Thursday, December 11, 2008

Merry Christmas!

...and see you in ANOVA in the New Year.

Reporting Significance Levels

John asked,

When reporting significance level at the .05 level, if my value is .051 can I report as p = .051 (using three decimal places to show approximation)?

Wednesday, December 10, 2008

Missing Values

Mari said earlier that
Absolutely you should drop any participant who is missing both predictors and outcome.


I have 2 predictors and 1 outcome.
In the event that the outcome and one predictor is missing values do I delete the case even if the other predictor has an value listed?

Assumptions

Can you test assumptions for a categorical variable? This doesn't seem to make sense, because looking at residuals for a contrast-coded variable doesn't seem to provide useful information. So maybe rather than can you test the assumptions, my question is am I supposed to?
Also, for a moderated model, do you check assumptions for the moderator variable? I know there was an earlier post that said you don't have to check assumptions of the predictor for each level of the moderator, but I'm unclear about checking the moderator as its own variable.

Tuesday, December 9, 2008

reflecting part 2

I noticed that after I had reflected my data and transformed it, the relationship became a positive one, where betas went from negative to positive. I do conceptually understand why it turned out this way, but in my results write up, do I indicate that after i have reflected and transformed my data, there was a significant negative relationship in transformed units, and then report the positive betas that I got from the regression?

mirroring

The distribution of my residuals were slightly negatively skewed, and when I mirrored and transformed my outcome, the histogram still showed a slight negative skew. Can this be normal, or did I overlook a step in my transformation process?

Thank you for all the lightning fast responses!

Violation of homoskedasticity?

Photobucket

Sorry if it is not okay to ask this outright, but does this look okay?  I went ahead and tried the transformations and it got progressively worse. Should I include in my write-up that I tried to transform but it got worse, or should I just say this is "good enough" and only include my first tests of assumptions?

Vanishing Post?

I was responding to a post, and blogger wigged out on me. Suddenly my response and the original post were both gone. If your post vanished, and you still need the answer, please repost!

How Much Overlap is Too Much?

There have been a couple of blog and backchannel questions about the acceptable degree of overlap between previous homework assignments and the final project.

The general rule is that as long as 51% or more of the model has changed, you are OK. That is,

1. if you are using some of the same variables, but in a different model (i.e., the homework model was an additive hierarchical model and now you are looking at the same variables in a mediated or moderated model), that's OK. (Note that the converse is not true--a mediated or moderated homework model cannot revert to an additive hierarchical model, because in that case, you would have no need to run the regressions, because they were already done in the original homework assignment. That is, regression 3 from a mediated model is exactly what you would run to test an additive model with those variables. Similarly, step 1 of a moderated model is the additive multiple regression model.)

1. if the outcome is the same, but predictor and mediator are different, that’s OK.

2. if one predictor is the same, but a moderator, mediator, or second predictor have been added, and the outcome is different, that's OK.

3. if a mediator is the same, but the predictor and outcome are different, that's OK.

If you aren't sure if your model fits those parameters, feel free to ask, but have patience for the reply. I start jury duty tomorrow and will not have internet access...

Transformations

I know that you just do a transformation when both assumptions (homoskedasticity and normality are violated), but what do you need to do when the two violated assumptions are linearity and homoskedasticity (a different pair)and normarlity is perfect. I found in my notes about polinomial regression or adding a squared term to the regression. Do I need to do that? If yes, HOW? If not, I will have 2 assumptions violated. Does that mean that this model does not work?

transformed results write up

would it be possible for us to see an example of an APA results section where the data was transformed? or is it just a matter of just indicating that the results were transformed and discussing the numbers in transformed units?

comparing negative Betas

Hello, I have another question regarding negative betas:

For my mediated model, if the B from the first regression (predictor->outcome) was, let's say -0.55, and the B of predictor->outcome on the third regression was -0.02. Would I still treat this as a situation where the B from the first regression is "greater" than the B from the third? Since mathematically, -0.55 is a smaller value than -0.02, but in terms of relationships, -0.55 still represents a greater amount of change per unit of X?

A question regarding my model

Will be acceptable to do a moderated model with sex as moderator, but using different predictor and outcome varibles not used in the last assigment?

Mediated Model

I have a question regarding my mediated model.

My unstand. B in R3 (-0.015) is not lower than B in R1 (-0.17), but the 3 regressions showed that each is significant (p-values of R1, R2, and R3 are less than .001). This shows that there is no mediation? What's going on?

And when I put this into the Sobel's test (for negative betas), the test statistic shows to be -8.48, but the p-value is 0. So there's a significant level of mediation, right?

These two results are not supporting one another.

Another question: for the Sobel's test statistic, do I regress Mediator (M) to Outcome (O) separately to find the B and SE? Or do I just use the M and O figures from my R3, which is (P and M on O)?

Thanks!

Transformed Variables and the Sobel Test

To add to Chris's question,
If we need to do a transformation in a mediated model, do we have to do anything to the unstandardized beta's before we use them for the Sobel test or can we use them as is?
Thanks,
Andrew

Exam 3 at Front Desk

Feel free to drop by and take a look at your exam, and where you currently stand in the class. Note that your final article reviews are NOT included in that grade estimate (just because the TAs are working on final exams and projects too, not because of any special thing about these assignments).

Monday, December 8, 2008

I am working in a moderated model were I need to run separate regressions for each level of the moderator variable. I want to check my assumptions, but I don't know if I need to use the unstandarized predicted values and residuals of the separate regressions or I need to run a single regression for all cases and use those unstandarized predicted values and residuals. In other words, do I need to check assumptions separate for each level of the moderator (2 graphics per assumption)?

negative betas and sobel's test

I was using the sobel's test website to test a mediated model, but i noticed that when one of the B's i put in the equation was negative, the significance values became what looks to me like 1-p? (i.e., if i had a 2-tailed p value of .95 with the negative B, it would turn into .05 if i changed that B to positive.) How would significance be determined/reported for this situation? And would I report the sobel's test statistic as negative as well?

thanks!

