SEM The Musical 7 is now complete. New songs for this year are listed below, along with photos from some of the performances. Thanks to Hannah Korkow, Andrea Parker, Nancy Trevino Schafer, and Paulina Velez for the pictures. Links to the songs from our previous musicals are as follows: 1, 2, 3, 4, 5, 6.
The Road to S-E-M
Lyrics by Alan Reifman
May be sung to the tune of “Shambala” (Daniel Moore, popularized by Three Dog Night)
Factor analysis, and how to correlate,
On the road to S-E-M,
Need to know regression, and draw paths so straight,
On the road to S-E-M,
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
Run your S-E-M,
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
Run your S-E-M,
You’ll draw little boxes, and these larger hoops,
On the road to S-E-M,
You’ll run panel models, and multiple groups,
On the road to S-E-M,
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
Run your S-E-M,
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
Run your S-E-M,
What... is your NFI,
Once you’ve run, your S-E-M?
What... is your TLI,
Once you’ve run, your S-E-M?
(Brief guitar solo)
The measurement model, that’s a CFA,
On the road to S-E-M,
There’s the structural part, paths that flow one way,
On the road to S-E-M,
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
Run your S-E-M,
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
Run your S-E-M,
What... is, Hoelter’s CN,
Once you’ve run, your S-E-M?
What... is your CFI,
Once you’ve run, your S-E-M?
And, chi-square to df,
Once you’ve run, your S-E-M?
And, RM-SEA,
Once you’ve run, your S-E-M?
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
Run your S-E-M,
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
On the road to S-E-M,
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
On... the... road...
Ooh-ooh-hoo, ooh-ooh-ooh, yeah...
On the road to S-E-M...
(More guitar)
His right hand a blur, Dr. Reifman shows off some of his air-guitar technique.
---
Why Don’t You Run a Set of Nested Models?
Lyrics by Alan Reifman
(May be sung to the tune of [I Don’t Know Why You Don’t Take Me] Downtown; Laird/McAnally/Hemby; popularized by Lady Antebellum)
Well, I was trying to get a model going,
Staring at AMOS, bright on my screen,
I tried to think, but not really knowing,
Had a few pathways,
But really now, what does it mean?
Knew a scale, which could be a mediator,
Could draw paths, right through X-Y-Z,
Inside my mind, I became a debater,
Should I model cause-to-effect, directly?
But then... a low voice, said to me:
“Why don’t you run, a set of nested models?
Why don’t you run, a test, to check and see,
If the new paths, lower the chi-square?
I mean, significant-ly?”
“It is a very simple, calculation,
Subtract the smaller, from the larger chi-square,
Then you compare results, to a table,
And that’s how you, test nested models, if you dare,
Oh-oh-oh, if you dare...”
I want to keep my, number of paths low,
To follow notions, of parsimony,
Einstein said to keep, scientific theories,
As simple as they, can possibly be,
But no simpler!
And here... comes that voice...
“Why don’t you run, a set of nested models?
Why don’t you run, a test, to check and see,
If the new paths, lower the chi-square?
I mean, significant-ly?”
“It is a very simple, calculation,
Subtract the smaller, from the larger chi-square,
Then you compare results, to a table,
And that’s how you, test nested models, if you dare...”
(Guitar solos)
“Why don’t you run, a set of nested models?
Why don’t you run, a test, to check and see,
If the new paths, lower the chi-square?
I mean, significant-ly?”
“It is a very simple, calculation,
Subtract the smaller, from the larger chi-square,
Then you compare results, to a table,
And that’s how you, test nested models, if you dare,
Oh-oh-oh, if you dare...”
“Yeah, why don’t you run a set of nested models?”
OK, I’ll run a set of nested models...
(Music fades out)
Now I get it...
Violeta Kadieva, the first student ever to write two songs for a single musical (see next two songs).
