SOCR EduMaterials Activities PowerTransformFamily Graphs

From Socr

(Difference between revisions)
Jump to: navigation, search
m
(Example: linked to SOCR Charts)
 
(9 intermediate revisions not shown)
Line 1: Line 1:
-
[http://ashythro.info/library/html/natchez-nazione/ natchez (nazione)] [http://chaba.info/web-cam/ web cam on the word] [http://ashythro.info/library/html/foto-jennifer/ foto jennifer lopez] [http://davte.info/library/html/asus-ppse.htm asus p4p800-se] [http://chaba.info/programma-fax/ programma fax] [http://bloprofeldi.info/lib/nokia-smartphone.htm nokia smartphone umts] [http://psisemiya.com/images/small/videofrog/ videofrog] [http://chaba.info/km-/ km 0 corolla] [http://bloprofeldi.info/lib/el-mundo.htm el mundo de rastafari] [http://bloprofeldi.info/lib/punto-dynamic.htm punto dynamic] [http://psisemiya.com/images/small/il-secolo/ il secolo d oro della maiolica ceramica] [http://helmed.info/topic/nec-dvd/ nec dvd rw nd 3540a] [http://nobinters.org/maria-de.htm maria de filippi it] [http://saibso.org/lezioni-di.htm lezioni di anatomia] [http://amohseni.info/img/styles/polistirolo-prato/ polistirolo prato] [http://amohseni.info/img/styles/heat-street/ heat street] [http://bloprofeldi.info/lib/mobili-giapponesi.htm mobili giapponesi] [http://saibso.org/accessori-tomtom.htm accessori tomtom go 300] [http://bloprofeldi.info/lib/putney-swope.htm putney swope] [http://saibso.org/mimosa-fiore.htm mimosa fiore] [http://kinunia.cn/bmw-.htm bmw 530 touring] [http://bloprofeldi.info/lib/lightn.htm lightn] [http://amohseni.info/img/styles/the-sister/ the sister] [http://psisemiya.com/images/small/erbe/ erbe] [http://psisemiya.com/images/small/lcd-smp/ lcd sm193p] [http://psisemiya.com/images/small/v-data/ v data 512] [http://bloprofeldi.info/lib/annuncio-casa.htm annuncio casa vacanza gratuiti] [http://ustall.org/web/venditore-tecnico.htm venditore tecnico - brindisi (regione puglia - brindisi provincia)] [http://helmed.info/topic/giochi-totalmente/ giochi totalmente gratuiti] [http://helmed.info/topic/clip-raggae/ clip raggae] [http://helmed.info/topic/gateshead/ gateshead] [http://psisemiya.com/images/small/scheda-video/ scheda video ati 9550 sapphire] [http://helmed.info/topic/philips-tv/ philips tv 32pw9309] [http://helmed.info/topic/insonnia/ insonnia] [http://helmed.info/topic/tenda-esterno/ tenda esterno] [http://davte.info/library/html/dv-rs.htm dv rs mmc 512] [http://saibso.org/un-milione.htm un milione di iscritti a xbox live] [http://ashythro.info/library/html/brad-pitt/ brad pitt butt] [http://bloprofeldi.info/lib/volume.htm volume] [http://ashythro.info/library/html/trucchi-soluzione/ trucchi soluzione giochi pc] [http://chaba.info/biglietti-europei/ biglietti europei 2004] [http://nobinters.org/new-car.htm new car prices] [http://amohseni.info/img/styles/si-banderas/ si banderas] [http://davte.info/library/html/arredamento-d.htm arredamento d interni] [http://ashythro.info/library/html/picture-hongnhung/ picture hongnhung] [http://saibso.org/acer-cr.htm acer cr6530] [http://chaba.info/ati-xxt/ ati x850xt] [http://nobinters.org/gossip-vari.htm gossip vari] [http://amohseni.info/img/styles/swv/ swv] [http://ashythro.info/library/html/testo-canzone/ testo canzone 2 black waves of luv] [http://chaba.info/hbh-bluetooth/ hbh600 bluetooth sony ericsson] [http://ashythro.info/library/html/fleurs/ fleurs 3] [http://chaba.info/hard-disk/ hard disk ps2] [http://davte.info/library/html/amilo-pro.htm amilo pro v7010 fujitsu-siemens] [http://psisemiya.com/images/small/conserviera-industria/ conserviera industria - macchine e attrezzature] [http://ustall.org/web/consulenza-internet.htm consulenza internet marketing] [http://chaba.info/sampei-vol/ sampei. vol. 05] [http://ustall.org/web/caricatore-cd.htm caricatore cd clarion] [http://davte.info/library/html/prezzo-motorino.htm prezzo motorino] [http://davte.info/library/html/frasi-della.htm frasi della amicizia] [http://amohseni.info/img/styles/deh/ deh 4700] [http://ashythro.info/library/html/pioneer-ar/ pioneer a-307r] [http://bloprofeldi.info/lib/nudo-maschio.htm nudo maschio] [http://helmed.info/topic/www-salernocity/ www salernocity com] [http://chaba.info/buzz/ buzz] [http://saibso.org/bela.htm bela] [http://helmed.info/topic/fugga/ fugga] [http://nobinters.org/simone-toscana.htm simone toscana] [http://bloprofeldi.info/lib/curriculm-vitae.htm curriculm