Assumptions for a Mediated Model

Hello friendly and helpful TAs (and/or Mari),

I have a question related to GLM assumptions for a mediated model. When we utilize Baron and Kenny's three model approach for testing mediation, there are three separate regressions performed to test the mediation; during these steps the 'predictor' and 'outcome' variables change according to what you want to analyze. (The relationship of the true predictor to true outcome, relationship of true predictor to mediator, and relationship of both true predictor and mediator to true outcome).

So, my questions:
1) Do we have to test each seperate relationship for GLM assumptions? I assume that at least the first two models do need to be tested, as the relationship of the predictor to outcome and the relationship of the predictor to mediator would have to conform to the assumptions to be valid, but I am unsure of the last model.

2) If assumptions are not met and a transormation needs to be tested on the outcome variable, should I transform for each step of B & K's mediation approach? If I do, this makes interpretation sort of hairy in the second step of the model, as the "outcome" variable to be transformed is no longer the outcome of true interest. Or should I just transform my true outcome on the first regression? In the case that I need to transform for all steps of B & K's approach, how do I interpret the relationship at each step?

Gracias,

Chris

clear-up on small detail

I know that we aren't allowed to use any model previously used in homework assignments or lecture, but we can still use a variable that was used in those assignments, right?

For example, would I be able to hypothesize that perceived humor and morality would predict global self worth? (Not actually using this model for my assignment, but global self worth is a variable we used in other assignments, but since the overall model uses different variables to accompany global self worth, I can go ahead with it?)

thanks!

Failed Assumptions

If when you test your assumptions and cannot pass no matter which transformation applied, can you still use that regression include in your write up that it didn't pass assumptions so that the data cannot be interpreted reliably? Do you want us to start the complete experiement over again with new variables until we find something that works?

Which residuals to use?

I am trying to test the assumptions for a hierarchical multiple regression. After I create the new variables (in this case, square root transformed), do I re-run my assumptions by plotting the new square root variables with the residuals that were generated from my first regression, or do I save new residuals by running the same hierarchical mutliple regression with the new transformed variables and then re-run the assumptions using those new residuals that were generated from the second regression?

Sunday, December 7, 2008

Testing Assumption of Homoskedasticity

After creating my scatterplot, i would like to test the ratio of highest to lowest variance. I am not sure how to split the file- the options within this drop down menu do not seem to include the ability to separate the predictor (or is it the predicted values i use?) into meaningful levels. Is there another step i am missing? I messed up my data file once already trying to accomplish this and had to red0 everything all over again :-(

Also, is there a generally accepted cut-off point when you have missing data (i.e. if the missing data represents < 5% of the total sample) that is applied when deciding to omit participants? Predicting values has already proven to be difficult due to more missing data in the alternative variables used.

Thursday, December 4, 2008

Final Project: Missing Values

My outcome variable is missing 8 values. I used a multiple regression with my outcome and two other variables that are significantly related to my outcome but aren’t my variables of interest. Yet, my outcome variable is still missing 8 values because those 8 cases were also missing values for the two significantly related variables. Next, I used the regression equation (Transform à Computer Variable) and formed a “predictedoutcome” variable a follows:

Predictedoutcome – B + (B * variable) + (B * variable)

My new predictedoutcome variable is still missing 8 values.

Where shall I go from here? Am I supposed to continue to look for additional variables that are significantly related to my outcome variable? Should I drop a case (subject) if there are missing values on all three of my variables of interest (i.e., my two predictors and outcome)?



Also, can you please specifically explain how to merge two variables on SPSS? I tried merging two variables in “Compute Variable” under the “Function group” but received an error messsage.

Thank you.

Wednesday, December 3, 2008

levels of moderation

Hello, I hope it's not too late to ask this question...

For categorical moderators, what does it mean exactly when you regress the outcome on the predictor for each level of the moderator? Would they be separate simultaneous multiple regressions where you regress predictor and level 0 of the moderator on outcome, and regress predictor and level 1 of the moderator on outcome?

Tuesday, December 2, 2008

note discrepancy

I found a discrepancy between the typed out notes and the slides, and could only speculate as to which one was correct. In the notes (for "Prediction and Validation", 3rd page, last sentence above Validation of models) it says
"As sample size increases and number of predictors INCREASE, these three types of R^2 grow closer..." (emphasis added).
The slides however (slide 17 i believe) says these three types "merge as sample size N increases and number of predictors (k) DECREASES"
It makes sense to me that k should decrease because an increase will take away from degrees of freedom, decreasing power. But i don't want to jump to conclusions...which is right? Thanks!!!

Monday, December 1, 2008

Review Sheet and Final Project Posted

The review sheet for exam 3 and the guidelines for the final project have now been posted to Portico. The TA's will also have copies of the review sheet at this evening's review session.

For those of you who would appreciate individual review sessions, please feel free to sign up for times with the TA's.

Article Review

I am working on an article review and I came across an article with an author listed his/her name as A. H. Y. Ho. Should I cite his/her name as "Ho, A. H. Y." or "Ho, A. H." in the reference section of the article review? Thanks.

Wednesday, November 26, 2008

article review ?

Ok...for one of my article reviews i have run into a problem...

When searching the results section (and then the rest of the paper!) i could not find the models used specifically stated. I know that they found frequencies, but the rest of their results are simply given in different symbols. I can only speculate (and try to remember) what these symbols mean. A few of the statistics look like this: x^2(l) = 8 54, p < 01 ....which i BELIEVE is chi-squared? Then further down it changes to Z = 3 25, p < 001...which i BELIEVE is z-test?