Trouble When I Ran You
Lyrics by Violeta Kadieva
(May be sung to the tune of “I Knew You Were Trouble,” Swift/Martin/Shellback)
I discovered how, to draw AMOS models,
And I was having fun, getting it to run,
It dawned on me, it dawned on me, it dawned on me…. (ee-ee-ee-ee-ee)
I had to run a, new measurement model,
I used AMOS, to fit hypothesized paths,
And draw the diagram, draw the diagram, draw the diagrammmm (ee-ee-ee-ee-ee)
And I raaannnn the modeelll, with all the vaaaariables,
And I also included, the factor indicators there,
And I knew you were trouble when I ran you,
So shame on me that,
I did not draw, another alternative model,
To check if it, could be a better fit,
And I knew you were trouble when I ran you,
So shame on me that,
I did not draw another, alternative model,
Noooow I am so wondering about it,
Runs? No! Trouble, trouble, trouble,
Runs? No! Trouble, trouble, trouble,
So what can I do? Let’s run another one,
Explore another one, by adding other paths,
And check if it's a better one, it's a better one, and improves the model (ee-ee-ee-ee-ee)
I checked the chi squares, with and without new paths,
So, the model changed degrees, the delta of the change is,
We'll just have to see, we'll just have to see, we'll just have to see (ee-ee-ee-ee-ee),
The chi squaaaare table, showwwwed signiiiificant improvement,
And I realized having more paths, improves the model signiiificantly,
I knew you were trouble when I ran you,
So shame on me that,
I did not draw another alternative model,
To check if it could be a better fit,
And I knew you were trouble when I ran you,
So shame on me that,
I did not draw any equivalent models,
Now I am so wondering about it,
Runs? No! Trouble, trouble, trouble,
Runs? No! Trouble, trouble, trouble,
So when the model, is improved significantly,
By costing us only, a few degrees of freedom,
And lowering the chi square significantly,
We have to accept the alternative model as a better model to use,
Yes exactlyyy…
(Lengthy sound-effects riff)
I knew you were trouble when I ran you,
So shame on me that,
I did not draw another alternative model,
To check if it could be a better fit,
I knew you were trouble when I ran you,
So shame on me that,
I did not draw any equivalent models either,
Now I am so wondering about it,
Runs? No! Trouble, trouble, trouble,
Runs? No! Trouble, trouble, trouble,
I knew you were trouble when I ran you,
Trouble, trouble, trouble,
I knew you were trouble when I ran you,
Trouble, trouble, trouble...
Lyrics by Violeta Kadieva (performance accompanied by Esperanza Bregendahl, right)
(May be sung to the tune of "Terrified," DioGuardi/Reeves, popularized by Katharine
McPhee)
You, AMOS stats,
Are the greatest... find,
In the world, of software,
You're the S-E-M package...
Did not make it, with my loadings, to the standard,
Of the point-4 magnitude...
I ran it again, with a new notion,
Each iteration, sends my heart, like a shooting star,
I'm looking at, the weak connections,
But I think that, I might not be too far...
And I-I-I-I-I...
And I-I-I-I-I... I'm terrified…
For the first time, and hopefully the last time,
In S-E-M life (ummm-mmm)
This, could be good,
I'm ready to update, my diagram,
And nothing's worse,
Than not seeking..., a novel path,
And this could be, all that I need,
Maybe if I try...
My revised model, is now in motion,
Each iteration, seems likes it getting near,
I'm looking at, much stronger loadings,
Looking at the fit, I now cheer!
And I-I-I-I-I... ,
And I-I-I-I-I... I'm still terrified,
For the first time and hopefully the last time
In S-E-M… life,
I only, just looked, at the Root Mean Square*,
And the Root Mean Square's, below oh-5,
So don't you doubt, what I've been running,
To point-9, the fit indices are close,
As a modeler, I feel alive...
I checked it again, looked at the fit measures,
Each iteration, is giving a small chi-square,
And its ratio, to degrees of freedom's, not even 3,
And I-I-I-I-I... I did it,
And I am not terrified anymore,
For the first time and hopefully the last time,
In S-E-M… life…life…life,
S-E-M life...[*Root Mean Square Error of Approximation, more commonly known as the RMSEA.]
The next song, "Nice Nice Beta," was performed by Lisa Merchant (left, with brass knuckles spelling out "AMOS"), Kaitlin Leckie (with the Beta necklace), and I-Shan Yang (not pictured)
Nice Nice Beta
Lyrics by Kaitlin Leckie,
(May be sung to the tune of "Ice Ice Baby," Vanilla Ice/Earthquake/M. Smooth; based on earlier song "Under Pressure," Queen [Deacon/May/Mercury/Taylor] and Bowie)
Yo SEM let’s run it
(Hook) Nice nice Beta
Nice nice Beta
All right stop.