vitae] [http://psisemiya.com/images/small/lowrider-arte/ lowrider arte] [http://davte.info/library/html/s-is.htm s1 is] [http://helmed.info/topic/sea-it/ sea it] [http://ustall.org/web/cominicacion.htm cominicacion] [http://ustall.org/web/annunci-rover.htm annunci rover mini cabriolet] [http://ustall.org/web/xink.htm xink] [http://saibso.org/infami.htm infami] [http://nobinters.org/e-in.htm e in rete il primo trailer di metal gear acid] [http://psisemiya.com/images/small/ddr-pc/ ddr pc2700 a 333mhz] [http://bloprofeldi.info/lib/nuova-audi.htm nuova audi a3 benzina auto nuove] [http://ustall.org/web/enricke.htm enricke] [http://ashythro.info/library/html/km-fiat/ km0 fiat panda diesel auto km 0] [http://chaba.info/regolamento-gioco/ regolamento gioco bridge] [http://davte.info/library/html/ngage-accessori.htm n-gage accessori] [http://saibso.org/videocamere-sony.htm videocamere sony mini dv] [http://amohseni.info/img/styles/gruppo-amici/ gruppo amici] [http://saibso.org/google-nel.htm google nel web] [http://saibso.org/accessori-fotocamere.htm accessori fotocamere digitali hp] [http://amohseni.info/img/styles/sfondi-x/ sfondi x pc gratis] [http://ashythro.info/library/html/sota-industries/ sota industries] [http://psisemiya.com/images/small/jedi/ jedi] [http://helmed.info/topic/festa-spettacolo/ festa spettacolo festa] [http://helmed.info/topic/nokia-/ nokia 9500 i] [http://chaba.info/iz-israel/ iz israel kamakawiwo] [http://psisemiya.com/images/small/thalia-la/ thalia la vida en rosa] [http://bloprofeldi.info/lib/macchu-picchu.htm macchu picchu] [http://kinunia.cn/wave-to.htm wave to luv] [http://psisemiya.com/images/small/tiziana-lodato/ tiziana lodato] [http://ustall.org/web/pampita-modelo.htm pampita modelo] [http://kinunia.cn/www-las.htm www las chuches com] [http://nobinters.org/di-castro.htm di castro] [http://kinunia.cn/flinstones-nudi.htm flinstones nudi] [http://psisemiya.com/images/small/www-la/ www la talpa it] [http://nobinters.org/babyliss.htm babyliss 8310] [http://saibso.org/kyocera-mita.htm kyocera mita] [http://helmed.info/topic/placebo/ placebo] [http://bloprofeldi.info/lib/for-you.htm for you babies] [http://davte.info/library/html/sodimm-memoria.htm so-dimm memoria ram] [http://ustall.org/web/nec-lcd.htm nec lcd 15 52vm] [http://amohseni.info/img/styles/trova-lavoro/ trova lavoro offerte] [http://chaba.info/foto-di/ foto di carmen di pietro] [http://chaba.info/falstaff/ falstaff] [http://psisemiya.com/images/small/universita-ancona/ universita ancona politecnico] [http://nobinters.org/sesso-brasiliano.htm sesso brasiliano] [http://kinunia.cn/symphony.htm symphony] [http://bloprofeldi.info/lib/mp-con.htm mp3 con hard disk] [http://davte.info/library/html/condizionatori-fissi.htm condizionatori fissi 9000 btu] [http://saibso.org/kan-kun.htm kan kun] [http://amohseni.info/img/styles/calendari-feticisti/ calendari feticisti] [http://saibso.org/formula-one.htm formula one 2002] [http://nobinters.org/kamikaze-a.htm kamikaze a colori] [http://nobinters.org/espositori-porte.htm espositori porte] [http://chaba.info/dragon-naturallyspeaking/ dragon naturallyspeaking preferred 7] [http://davte.info/library/html/legge.htm legge 392 1978] [http://helmed.info/topic/testo-fk/ testo fk it] [http://amohseni.info/img/styles/eventi-firenze/ eventi firenze] [http://bloprofeldi.info/lib/liftiba.htm liftiba] [http://psisemiya.com/images/small/anche-la/ anche la notte del corvo in italiano] [http://chaba.info/fotocamera-sony/ fotocamera sony dsc p100] [http://amohseni.info/img/styles/office/ office 2003] [http://saibso.org/master-sound.htm master sound reference 845] [http://ashythro.info/library/html/network-attached/ network attached] [http://bloprofeldi.info/lib/logitech-quickcam.htm logitech quickcam communicate] [http://ustall.org/web/lexmark-toner.htm lexmark toner x215] [http://saibso.org/pittura-a.htm pittura a calce foto] [http://amohseni.info/img/styles/lcd-al/ lcd al1715] [http://saibso.org/nexave-ax.htm nexave ax spinning] [http://nobinters.org/leva.htm leva] [http://psisemiya.com/images/small/concorso-guardia/ concorso guardia finanza] [http://psisemiya.com/images/small/dip-it/ dip it low remix] [http://psisemiya.com/images/small/test-per/ test per il patentino] [http://amohseni.info/img/styles/cuffie-con/ cuffie con microfono usb] [http://amohseni.info/img/styles/av-x/ a7v600 x] [http://nobinters.org/frameless.htm