Are these speculations correct? should i simply state that they didn't give a specific model used in determining results?

If needed, here is the reference for my article:

Egeland, B., & Sroufe, L. A. (1981). Attachment and early maltreatment. Child Development, 52, 44-52.

Thanks in advance for your answers!

Monday, November 24, 2008

Review Session Questions...Answered!

Hi all!

As promised, I contacted Dr. Clements to get the answers to questions I wasn't sure about that were asked during tonight's review session.

1. Sobel's Test is reported with the symbol z prime. That is, use a lowercase, italicized z with a tick mark superscripted above it. (If I could get the blog to show it, I would.) If you don't understand from my description, you can see the article that Dr. Clements suggested you look at for an example of writing up mediated models found in an earlier post on the blog.

2. Always, always, always use 2-tailed tests of significance.

3. You do NOT have to include ANY figures for the moderated/mediated models homework. However, IF you do choose to include them, make sure they are formatted according to APA format.

4. Finally, we come to centering. This is important for one of the methods for testing moderated models. If you choose to test it using the method that requires an interaction term, you need to center the continuous predictor variable. Make sure you do this before creating the interaction term. Otherwise, you'll have collinearity issues.

SPSS GradPack Installation Issues

Bought the gradpack this weekend. I had a lot of problems trying to get the software to work. After waiting 1 1/2 hours for SPSS tech support this morning, it turned out that the company mislabelled their installation authorization codes.

In the gradpack, you will see two authorization codes: SPSS Installation Authorization Code and Amos Installation Authorization Code. For my gradpack, the code for the SPSS Installation Authorization Code is actually the code for AMOS Installation Authorization Code, and vise versa. If you are thinking of purchasing the SPSS software, and you encounter similar installation issues, you might want to try using the Amos code.

The SPSS technician said this problem has been noted and that I wasn't the first person to have this problem. Check with the SPSS technician if you are still having installation issues.

Good luck.

Logistic Regression Yanked

I have decided that it makes more sense to consolidate what we already know about regression than to add another topic...

Sunday, November 23, 2008

Sobel's Test

Regarding to question 2. A., how do we report Sobel's test result in APA format? Is there a specific symbol stand for Sobel's test, such as B stands for unstandardized B? Thank you.

Sobel's Test, Part 2

I think I understand what the diagram on the website means conceptually, but my question is more related to reading the SPSS printout. On my SPSS output for the third regression of question 2, I have three Betas: the constant, and two Betas for the two independent variables I used in the regression. What I'm not sure of is which of these three Betas Sobel's test is asking for.

Saturday, November 22, 2008

Sobel's Test

I'm having trouble figuring out which numbers to use for the online Sobel's Test calculator (http://www.danielsoper.com/statcalc/calc31.aspx). On the website it asks for four values: A, SE of A, B, and SE of B. I figured out where to find A and SE of A (i.e. the Beta and SE of the predictor-mediator regression), but I'm not sure where to find B and the SE of B (i.e. the Beta and SE of the mediator-outcome regression). According to the "Additive, Moderated, and Mediated Models" handout, slide 11, there is no Mediator-Outcome regression, so where do I find the Beta and SE that the Sobel Test is looking for?

Centering in SPSS

i cannot seem to find directions for the keystrokes necessary to center a variable in SPSS. How does one translate the equation into something that SPSS recognizes- i've hit a wall. I've done it manually but am not sure whether or not the results are precise enough.

Friday, November 21, 2008

2 questions

(1) When looking at slide 7 and realizing which test we should complete, i realize that the one we use does not include looking at the interaction. I'm wondering, then, if we still need to do so because in slide 9 the second bullet says that we must interpret the interaction. So, do we still need to look at the interaction term even though it is not discussed in the type of test we are using for question number 1?

(2) In the hw you say that "if" we include figures...this doesn't say that we need to, but should we since it is mentioned in the instructions?

Thanks!

Betas for interaction model

After adding the interaction term to the second model, it seems unnesscessary to explain the betas for the gender and PAQ variables because they have already been explained through the interaction term interpretation. Is it then necessary to interpret the Betas for gender and PAQ for the second model in the write up after you have already explained the interaction term?

At Long Last

Received from the bookstore
----------------------------------------------------------
Dr. Clements,

The SPSS 17 Grad Pack is now available in the bookstore. We currently have 5 copies for Mac and 3 copies for Windows. Thanks!

Jeremy Mast
Bookstore Floor Supervisor

Thursday, November 20, 2008

Based on the last question:

Can we use a calculated interaction term for question 1 with gender, by treating gender as continuous?

Furthermore, can we center gender if we have problems with collinearity? Is it okay to center gender?

Wednesday, November 19, 2008

Multiple vs. Linear Regressions

I'm looking at question #1 on the homework and I'm not sure exactly what type(s) of regression(s) to run. According to the PowerPoint slide handout for "Additive, Moderated, and Mediated Models", Slide 7, we are supposed to run three separate regressions:



1. Outcome by Predictor

2. Outcome by Moderator

3. Outcome by Moderator/Predictor Interaction Term



Did I understand this right? Also, are we running three separate linear regressions, or one multiple regression, or some combination of linear and multiple regressions?

Sample moderation/mediation APA write-up

Looking through the notes, I notice that we do not have a sample for how to write up a moderation or mediation results section like we had for Multiple Regression/Linear Regression. From the notes, I know what moderation and mediation mean, I just don't know how to write them up. I know how to use APA format, I just do not understand how to say what I need to say and what statistics are appropriate for moderation/mediation.

Tuesday, November 18, 2008

Hierarchical Stepwise Regression

What is a hierarchical stepwise regression? Is it as just as "bad and evil" as stepwise regressions? How does it relate to forward and backward entry?

Thank you.

