This channel is for my love of statistics and teaching! As a former middle school teacher I love teaching challenging concepts in accessible ways. I now teach graduate students quantitative & qualitative methods and modeling, survey & measurement, and proposal writing at CU Denver. If you are looking for more research methods and analysis support check out my site here: courtneydonovan1.wixsite.com/researchmethods
Hi thks for the great video, just wanted to ask if my infit an outfit results shows a misfitting question that was removed and improved overall measurement productivity should i be doing the PCAR both before and after the misfitting question was removed to determine if its the cause of eigenvalue>2 for the 1st contrast?
Thank you for the video! I have a question: I want to use the JMLE measure scores for each student in subsequent analysis, and the person stats (Table 6) output stats for only half of the students in my case. I am wondering why the Table 6 cannot output all the cases?
Great Video! I’m studying for my bachelor’s in psychology right now and I didn’t really get what the fuss was all about with IRT, but you made me go ‚oh wow‘ three times in just 10 minutes. Thank u :)
Thank you for the comprehensive explanation! Scale validation is a dense subect, I am glad there are resources like this lecture to help us make sense of things.
Thanks for the great video. Is the Bond & Fox Reference this one? My eigenvalue is slightly above 2. I have a short survey scale with 16 items. So this reference is helpful to make my argument.
Thank you for clear explanation. Residual SD in JASP is calculated from Total df. To my understanding, it should be calculated from Residual df instead. Correct me if i'm wrong. thanks.
This video was super helpful! May I ask you why you coded class membership the way you did? Im currently using logistic regression in a research project that asks about practitioner responses given varying company practices and for each practice there are 4 variations. So for example, a question about dosage starts at 10, then 20, 30, and 40. Im playing with a hypothetical data set right now and I code those predictors as 1,2,3,4. I guess im asking if i should be coding them the way you did? would that make a difference in the analysis?
for me I am the first to study this distribution. So effect size doesn't exist. So it seems I cannot estimate the power of my hypothesis test. Right? (using p-values/t-test)
I don't get it. How do you compute power BEFORE you do the study? I cannot compute p-values for example without my data (since I can't compute the mean). Therefore, how do I actually compute the power before the study starts (before I collect data)? Is it just with simulated data and then using that and estimates of the means, stds, guess a sample size that is needed?
Hi, could I ask if forced choice questions (whether A is better or B is better) would affect internal validity (since the participant might not be able to choose other options which he feels more inclined to)
Hi Courtney, I recently shared your video with a statistics class that I'm currently taking because your explanation of the concepts is very good! However, I was told by my professor that in 6 minutes 13 seconds of the video the effect size of ANOVA use eta was indicated, but it should be eta squared. Again, your explanation of the concepts impacted my understanding to the degree that I shared the video with my class! Therefore, great job and thank you for the clarity of the concepts!!!
Thank you!! I learned very much!! I have question...you showed one slide item range, -2.5 to 3 (range 5.5 logit) is very good!! why very good?? I want to know criterion the range in the maps!! I will wait your answer!! Thanks again!!
Firstly, thnx for uploading such a simple and succinct video explaining what parallel analysis is...However, I do have a qst. In the fictitious data, you say that mean values are counted as eigen values to be compared to PCA eigen values. But, in the excel table (2:45 mins.), the values you wrote under the "parallel" heading match with neither mean values nor prcntyle values in the syntax file (1:49 mins.). Why is that so?