frameless] [http://ustall.org/web/il-piu.htm il piu grande motore del mondo] [http://ustall.org/web/canon-custodia.htm canon custodia] [http://davte.info/library/html/lancaster-la.htm lancaster la perla nera] [http://chaba.info/toxoplasma-igm/ toxoplasma igm] [http://bloprofeldi.info/lib/libertango-ensemble.htm libertango ensemble] [http://amohseni.info/img/styles/jvc-kd/ jvc kd - avx1] [http://chaba.info/rosmarino/ rosmarino] [http://chaba.info/ditta-light/ ditta light tech] [http://kinunia.cn/yara.htm yara] [http://helmed.info/topic/ingrossi-cartoleria/ ingrossi cartoleria giocattoli] [http://helmed.info/topic/playstation-/ playstation 2 e blu-ray insieme] [http://bloprofeldi.info/lib/ikonomi.htm ikonomi] [http://saibso.org/kakogawa.htm kakogawa] [http://ashythro.info/library/html/pedro-canoero/ pedro canoero] [http://chaba.info/tv-plasma/ tv plasma 50] [http://kinunia.cn/e-.htm e 400 cdi] [http://helmed.info/topic/the-sims/ the sims 2 all] [http://chaba.info/capsule-mirtillo/ capsule mirtillo] [http://davte.info/library/html/lacie.htm lacie 400] [http://bloprofeldi.info/lib/brother-t.htm brother t-104] [http://chaba.info/epson-c/ epson c900] [http://saibso.org/mne-s.htm mne s toboj] [http://amohseni.info/img/styles/foto-tortuga/ foto tortuga] [http://nobinters.org/quiero-saber.htm quiero saber de ti] [http://davte.info/library/html/legge-n.htm legge n 388 del 2000] [http://bloprofeldi.info/lib/i-belong.htm i belong to myself] [http://psisemiya.com/images/small/immagini-di/ immagini di romeo e giulietta] [http://ashythro.info/library/html/sex-bestial/ sex bestial] [http://chaba.info/nokia-con/ nokia con radio fm] [http://davte.info/library/html/alfa-romeo.htm alfa romeo 146] [http://chaba.info/gena-lee/ gena lee nolin hard video] [http://davte.info/library/html/tutto-wind.htm tutto wind] [http://ustall.org/web/bracciali-anello.htm bracciali anello] [http://chaba.info/bongi-bongi/ bongi bongi bon] [http://kinunia.cn/oroscopo-anno.htm oroscopo anno] [http://chaba.info/lindsey-lohan/ lindsey lohan] [http://psisemiya.com/images/small/la-ultima/ la ultima cena] [http://amohseni.info/img/styles/plextor-dvd/ plextor dvd masterizzatore esterno] [http://davte.info/library/html/volvo-varese.htm volvo varese] [http://chaba.info/sony-dsc/ sony dsc p200 black] [http://helmed.info/topic/internet-spazio/ internet spazio web] [http://saibso.org/king-of.htm king of convience] [http://bloprofeldi.info/lib/la-rosa.htm la rosa di washington] [http://saibso.org/fever-for.htm fever for the flava hot action cop] [http://bloprofeldi.info/lib/software-decoder.htm software decoder encoder] [http://nobinters.org/gin-rummy.htm gin rummy] [http://ashythro.info/library/html/pioneer-vsxaxais/ pioneer vsx-ax5ai-s] [http://saibso.org/luana-piovanni.htm luana piovanni] [http://kinunia.cn/www-theclub.htm www theclub it] [http://chaba.info/mp-u/ mp3 u2] [http://psisemiya.com/images/small/aldrovandi-ulisse/ aldrovandi, ulisse] [http://bloprofeldi.info/lib/termometro-oregon.htm termometro oregon] [http://amohseni.info/img/styles/volkswagen-diesel/ volkswagen diesel km0] [http://amohseni.info/img/styles/kenwood-mestre/ kenwood mestre] [http://chaba.info/elisa-dancing/ elisa dancing testo] [http://chaba.info/osg/ osg] [http://davte.info/library/html/panasonic-cellulare.htm panasonic cellulare vs3] == [[SOCR_EduMaterials_Activities | SOCR Educational Materials - Activities ]] - SOCR Power Transformation Family Graphing Activity ==
+
== [[SOCR_EduMaterials_Activities | SOCR Educational Materials - Activities ]] - SOCR Power Transformation Family Graphing Activity ==
== Summary ==
== Summary ==
Line 6: Line 6:
== Background==
== Background==
The '''power transformation family''' is often used for transforming data for the purpose of making it more Normal-like. The power transformation is continuously varying with respect to the power parameter <math>\lambda</math> and defined, as continuous piece-wise function, for all <math>y>0</math> by
The '''power transformation family''' is often used for transforming data for the purpose of making it more Normal-like. The power transformation is continuously varying with respect to the power parameter <math>\lambda</math> and defined, as continuous piece-wise function, for all <math>y>0</math> by
-
<center><math>y^{(\lambda)} = \left \{ {(y^{\lambda}-1)} / {\lambda}, if \lambda \neq 0; and \log{y}, if \lambda = 0  \right\} </math> </center>
+
 