Formula for the Curve

For any assignment curved in any of my classes, the formula is the same:

Individual's score
------------------------- X 100
Highest score in class

In this case, there were a few folks who scored 100 or 92, but I took them off the curve, and used the next highest score (90) as the denominator.

So, if your score had been 80, solving this equation, you would have a score of

80
--- X 100 = 88.8
90

Next Quarter ANOVA Sections

The ANOVA class is just like the Regression class in terms of the course sections. The two sections are the same--there is no PhD or PsyD section. Choose the one that fits best with your own work, class, and personal schedule.

Q regarding the article review

Hi,
I read an article using the quantitative reserch review method, and wrote a review under the empirical article review format. I just wonder whether it's ok, or I'd better adopt the theoretical review format.
Thank you.

Monday, November 17, 2008

Recommending normality transformations...

So, the book doesn't recommend the need for transformation if there is a problem with normality (p.46). I think they give a reason for this, but if it's their reason, i don't understand it. They even say that "many regression textbooks" do find this type important. I know transforming is largely subjective...but what is the rule of thumb for this?

Thanks in advance for the clarification!!!

Saturday, November 15, 2008

Interactive and Mediated Models Homework

The homework assignment is posted on Portico. Note due date change from syllabus.

Wednesday, November 12, 2008

Article Reviews and Next Homework Assignment

So, given that this coming Tuesday has many, many things due, I thought that it might make sense to modify our due dates as follows:

The Article Reviews that were due on Tuesday are now due on Thursday.

The Interactive Models homework that was due on Thursday is now due on the following Tuesday.

I realize that this just redistributes pain rather than eliminating it, but if it helps you to have a couple of extra days, please take them as outlined above.

df1 = k - 1

Hi, I'm working on question 9 in the review sheet.

When using the equation df1 = k - 1 in regression, is the constant considered one of the predictors so that df1 = k - 1 = 2 (the constant and another predictor) - 1 = 1?

Is this the right way to look at it or should I be taking the class again?

Monday, November 10, 2008

?? regarding the text

Okay...So, i've been meaning to ask for a while, just never sat down to ask.

The book makes a lot of weird marks above the symbols, and i dont' know what the different marks mean. For example...The predicted value from the model is (symbols that i can't even try to make with word so i'll attempt to explain in words)...Xi with a tilda (~) above it and then β with a ^ above it...

p.48 for reference due to my lack of vocabulary...

So...do these symbols have a meaning? I'm sure they do...so i guess what is the meaning they carry? and is it common to use them?

Review Sessions this Week

In addition to our regularly scheduled Monday session at 5 p.m. in room 126 Weyerhaeuser, there is an additional session scheduled for Wednesday at 6 p.m. in room 311 Weyerhaeuser.

(Weyerhaeuser is the official name of the Psych Building...)

Friday, November 7, 2008

Study Guide for Exam 2

The review sheet for Exam 2 is posted on Portico.

Wednesday, November 5, 2008

Sample size & descriptive statistics

I was about to write up my results section for the homework and noticed that the homework handout mentions surveying 240 college students, while my SPSS output looks like it has a sample size of 371, where F(2, 368) = xxx.xx for model 1. Was this a typo on the handout, or am I missing something?

Also, do we need to include descriptive statistics in our results write up? Thanks!

write up

For question 1A, we are asked to report whether adding more predictors will improve the predictability of all of the X variables or not. Do we have to report the R square for each model or do we have to report the R square for the overall model only? When the change of R square between two models is 0.00, does it mean adding extra predictor variable(s) does not improve the prediction? Thanks!

Tuesday, November 4, 2008

question about the write-up

As I am looking at my powerpoint notes, I noticed that the write-up talks about "higher education weakly but significantly predicted lower happiness" and later "Age was also found to signicficantly predict happiness, with older respondents slightly but significantly less happy." I am assuming these are referring to the unstandardized betas and obviously the significance values.
My question is how else to state/explain the differences in unstd. betas as we look at six different variables. I started to say in my own write up that one had a slightly stronger correlation than the other or that the strongest variable correlated was such and such. I'm afriad this is too close to the dreaded "better predicts" that Dr. Clements told us to avoid and that correlated isnt the right description??
Is it important that we differentiate between unstd. betas as we do our write up, or is it enough to say that they all significantly predicted self worth or all but such and such sig. predicted?

Thanks...

Transformations PowerPoint Slides

Hi all!

After looking back over the PowerPoint slides from the transformations lecture today, I realized that I made a change to a slide, but forgot to mention it. Your print-out of the slides needs to be modified at one point.

If you look at the first slide on centering, it states "To center: Y i centered = Yi – Mi." It should actually read, "To center: X i centered = Xi – Mi" We only ever center predictors, and X stands for our predictors, while Y stands for our outcome variables. To center, subtract each value of the predictor from the mean of the predictor (or some other meaningful value). Sorry for the confusion.

What means altering the order of entry of the blocks?

For the second step of the HW, we have to "alter the order of the entry for the blocks of variables". Note it does not say altering the order of variables.I am interpreting "altering the order of the blocks" as we should keep together the variables that were together in a block in the first analysis. In other words, if in block 1 of the first regression I had variables A and B together, in the second regression I will keep A and B together but will entered in step (block) 2,3,4. Is this correct? Should I mix the varibles and create new blocks (for example have varible A in step 3 and B in step 4).

Colinearity and Tolerance

When describing colinearity for part C of question 2, we are using tolerance statistics via SPSS (which have an inverse relationship with with colinearity; e.g., the higher the tolerance value, the less colinear are the variables). SPSS gives tolerance statistics for each variable in every step (or block) of the model. My question: for each specified variable that is excluded (in the first step there are 4, the second, there are 3, and the third, there is 1), does the tolerance stastic associated with that variable refer to colinearity between that variable and the model at that point in time? For example, at Step 1, the tolerance level that is reported for physical appearance is the relationship of colinearity between that variable and the overall model- which up to that point has used intellectual ability and school competence (and therefore only refers to colinearity between these variables used together and physical appearance?) If you could help to deliniate what the tolerance levels mean for each block, it would be helpful.