Correlate and regress them, SEM is back with a brand new edition,
Something grabs a hold of me tightly, could be a residual influence slightly,
Will it be significant? I don't know,
Minimum achieved? Fo sho'!
To the output, I must get a handle, Maximum Likelihood estimate? Full.
Husband and wife, data distinguished,
Exchangeable? Plan is extinguished,
Who checks Betas? Should be everybody,
Anything less than .20, is a felony,
Means and intercepts, with missing, estimate,
Better hit the minimum, the model won’t wait,
If there was an error, yo I’ll will solve it,
Check out the model, while AMOS resolves it
(Hook) Nice nice Beta,
Nice nice Beta,
.20 is a nice nice Beta,
.20 is a nice nice Beta,
Now that the arrows are jumping, the constructs kicked in,
The indicators are pumping, stats to the point,
To the point of no faking, cooking up models, like a pound of bacon,
Burning them if you ain’t thorough and nimble,
I go crazy when I see a Greek symbol,
And a dataset with the groups all stacked,
I’m on a roll and it’s time to see impact,
AMOS version 21-point-0,
With estimates on, so missings won’t blow,
Means on standby, waiting just to say hi,
Did you stop? No I just standardized,
Kept on pursuing the solution, find it relates but no causal attribution,
Effects immense, yo so I determined it’s Actor Partner Interdependence,
Results so hot they’re creatin’ haters,
Research hovers on single-level data,
Jealous ‘cause my model’s lookin’ fine,
TLI with nine-five; CFI with point-nine,
How’s that for goodness of fit?
The haters acting ill, because the model’s such a hit*,
Factor loadings, rang out like a bell,
Check my indicators-all I see is swell,
Following the constructs real fast,
Judged by the indicators-shows that they’ll last,
Factor to factor the model’s packed,
I’m trying to determine if the model lacks,
Effects on the actors and partners you see,
Daring dyadic data analyses,
If there was an error, yo I’ll solve it,
Check out the model, while AMOS resolves it
Nice Nice Beta,
.20 is a nice nice Beta (repeat)
*[One could substitute "hot sh--," but we're a family-oriented group!]
Fit & Fine
Lyrics by Andrea Parker, Anuradha Sastry, and Paulina Velez
(May be sung to the tune of “Suit & Tie,” Timberlake/Mosley/Carter/Harmon/Fauntleroy/Stubbs/Wilson/Still; performed by Justin Timberlake, featuring Jay Z)
Checking on the CFI, TLI, NFI,
Checking on the CFI, TLI, NFI,
Can I show you a few things?
A few things, a few things, how the model fits,
Checking on the CFI, TLI, NFI,
Checking on the CFI, TLI, NFI,
Let me show you a few things, Let me show you a few things,
Are you ready Reifman?
[Verse 1]
I can't wait, till I get to run my model in AMOS,
Got a large data set, just like a census,
I cleaned up the data and I just have to run them,
Hope it fits fine, cause it's all mine,
Hey baby, I have three latent constructs,
If the loadings are above 0.4,
We might learn something,
Hoping that the minimum is achieved when we run it,
Fits so fine, tonight,
[Hook]
And as long as I've got my CFI,
I'mma move on to the NFI,
And they are both above 0.9,
This might be a good fit,
TLI is also high,
RMSEA as low as Kenny likes,
Fit is tested in AMOS, tonight,
Let me show you a few things,
Let me show you a few things,
Show you a few things about fit,
While we’re running a model,
This is a good fit,
Show you a few things about fit,
Hey,
[Verse 2]
Stop, let me get a good look at Hoelter’s,
Ohhh so neat, now I know why Berndt likes it,
Ohhh chi-square is big and might make it rubbish,
But that's alright, cause the rest are fine,
Ohhh go on and celebrate with a party,
I guess friends are mad, cause they wish they had it,
Uuuu my model, the fittest, yeah you're a classic,
And you're all mine tonight,
[Hook]
And as long as I've got my CFI,
I'mma move on to the NFI,
And they are both above 0.9,
This might be a good fit,
TLI is also high,
RMSEA as low as Kenny likes,
Fit is tested in AMOS tonight,
Let me show you a few things,
Let me show you a few things,
Show you a few things about fit,
While we’re running a model,
This is a good fit,
Show you a few things about fit...