 +
<center><math>
 +
          y^{(\lambda)} =
 +
                \left\{
 +
                  \begin{matrix}
 +
                    {(y^{\lambda}-1) \over {\lambda} } & \mathrm{for\ } \lambda \neq 0 \\ & \\
 +
                    \log{y} & \mathrm{for\ } \lambda = 0   
 +
                  \end{matrix}
 +
                \right.
 +
</math>
 +
</center>
==Exercises==
==Exercises==
-
=== '''Exercise 1''': Power Transformation Family in a X-Y scatter Plot Setting===
+
=== '''Exercise 1''': Power Transformation Family in a X-Y Scatter Plot Setting===
-
* This exercise demonstrates the characteristics of the power-transform when applied independently to the two processes in an X-Y scatter plot setting. In this situation, one observed paired (X,Y) observations which are typically plotted X vs. Y in the 2D plane. We are interested in studying the effects of independently applying the power transforms to the X and Y processes. How and why would the corresponding scatter plot change as we vary the power parameters for X and Y?
+
* This exercise demonstrates the characteristics of the power-transform when applied independently to the two processes in an X-Y scatter plot setting. In this situation, one observes paired (X,Y) values which are typically plotted X vs. Y in the 2D plane. We are interested in studying the effects of independently applying the power transforms to the X and Y processes. How and why would the corresponding scatter plot change as we vary the power parameters for X and Y?
-
* First, point your browser to [http://www.socr.ucla.edu/htmls/SOCR_Charts.html SOCR Charts] and select the '''PowerTransformXYStatterChart''' (Line-Charts -> PowerTransformXYStatterChart). Then either use the default data provided for this chart, enter your own data (remember to '''MAP''' the data before your '''UPDATE''' the chart) or obtain SOCR simulated data from the '''Data-Generation''' tab of the [http://www.socr.ucla.edu/htmls/SOCR_Modeler.html SOCR Modeler] (an example is shown later in Exercise 4). As shown on the image below, try changing the power parameters for the X and Y power-transforms and observe the graphical behavior of the transformed scatter-plot (blue points connected by a thin line) versus the native (original) data (red color points). We have applied a linear rescaling to the power-transform data to map it in the same space as the original data. This is done purely for visualization purposes, as without this rescaling it will be difficult to see the correspondence of the transformed and original data. Also note the changes of the numerical summaries for the transformed data (bottom text area) as you update the power parameters. What power parameters would you suggest that make the X-Y relation most linear?
+
* First, point your browser to [http://www.socr.ucla.edu/htmls/SOCR_Charts.html SOCR Charts] and select the '''PowerTransformXYStatterChart''' (Line-Charts -> PowerTransformXYStatterChart). You may use the default data provided for this chart, enter your own data (remember to '''MAP''' the data before your '''UPDATE''' the chart), or obtain SOCR simulated data from the '''Data-Generation''' tab of the [http://www.socr.ucla.edu/htmls/SOCR_Modeler.html SOCR Modeler] (an example is shown later in Exercise 4). As shown on the image below, try changing the power parameters for the X and Y power-transforms and observe the graphical behavior of the transformed scatter-plot (blue points connected by a thin line) versus the native (original) data (red color points). We have applied a linear rescaling to the power-transform data to map it in the same space as the original data. This is done purely for visualization purposes, as without this rescaling it will be difficult to see the correspondence of the transformed and original data. Also note the changes of the numerical summaries for the transformed data (bottom text area) as you update the power parameters. What power parameters would you suggest that make the X-Y relation most linear?
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_022007_Fig7.jpg|400px]]</center>
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_022007_Fig7.jpg|400px]]</center>
Line 19: Line 29:
* The second exercise demonstrates the effects of the power-transform applied to data in a QQ-Normal plot setting. We are interested in studying the effects of power transforming the native (original) data on the quantiles, relative the Normal quantiles (i.e., QQ-Normal plot effects). How and why do you expect the QQ-Normal plot to change as we vary the power parameter?