Chris

Difference between the first hypothesis and 2-4.

In the write up portion of the assignment should we account for the difference in wording from the first hypothesis and the other three. The first states "expect to predict higher levels of global self-worth", while the other three state "significantly improve prediction of global self-worth". Does "improve" refer to the "prediction" or "global self-worth"?

The way I read it is that "improve" is referring to prediction, so the variables in hypothesis 2, 3, and 4 could all improve prediction for lower self-worth and still prove the hypothesis. Am I reading this wrong?

Multiple Regression Homework: Question 1

Are we running four hierarchical multiple regressions (i.e., 1 - block 1; 2 - block 1 and 2; 3 - block 1, 2, & 3; and 4 - block 1, 2, 3, & 4)? Or, are we running one hierarchical multiple regression (i.e., 1 - block 1, 2, 3, & 4)? The coefficients table yields slightly different values.

Thanks.

Monday, November 3, 2008

hypothesis 1

For the first hypothesis of the Multiple Regression homework, are we using a simultaneous multiple regression to find our answer instead of a heirarchical?

Or are hypothesizing that perceived school competence and intellecutal ability would predict higher global self-worth, holding all other variables constant? So if it were a heirarchical regression, would the independent variables in the first block 0f the heirarchical regression be schcomp and intabil, and the second block all the other variables that we are considering for the assignment?

Writing Workshop

Please encourage any and all students who are having difficulty with their writing skills to attend our upcoming Writing Workshops, presented by Fuller's Writing Center. By encouraging your students to attend, you will not only help them to improve the quality of their writing, but also potentially save yourself and your TAs some grief in grading papers at the end of the quarter! :) All workshops are taught by Fuller alumna Kathryn Streeter, who came to Fuller with six years of English teaching experience and has, to date, served as a TA for a total of nine classes taught by four different Fuller professors. The workshop schedule is as follows:

Composition Workshop
How to develop a strong thesis statement, form coherent paragraphs, and use supporting evidence appropriately
Friday, November 7, 2008, from 1-3 p.m., in Payton 102

Advanced Composition Workshop
How to develop different kinds of thesis statements, transition deftly between paragraphs, smoothly integrate quoted material, and more!
Friday, November 14, 2008, from 1-3 p.m., in Payton 102

Grammar & Editing Workshop
How to fix common grammatical errors such as inconsistent verb tense, flawed sentence structure, and misplaced punctuation
Friday, November 21, 2008, from 1-3 p.m., in Payton 102

All workshops are FREE, and no RSVP is needed. A packet of helpful materials will be available at each workshop for $5.

Thank you for your help in getting the word out! Flyers will be available in classrooms this coming week for the benefit of interested students. Feel free to contact kathryn_streeter@fuller.edu with any questions.

Saturday, November 1, 2008

Trouble with downloading SPSS file

I was trying to download the SPSS file for our Multiple Regression assignment in the library computer lab and it did not work. I went back to the linear regression assignment SPSS file, only the zip file would work. So, can we can have the zip file for Multiple Regression as well? Thanks!

Wednesday, October 29, 2008

Multiple Regression Homework

I heard that some of you were all geared up for a take home exam in another class that has now been delayed, and would appreciate getting the Multiple Regression homework sooner, so it is now posted on Portico.

Tuesday, October 28, 2008

tips for article reviews

hey guys,

so the TAs have noticed a consistent pattern around a few types of mistakes that are being made on the article reviews. so we collaborated together with Dr. Clements and came up with a list of things, broken down by the section of assignment, that you guys should watch for when you do the rest of your article reviews. hope this helps.

Major Findings:
-Make sure you specify what kind of statistical analysis was used. Because this is a stats class, attending to the analysis used is important. Notice that for future use (not for grading purposes), you will also want to know how people have analyzed these kinds of questions. You will also want to note, for your own use (as well as for inclusion in the flaws and limitation section) whether or not the analysis was the right one to use for the types of data the researchers were analyzing.

Population:
-Make sure you include number of participants, age, ethnicity, and gender. If the authors omitted that information, note that it was not provided. Otherwise, we have no way of knowing that they made the mistake (not you).

Relevance:
-Make sure you tie in how the study relates to your specific research interest. Part of the task of these assignments is to explore a research area so that you will be well positioned to write your masters or dissertation. If you do not read articles that relate to your scholarly interests, this goal cannot be fulfilled. You are not being asked to commit to a particular topic, but your exploration does need to be serious and scholarly, and you must include evidence that you have considered how this work is connected to work you might want to do.

Other things to note:
-Don't bold headings. Italicize them. The only proper use of bold type in APA style is reporting vectors (see p. 140 of the APA Publication Manual).
-Indent paragraphs.
-Margins should be 1 inch all around.
-Don't start sentences with numerals. (e.g. “23 people were studied...” = BAD :( ; “Twenty-three people were studied...” = GOOD :)) See pp. 122-130 of the Publication Manual for the appropriate use of numerals versus written out numbers.

Updated Faculty Recommendations for Readings Posted

The faculty recommendations for articles to read for Article Reviews have been reposted to Portico. There are some additions for some faculty, and some corrections for others.

Wednesday 10/29 at 4 pm in Travis

Monday, October 27, 2008

Table Notes Font Size

Is the font size for table notes the standard 12 pt. font? In the APA manual's table examples (pp. 162-169), the font clearly seems smaller. However, I was unable to find a definitive answer in the APA manual (see p. 170). I noticed the table notes on the lecture slides are the same size font as the font size of its respective table; therefore, I'm assuming that we are to use the standard 12 pt. font size for table notes.

