant differences in a post hoc test ?