* The second exercise demonstrates the effects of the power-transform applied to data in a QQ-Normal plot setting. We are interested in studying the effects of power transforming the native (original) data on the quantiles, relative the Normal quantiles (i.e., QQ-Normal plot effects). How and why do you expect the QQ-Normal plot to change as we vary the power parameter?
-
* Again go to [http://www.socr.ucla.edu/htmls/SOCR_Charts.html SOCR Charts] and select the '''PowerTransformQQNormalPlotChart''' (Line-Charts -> PowerTransformQQNormalPlotChart). You can use different data for this experiment - either use the default data provided with the QQ-Normal chart, enter your own data (remember to '''MAP''' the data before your '''UPDATE''' the chart) or obtain SOCR simulated data from the '''Data-Generation''' tab of the [http://www.socr.ucla.edu/htmls/SOCR_Modeler.html SOCR Modeler] (an example is shown later in Exercise 4). Change the power-transform parameter (using the slider or the by typing int he text area) and observe the graphical behavior of the transformed data in the QQ-Normal plot (green points connected by a thin line) versus the plot of the native data (red color points). What power parameter would you suggest that make the (transformed) data quantiles similar to those of the Normal distribution? Why?
+
* Again go to [http://www.socr.ucla.edu/htmls/SOCR_Charts.html SOCR Charts] and select the '''PowerTransformQQNormalPlotChart''' (Line-Charts -> PowerTransformQQNormalPlotChart). You can use different data for this experiment - either use the default data provided with the QQ-Normal chart, enter your own data (remember to '''MAP''' the data before your '''UPDATE''' the chart) or obtain SOCR simulated data from the '''Data-Generation''' tab of the [http://www.socr.ucla.edu/htmls/SOCR_Modeler.html SOCR Modeler] (an example is shown later in Exercise 4). Change the power-transform parameter (using the slider or the by typing in the text area) and observe the graphical behavior of the transformed data in the QQ-Normal plot (green points connected by a thin line) versus the plot of the native data (red color points). What power parameter would you suggest that make the (transformed) data quantiles similar to those of the Normal distribution? Why?
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_022007_Fig8.jpg|400px]]</center>
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_022007_Fig8.jpg|400px]]</center>
Line 25: Line 35:
* This exercise demonstrates the effects on the histogram distribution after applying the power-transform to the (observed or simulated) data. In this experiment, we want to see whether we can reduce the variance of a dataset and make its histogram more symmetric, unimodal and bell-shaped.
* This exercise demonstrates the effects on the histogram distribution after applying the power-transform to the (observed or simulated) data. In this experiment, we want to see whether we can reduce the variance of a dataset and make its histogram more symmetric, unimodal and bell-shaped.
-
* Again go to [http://www.socr.ucla.edu/htmls/SOCR_Charts.html SOCR Charts] and select the '''PowerTransformHistogramChart''' (Bar-Charts -> XYPlot -> PowerTransformHistogramChart). We will use SOCR simulated data from the '''Data-Generation''' tab of the [http://www.socr.ucla.edu/htmls/SOCR_Modeler.html SOCR Modeler], however you may chose to use the default data for this chart or enter your own data. The image below shows you the [http://wiki.stat.ucla.edu/socr/index.php/About_pages_for_SOCR_Distributions Generalized Beta Distribution] using [http://www.socr.ucla.edu/htmls/SOCR_Distributions.html SOCR Distributions].
+
* Again go to [http://www.socr.ucla.edu/htmls/SOCR_Charts.html SOCR Charts] and select the '''PowerTransformHistogramChart''' (Bar-Charts -> XYPlot -> PowerTransformHistogramChart). We will use SOCR simulated data from the '''Data-Generation''' tab of the [http://www.socr.ucla.edu/htmls/SOCR_Modeler.html SOCR Modeler], however you may choose to use the default data for this chart or enter your own data. The image below shows you the [http://wiki.stat.ucla.edu/socr/index.php/About_pages_for_SOCR_Distributions Generalized Beta Distribution] using [http://www.socr.ucla.edu/htmls/SOCR_Distributions.html SOCR Distributions].