Is this correct? Is decreasing table notes font size the job of the editor?

Thanks.

First Review/Consolidation Session Today!

[this is really from Kris, not me...]

Just a reminder that today's review session will be in Psych 126 at 5pm. Please bring your questions regarding material covered so far as I will not be structuring the review time. I will walk through the computation of linear regression on SPSS using an alternate dataset from what you are using for your second assignment if you are feeling confused about what it is we are covering currently and how to run the analysis.

See you this afternoon.

Kris

Friday, October 24, 2008

Questions About Linear Homework

Hey Guys!
On the table, since it is linear regression and not multiple regression, will we only have step 1? If not, where does step 2 come from? Under model are we supposed to have a 1 and a 2? Also, for the write up, are we supposed to make up a hypothesis? And should we refer to the table, even though in step one we have not made it to the table yet? Also, is there a certain order that the write out has to be in in reporting B, p, R, etc.? On the table are we not supposed to report the weight in pounds, and in the example handout out why does the education variable appear twice? I am not sure that I computed the correlation part right. Are we to do it like the bivariate example or should we do it differently since there are more than 2 variables? I know this is a long question but I have a hunch that there are other people out there wondering about the same things? Thanks so much for taking the time to answer!

Table

I'm pretty confused as to how to make the table.

How do you make the table? As in, do you export it from the SPSS to Word and then make changes, or do I have to make it from scratch in Word? If there is a way to export the data from SPSS into Word in the table form, how do you do that?

Thanks.

"Write Up"

In writing up the results "appropriately for an APA journal" is it okay to follow the outline exactly as given in class or is that plagiarism? I know there is a certain way, so is following exactly as one of the slides in the handout plagiarizing or simply just doing it "the" way? Thanks for your help!!!

Thursday, October 23, 2008

Table size

Does an APA formatted correlation table stretch out the entire page, or the size of table vary according to the amount of numbers we are putting in? Thanks.

Correlations table question

When we're computing the correlations table for question number 3, should we add the variable age into the table or only use the three variables we used in computing our linear regressions?
Thanks,
Andrew

opening spss dataset on portico

hey y'all,
if you're having trouble opening the spss dataset for your homework from portico, make sure when you click on it, you just open it directly instead of save to open. because if it saves, you won't be able to access it once it downloads and saves. if you still can't access it, email Dr. Clements and she will email you the dataset. good luck!

Weekly Review/Consolidation Sessions

The weekly review and consolidation sessions will be at 5 p.m. on Mondays in room 126, starting this Monday (10/27).

My apologies to those of you for whom this time does not work. Unfortunately, there was no time that worked for everyone who wanted to attend.

Wednesday, October 22, 2008

Regarding Final Project

This is really far from the due date, but I was wondering if I can hand in the final project earlier than Dec 11? I don't think I will be able to hand it in a week ahead, but probably within the week that it's due. Will that be okay with you, Dr. Clements, or will you prefer it later?

Thanks.

What is the F?

Hello. I'm going through my notes and trying to drill Monday's lecture into my head and just came across the "F" in the ANOVA section. Unfortunately, I didn't write any notes on what this actually means and was wondering if there was a quick and easy way of defining it, its significance to the regression and the importance of reporting it? (I looked through both sets of notes and didn't see it, so I apologize if it's a matter of simple oversight).

Tuesday, October 21, 2008

Linear Regression Homework

The linear regression home work, the data set, and the pseudonym list have all been posted on Portico.

We will talk more in class about how to write up a regression (beyond just what stats to include) on Thursday.

Monday, October 20, 2008

Content question

For Major Findings, do we only have to report findings that are related to the hypotheses only? The authors of the article I have chosen included data about the scale they used in the research study, do I have to include them in my article review? Thanks.

Saturday, October 18, 2008

APA question - author's name

One of the authors of the article I am reviewing is listed as "Nancy Jo Dunn".  The other authors are listed by their first name, initial, and last name, such as "Nancy J. Peterson" and "Sara D. Bailey".  Since it appears that Nancy Jo may be her first name, and Jo is not her middle name, should I list her as "Dunn, N." or as "Dunn, N. J." ?  Or since it is not hyphened as "Nancy-Jo" should I assume Jo is her middle name?

Question on Article Review

I was reviewing the previous article review that we got back, and saw that I was asked to add in "values" under Major Findings. I was wondering what kind of values are being asked for, because there's no example of that in the empirical article summary outline...

Thanks.

Exam 1 is at the Front Desk

The first exam has been graded. A curve was applied, but it resulted in very small changes to scores. [I curve scores by setting the highest score in the class--in this case, 98--equal to 100. Every person's score is divided by the highest score and then multiplied by 100. So, if someone had made, for instance, a 49 on the exam, the curved score would be 50: (49/98) * 100 = .5 * 100 = 50.]

You may go to the front desk to look at your exam. You may not take the exam with you. However, on each person's exam is taped a list of things to review for the final. This list is based solely on the items missed on this exam.

The indicators of central tendency for this exam are as follows:
Mean = 88 (B+)
Median = 90 (A-)
Modes = 88 (B+), 92 (A-), and 94 (A-)

I'm still working on some item analysis, and although I can tell you that it looks like each item was answered correctly by the majority of the class, I will review in class any items that a substantial minority missed.

You are always welcome to come discuss your exam with me--just sign up for a time on my office door.

Friday, October 17, 2008

review session time for the next quiz! PLEASE RESPOND!

hi friends! Dr. Clements and the TAs are trying to figure out when the best time is to have the review sessions for the next quiz to best prepare you guys. the next quiz is on thursday, nov. 13th, so we will be having a review session that tuesday and wednesday. some students had indicated that your cohort generally got out of class earlier on tuesdays, and so let us know what are good times to meet so that commuters who want to attend the session would not have to stay around school for an extra 6 hours. also, now having taken the quiz, let us know whether the format and depth of the review session (going through the study guide item by item with application questions) were informative to helping you prepare for the actual quiz, and if there’s anything you’d like to see us do or change to better equip you for the next exam.

so respond:
1. good times for the tuesday review session
2. good times for the wednesday review session
3. feedback/suggestions for review session

spacing between sentences???

Ok, I double spaced between sentences on my last article review and they're all circled! We're only supposed to single space between sentences??? The examply clearly looks double-spaced..

Thursday, October 16, 2008

Reference - Title capitalization

The title for a book chapter is "Spiritually Oriented Cognitive-Behavioral Therapy." Do I cite this as:

1) Tan, S. Y., & Johnson, W. B. (2005). Spiritually oriented Cognitive-Behavioral Therapy.

2) Tan, S. Y., & Johnson, W. B. (2005). Spiritually oriented Cognitive-behavioral Therapy.

3) Tan, S. Y., & Johnson, W. B. (2005). Spiritually oriented Cognitive-Behavioral therapy.

4) Tan, S. Y., & Johnson, W. B. (2005). Spiritually oriented cognitive-behavioral therapy.


Thank you!

Wednesday, October 15, 2008

Questions from Review Session

1. Will students be asked to produce the formulae for central tendency and dispersion?
---
No, but you might well be asked to recognize them. My advice would be to understand what each measure does and how they differ from one another rather than rotely memorizing symbols. That is, if you understand conceptually what a standard deviation is and how it differs from variance or SE or SS, you should recognize its formula. Such recognition and understanding will be infinitely more useful to you in both the long- and short-term than simple memorization.

2. What is the unit of the standard error?
---
The unit of the standard error is the original unit of measurement in the data set. Remember that the standard error provides an estimate of the precision of the mean. Said in another way, the SE defines the range around the sample mean in which the population mean is likely to lie. If the SE is large, your estimate of the mean is not very precise.

Imagine, for instance, that the obtained mean of all your grades in a given course was 91. If the standard error of that estimate were 1/2 point, you'd be feeling pretty confident about how much knowledge you really obtained. If, on the other hand, the SE were 50, this estimate of 91 could be very different from the true measure of your knowledge in the class. With a small standard error, we are more hopeful that our obtained mean more closely (a) represents the sample data and (b) approximates the population parameter.

3. What is the proper notation for population parameters and sample statistics?
---
As noted in class, population parameters are typically indicated using Greek letters (which, by APA style guildelines, are never italicized) and sample statistics are indicated using italicized Roman letters. There are a few exceptions to this general rule, but we have not yet covered any of those exceptions.

Question on formulas

It would be helpful to me if the formulas for variance, sum of squares, standard deviation, and standard errors could be put into words. I would also appreciate clarification as to what each symbol in the formula means.

Tuesday, October 14, 2008

Study Guide for Exam 1

The study guide for exam 1 is now posted on Portico. The TAs will have copies of it at the review sessions as well.

Location for Study Session

The Tuesday night review session will be at 6 p.m. in Room 314 in the Psych Building.

The Wednesday night review session will be at 6 p.m. in Room 311 in the Psych Building.

Monday, October 13, 2008

Printed Output

Is it ok to copy the data into a smaller format so it won't use so much paper? I have already exported it to Word and all looks good (a bit different presentation due to formatting differences) or do you require the original output? Also, do you want the data file in its entirety to show the z-score calculations?

Z-Scores, Part II

I'm a little confused as to what rolls we're supposed to compute the z-scores for in question 2. Are we supposed to use the rolls from Group 1?

Z-score calculations

I am having trouble setting up SPSS to calculate the z-scores for the specific rolls. I can do all this manually but would prefer to do it the "easy" way. What i have done so far is calculate the means for die1, die2, and the total for each of the 6 rolls. With this done, which variables do i choose when creating the z-scores? Am I at least on the right track? If not, what direction should i take? I know where i want to go but am not sure how to get there. A little help please :-)

Saturday, October 11, 2008

number format

For the homework assignment, do we have to put our answers in a specific format? For instance, if an answer that I got from SPSS was 1.234, do I need to put 1.23? Or if an answer was 3, do I have to put 3.0 or 3.00? Thanks.

Clarification

I have a question on our first assignment. Question 3A and 3E are highly similar, I would like to know what specific things we should focus on when we are answering them. Thank you.

Friday, October 10, 2008

SPSS Grad Pack 17.0

I just received the following email from a supervisor at the bookstore:
---
Some of the students in your linear regression class have been patiently asking when SPSS Graduate Pack 17.0 will arrive at the bookstore. We ordered copies of the program almost 2 weeks ago but it has not yet arrived.

When we called SPSS this morning about the delay, we were surprised to learn that while the Professional Pack 17.0 is available, the Graduate Pack is not yet available. Although we will carry the Graduate Pack when it is shipped, SPSS unfortunately does not know when the Graduate Pack will be ready.

I thought this information might be of use to you and your students.
---
This is, of course, concerning news, and I am dreadfully sorry that it is affecting you.

There are several options available. You could use the software in the library/computer labs. You could purchase an earlier version of the software from another source (online, for instance). You could use the computer of a colleague in the class who owns a previous version of the software. You could use the computer of an advanced student who owns a previous version of the software.

Thursday, October 9, 2008

Z-scores (NOTE NEW ANSWER)

In question 2 of our descriptive homework, we are asked to calculate the z-scores of numbers 1 through 6 based on the data garnered from question 1. This works for die1 and die2, but as for the total, shouldn't we instead find the z-scores from numbers 2 through 12? The table is only set up from 1 to 6, so should we just write in the z-scores from 2 to 12 instead?

Review Sessions Tuesday and Wednesday at 6 p.m.

The first exam is rapidly approaching. . .