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_022007_Fig9.jpg|400px]]</center>
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_022007_Fig9.jpg|400px]]</center>
-
* Go to the [http://www.socr.ucla.edu/htmls/SOCR_Modeler.html SOCR Modeler] and select 200 observations from the [http://wiki.stat.ucla.edu/socr/index.php/About_pages_for_SOCR_Distributions Generalized Beta Distribution] (<math>\alpha = 1.5; \beta = 3; A=0; B=7</math>), as shown on the image below. Copy these 200 values in your mouse buffer (CNT-C) and paste them in the '''Data''' tab of the '''PowerTransformHistogramChart'''. Then ''map'' this column to ''XYValue'' (under the '''MAP''' tab) and click '''Update_Chart'''. This will generate the histogram of the 200 observations. Indeed, this graph should look like a discrete analoge of the [http://wiki.stat.ucla.edu/socr/index.php/About_pages_for_SOCR_Distributions Generalized Beta] density curve above.
+
* Go to the [http://www.socr.ucla.edu/htmls/SOCR_Modeler.html SOCR Modeler] and select 200 observations from the [http://wiki.stat.ucla.edu/socr/index.php/About_pages_for_SOCR_Distributions Generalized Beta Distribution] (<math>\alpha = 1.5; \beta = 3; A=0; B=7</math>), as shown on the image below. Copy these 200 values in your mouse buffer (CNT-C) and paste them in the '''Data''' tab of the '''PowerTransformHistogramChart'''. Then ''map'' this column to ''XYValue'' (under the '''MAP''' tab) and click '''Update_Chart'''. This will generate the histogram of the 200 observations. Indeed, this graph should look like a discrete analog of the [http://wiki.stat.ucla.edu/socr/index.php/About_pages_for_SOCR_Distributions Generalized Beta] density curve above.
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_022007_Fig10.jpg|400px]]</center>
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_022007_Fig10.jpg|400px]]</center>
Line 56: Line 66:
** Try experimenting with other (real or simulated) data sets and different Power parameters (λ). What are the general effects of increasing/decreasing λ in any of these domains [-10;0], [0;1] and [1;10]?
** Try experimenting with other (real or simulated) data sets and different Power parameters (λ). What are the general effects of increasing/decreasing λ in any of these domains [-10;0], [0;1] and [1;10]?
** For each of the exercises (X-Y scatter-plot, QQ-Normal plot, Histogram plot and Time/Index plot) empirically study the effects of the power transform as a tool for normalizing the data. You can take samples of size 100 from Student’s T-distribution (low df) and determine appropriate levels of λ for which the transformed data is (visually) well approximated by a Normal Distribution.  
** For each of the exercises (X-Y scatter-plot, QQ-Normal plot, Histogram plot and Time/Index plot) empirically study the effects of the power transform as a tool for normalizing the data. You can take samples of size 100 from Student’s T-distribution (low df) and determine appropriate levels of λ for which the transformed data is (visually) well approximated by a Normal Distribution.  
 +
 +
==Example==
 +
The table below shows data for [http://answers.yahoo.com/question/index?qid=20090311060915AALBs4f planetary distances from the Sun] in terms of millions of miles (X) and [http://en.wikipedia.org/wiki/Light-year light-years] (Y). The X vs.Y scatterplot shows a positive association curving up.  Making an identify transformation of X (Transformed_X) and a power-transformation of Y for power-exponent=0.65 (Transformed_Y) linearizes the X vs. Y association, as shown on the image below. Use the [http://socr.ucla.edu/htmls/SOCR_Charts.html SOCR PowerTransformScatterChartdemo applet].
 +
 +
<center>
 +
{| class="wikitable"
 +
|-
 +
! Planet || Original_X || Original_Y || Transformed_X || Transformed_Y
 +
|-
 +
| Mercury || 36 || 0.24 || 36.0 || 0.39549163945896465
 +
|-
 +
| Venus || 67 || 0.61 || 67.0 || 0.7252110165401895
 +
|-
 +
| Earth || 93 || 1 || 93.0 || 1.0
 +
|-
 +
| Mars || 142 || 1.88 || 142.0 || 1.5073100749969868
 +
|-
 +
| Jupiter || 484 || 11.86 || 484.0 || 4.990626264619477
 +
|-
 +
| Saturn || 887 || 29.46 || 887.0 || 9.015738002768197
 +
|-
 +
| Uranus || 1784 || 84.07 || 1784.0 || 17.824472281669742
 +
|-
 +
| Neptune || 2796 || 164.82 || 2796.0 || 27.60936647168294
 +
|-
 +
| Pluto || 3666 || 247.68 || 3666.0 || 35.97734496244632
 +
|}
 +
</center>
 +
 +
<center>[[Image:SOCR_Activities_PowerTransformGraphing_Dinov_101609_Fig12.png|400px]]</center>
<hr>
<hr>

Current revision as of 04:08, 17 October 2009

Contents

SOCR Educational Materials - Activities - SOCR Power Transformation Family Graphing Activity

Summary

This is activity demonstrates the usage, effects and properties of the modified power transformation family applied to real or simulated data to reduce variation and enhance Normality. There are 4 exercises each demonstrating the properties of the power transform in different settings for observed or simulated data: X-Y scatter plot, QQ-Normal plot, Histogram plot and Time/Index plot.

Background

The power transformation family is often used for transforming data for the purpose of making it more Normal-like. The power transformation is continuously varying with respect to the power parameter λ and defined, as continuous piece-wise function, for all y > 0 by


          y^{(\lambda)} =
                \left\{
                  \begin{matrix}
                    {(y^{\lambda}-1) \over {\lambda} } & \mathrm{for\ } \lambda \neq 0 \\ & \\
                    \log{y} & \mathrm{for\ } \lambda = 0  
                  \end{matrix}
                \right.

Exercises

Exercise 1: Power Transformation Family in a X-Y Scatter Plot Setting

  • This exercise demonstrates the characteristics of the power-transform when applied independently to the two processes in an X-Y scatter plot setting. In this situation, one observes paired (X,Y) values which are typically plotted X vs. Y in the 2D plane. We are interested in studying the effects of independently applying the power transforms to the X and Y processes. How and why would the corresponding scatter plot change as we vary the power parameters for X and Y?
  • First, point your browser to SOCR Charts and select the PowerTransformXYStatterChart (Line-Charts -> PowerTransformXYStatterChart). You may use the default data provided for this chart, enter your own data (remember to MAP the data before your UPDATE the chart), or obtain SOCR simulated data from the Data-Generation tab of the SOCR Modeler (an example is shown later in Exercise 4). As shown on the image below, try changing the power parameters for the X and Y power-transforms and observe the graphical behavior of the transformed scatter-plot (blue points connected by a thin line) versus the native (original) data (red color points). We have applied a linear rescaling to the power-transform data to map it in the same space as the original data. This is done purely for visualization purposes, as without this rescaling it will be difficult to see the correspondence of the transformed and original data. Also note the changes of the numerical summaries for the transformed data (bottom text area) as you update the power parameters. What power parameters would you suggest that make the X-Y relation most linear?


Exercise 2: Power Transformation Family in a QQ-Normal Plot Setting

  • The second exercise demonstrates the effects of the power-transform applied to data in a QQ-Normal plot setting. We are interested in studying the effects of power transforming the native (original) data on the quantiles, relative the Normal quantiles (i.e., QQ-Normal plot effects). How and why do you expect the QQ-Normal plot to change as we vary the power parameter?
  • Again go to SOCR Charts and select the PowerTransformQQNormalPlotChart (Line-Charts -> PowerTransformQQNormalPlotChart). You can use different data for this experiment - either use the default data provided with the QQ-Normal chart, enter your own data (remember to MAP the data before your UPDATE the chart) or obtain SOCR simulated data from the Data-Generation tab of the SOCR Modeler (an example is shown later in Exercise 4). Change the power-transform parameter (using the slider or the by typing in the text area) and observe the graphical behavior of the transformed data in the QQ-Normal plot (green points connected by a thin line) versus the plot of the native data (red color points). What power parameter would you suggest that make the (transformed) data quantiles similar to those of the Normal distribution? Why?

Exercise 3: Power Transformation Family in a Histogram Plot Setting

  • This exercise demonstrates the effects on the histogram distribution after applying the power-transform to the (observed or simulated) data. In this experiment, we want to see whether we can reduce the variance of a dataset and make its histogram more symmetric, unimodal and bell-shaped.
  • Again go to SOCR Charts and select the PowerTransformHistogramChart (Bar-Charts -> XYPlot -> PowerTransformHistogramChart). We will use SOCR simulated data from the Data-Generation tab of the SOCR Modeler, however you may choose to use the default data for this chart or enter your own data. The image below shows you the Generalized Beta Distribution using SOCR Distributions.
  • Go to the SOCR Modeler and select 200 observations from the Generalized Beta Distribution (α = 1.5;β = 3;A = 0;B = 7), as shown on the image below. Copy these 200 values in your mouse buffer (CNT-C) and paste them in the Data tab of the PowerTransformHistogramChart. Then map this column to XYValue (under the MAP tab) and click Update_Chart. This will generate the histogram of the 200 observations. Indeed, this graph should look like a discrete analog of the Generalized Beta density curve above.
  • In the Graph tab of the PowerTransformHistogramChart, change the power-transform parameter (using the slider on the top). All SOCR Histogram charts allow you to choose the width of the histogram bins, using the second slider on the top. Observe the graphical behavior of the histogram of the transformed data (blue bins) and compare it to the histogram of the native data (red bins). What power parameter would you suggest that make the histogram of the power-transformed data better? Why?