Descriptive Homework

The dataset (and an electronic copy of the assignment) are posted on Portico. Log in, select the My Courses tab, choose Files from the menu on the left, and download the SPPS data file.

Wednesday, October 8, 2008

Title Page?

I know this is late but does anybody know if we turn our article review just as Dr. Clements has or do we put a title page?

APA format question

I cannot find any information concerning the use of a title in an article critique? Is there such a thing or do we just put "Article Critique" as the title?

What's in a pseudonym...

Hello. I was trying to figure out where to put my name for this assignment since we won't be using a cover page (where it would normally be). I'm assuming in the upper right hand corner? Also, can you (Mari, TAs, anyone) give a little more information on the use of a pseudonym and how this will work out when you hand the assignments back out to us? Gracias.

That's Average?!?

Okay, this has nothing to do with how well any of us learn GLM, but, as a former eating disorder research assistant (Chris, feel free to jump in), I think Dr. Clements' hubby's standards for "average" are, wow.

Monica Sales is average? (Face may not be perfect, but great Dancing With the Stars body).

An actress/comedian who's "bit" is being "average" and talking about the frustrations as such: Genine Garofalo.

Genine's talked about how she's always 30 pounds heavier between movies, they give her parts with it in her contract that she first has to lose the pounds, and then "she sells out" (her words) and loses this weight to secure the part.

I also love her comedian act that talks about women eating muffin tops as being a sign of having an eating disorder (as she rips off a muffin top and bites into it).

Anyways, averages in stats are more about mean, mode, median (or actually just means), but, there go my morning thoughts.

Hope all's well in "journal analyzing land."

(The profs at Fuller have a lot of cool empirical studies they've published.)

God bless to all (big, small, gorgeous, "ugly", and average),
-Ramona

article review question: population

hello, i have a question regarding the article review:

the article i am using is a theoretical article, and it looks at a lot of general pictures with very little number crunching. if the authors are primarily using references to other works to support their argument (like saying "this person's study showed that 10% of these people are likely to ____"), and cites a lot of these types of examples, would i have to include all of them in the "Population from Theory was Developed" section of the article review, even if some of them don't actually go into specifics about the sample/population sizes? or should they even go in that section because the authors did not primarily interact with those populations? thanks!

Friday, October 3, 2008

Blogger invitation errors

One of the students in the class who had been having repeated difficulties signing in to blogger sent the following advice for anyone else who has experienced this difficulty:

Hello, I think I figured out what was causing the error, and here is how I got the registration to work - Basically, the link you sent us is the sign-in screen for blogger. It was asking if you have a google account or not, but what you have to do is click on the "create account" anyway, even if you have an existing google account. Then, when you go into the "create account", it will display your google account, and ask you what your blogger username will be, and once you register that name, it will register you into the blogger. I hope this might help.

I re-sent invitations again at ~4 p.m. this afternoon to those who still had invitations pending...

Thursday, October 2, 2008

Resources for Article Reviews

Are posted on Portico. Click on the "My Courses" tab, then select "Gen Linear Model: Regression," then select "Files."

The Article Summary Outline (that includes an embedded example) is a Word document, and the list of faculty recommendations for research articles is a pdf file.

Monday, September 29, 2008

Congratulations, You Found It!

Welcome to the blog for PG850: General Linear Models--Regression.

This blog is to be used for asking, clarifying, discussing, and checking out. No asked question is "dumb," but unasked questions may well hurt you.

The use of the blog is not intended to stigmatize those asking questions (or those who don't), but is necessary to ensure that all of us who will be evaluating your work are on the same page about the things that are seen as confusing AND about the answers you've received. To that end, it is to your advantage to check the blog while completing homework assignments and the final project.

Having said that, there are a few important ground rules for the class:

1. Do not email or call the TA or the instructor directly. Any questions submitted "back-channel" will be posted and answered on the blog. You will not receive an email or phone response to questions. This is the first and most important ground rule for the class. Although I am sympathetic to the desire not to be embarrassed by asking a question "in public," it is absolutely necessary that we do it this way for three important reasons. First, if you have a particular question, chances are at least one other person (and maybe 41 other people!) have that same question. It is much better for all of us if the question gets answered once rather than 41 times. Second, it is critical that I and the TAs are on the same page with our answers to all of you, and we can't be certain of that unless we see every question and every answer. That is, it is possible that I would answer one aspect of a given question, Kelly would answer a second aspect, Kris a third, Justin a fourth, and Ann a fifth. Although all answers would be potentially helpful, if I am looking for a particular thing in an answer, I need to know that you have actually heard that particular thing in response to your question. Third, an important part of your professional development is learning how to work together and how to constructively offer help/feedback. I expect that all of us--not just the TAs and I--will be working to increase knowledge and facilitate learning in this class.

2. Do not wait until the last minute to answer your question (and closely related 3. Do not be impatient for an answer). Unfortunately, if you wait until the hour before your homework is due to begin working on it, there may not be time for an answer to be posted to the blog before you need it. Similarly, it is unlikely that the blog will be checked very late the night before an assignment is due. Please plan ahead, because even if you call the TA or me in a panic right before class, ground rule #1 applies.

3. Do not be impatient for an answer. I understand that it can be very anxiety provoking to not know the answer to your question. Please have faith that the TAs and I have a schedule for checking and responding to the blog and that your question WILL be answered. One year, I had a student who became very worried that the question posed on the blog had not been answered. Imagine my surprise to find out that the question had been posted for less than an hour! We do check the blog and we will respond, but fortunately for us all, no one is permanently subscribed to the blog.

4. Blog and respond to others as you would have them do unto you. This goes without saying, but just in case someone is still worried about posting on the blog, the goal is to help you improve your stats knowledge, to help you figure out the question you have, and to help you move forward. Posts that are failed attempts at sarcastic humor or otherwise come across negatively will be removed by a moderator.