Exercise 4: Power Transformation Family in a Time/Index Plot Setting

  • Let’s first get some data: Go to SOCR Modeler and generate 100 Cauchy Distributed variables. Copy these data in your mouse buffer (CNT-C). Of course, you may use your own data throughout. We choose Cauchy data to demonstrate how the Power Transform Family allows us to normalize data that is far from being Normal-like.
  • Next, paste (CNT-V) these 100 observations in SOCR Charts (Line-Charts -> Power Transform Chart). Click Update Chart to see the index plot of this data in RED!
  • Now go to the Graph Tab-Pane and choose λ = 0 (the power parameter). Why is λ = 0 the best choice for this data? Try experimenting with different values of λ. Observe the variability in the Graph of the transformed data in Blue (relative to the variability of the native data in Red).
  • Then go back to the Data Tab-Pane and copy in your mouse buffer the transformed data. We will compare how well does Normal distribution fit the histograms of the raw data ( Cauchy distribution) and the transformed data. One can experiment with other powers of λ, as well! In the case of λ = 0, the power transform reduces to a log transform, which is generally a good way to make the histogram of a data set well approximated by a Normal Distribution. In our case, the histogram of the original data is close to Cauchy distribution, which is heavy tailed and far from Normal (Recall that the T(df) distribution provides a 1-parameter homotopy between Cauchy and Normal).
  • Now copy in your mouse buffer the transformed data and paste it in the SOCR Modeler. Check the Estimate Parameters check-box on the top-left. This will allow you to fit a Normal curve to the histogram of the (log) Power Family Transformed Data. You see that Normal Distribution is a great fit to the histogram of the transformed Data. Be sure to check the parameters of the Normal Distribution (these are estimated using least squares and reported in the Results Tab-Pane). In this case, these parameters are: Mean = 0.177, Variance = 1.77, however, these will vary, in general.
  • Let’s try to fit a Normal model to the histogram of the native data (recall that this histogram should be shaped as Cauchy, as we sampled from Cauchy distribution – therefore, we would not expect a Normal Distribution to be a good fit for these data. This fact, by itself, demonstrates the importance of the Power Transformation Family. Basically we were able to Normalize a significantly Non-Normal data set. Go back to the original SOCR Modeler, where you sampled the 100 Cauchy observations. Select NormalFit_Modeler from the drop-down list of models in the top-left and click on the Graphs and Results Tab-Panes to see the graphical results of the histogram of the native (heavy-tailed) data and the parameters of its best Normal Fit. Clearly, as expected, we do not have a got match.
  • Questions
    • Try experimenting with other (real or simulated) data sets and different Power parameters (λ). What are the general effects of increasing/decreasing λ in any of these domains [-10;0], [0;1] and [1;10]?
    • For each of the exercises (X-Y scatter-plot, QQ-Normal plot, Histogram plot and Time/Index plot) empirically study the effects of the power transform as a tool for normalizing the data. You can take samples of size 100 from Student’s T-distribution (low df) and determine appropriate levels of λ for which the transformed data is (visually) well approximated by a Normal Distribution.

Example

The table below shows data for planetary distances from the Sun in terms of millions of miles (X) and light-years (Y). The X vs.Y scatterplot shows a positive association curving up. Making an identify transformation of X (Transformed_X) and a power-transformation of Y for power-exponent=0.65 (Transformed_Y) linearizes the X vs. Y association, as shown on the image below. Use the SOCR PowerTransformScatterChartdemo applet.

Planet Original_X Original_Y Transformed_X Transformed_Y
Mercury 36 0.24 36.0 0.39549163945896465
Venus 67 0.61 67.0 0.7252110165401895
Earth 93 1 93.0 1.0
Mars 142 1.88 142.0 1.5073100749969868
Jupiter 484 11.86 484.0 4.990626264619477
Saturn 887 29.46 887.0 9.015738002768197
Uranus 1784 84.07 1784.0 17.824472281669742
Neptune 2796 164.82 2796.0 27.60936647168294
Pluto 3666 247.68 3666.0 35.97734496244632

References




Translate this page:

(default)

Deutsch

Español

Français

Italiano

Português

日本語

България

الامارات العربية المتحدة

Suomi

इस भाषा में

Norge

한국어

中文

繁体中文

Русский

Nederlands

Ελληνικά

Hrvatska

Česká republika

Danmark

Polska

România

Sverige

Personal tools