Model BuildingIntroductionIn data analytics, model building refers to assembling the needed data and analyzing it to address your identified problem.For this second course project assignment, you will
5/30/2020 Model Building Scoring Guide https://courseroomc.capella.edu/bbcswebdav/institution/HMSV/HMSV5316/191000/Scoring_Guides/u07a1_scoring_guide.html 1/1 Model Building Scoring Guide Due D ate : U nit 7 P erc en ta g e o f C ours e G ra d e: 1 5% . CRIT E R IA N O N-P ER FO RM ANCE BASIC P R O FIC IE N T DIS TIN G UIS H ED P re sen t d ata in a d escrip tiv e f o rm at (fo r e xam ple , t a b le s, ch arts a n d g ra p hs). 2 0% D oes n ot p re se nt d ata in a ny d escrip tiv e fo rm ats . P re se nts s o m e d ata in a d escrip tiv e fo rm at, b ut n ot all o f it . P re se nts d ata in a d escrip tiv e fo rm at ( fo r exa m ple , ta ble s, c h arts a nd g ra phs). P re se nts d ata in a d escrip tiv e fo rm at a nd pro vid es e xp la natio n o f th e ta ble , c h art, g ra ph, or o th er fo rm at. Id en tif y a n aly ses co nducte d o n b oth q uan tit a tiv e a n d qualit a tiv e d ata . 20% D oes n ot id entif y a ny analy se s c o nducte d o n data . Id entifi e s o ne ty p e o f analy sis c o nducte d o n data ( e it h er q ualit a tiv e o r quantit a tiv e ), b ut n ot b oth . Id entifi e s analy se s co nducte d o n both q ualit a tiv e a nd quantit a tiv e d ata . Id entifi e s a naly se s co nducte d o n b oth q ualit a tiv e a nd quantit a tiv e d ata a nd exp la in s w hy th e analy se s w ere s e le cte d fo r b oth . P re sen t c o nte n t an aly ses o f qualit a tiv e d ata . 20% D oes n ot d is cu ss co nte nt a naly se s o f qualit a tiv e d ata . D is cu sse s c o nte nt analy se s o f q ualit a tiv e d ata b ut d oes n ot p re se nt th e analy se s in a c le ar o r w ell- o rg aniz e d m anner. P re se nts c o nte nt analy se s o f qualit a tiv e d ata . P re se nts c o nte nt analy se s o f q ualit a tiv e d ata , a nd e xp la in s th e analy se s a nd p ossib le im plic a tio ns o f th e re su lt s o f th e a naly se s. P re sen t s ta tis tic al an aly ses o f quan tit a tiv e d ata . 20% D oes n ot d is cu ss sta tis tic a l a naly se s o f quantit a tiv e d ata . D is cu sse s s ta tis tic a l analy se s o f q uantit a tiv e d ata , b ut th e r e su lt s a re n ot c le ar. P re se nts s ta tis tic a l analy se s o f quantit a tiv e d ata . P re se nts s ta tis tic a l analy se s o f quantit a tiv e d ata , in te rp re ts th e r e su lt s o f th e s ta tis tic a l a naly se s, a nd d is cu sse s th e im plic a tio ns o f th e re su lt s . C om munic ate in a m an ner t h at is c le ar an d w ell o rg an iz e d . 20% C om munic a te s in a m anner th at is s o d is o rg aniz e d a nd/o r h as so m any e rro rs in w rit in g m ech anic s th at th e id eas c a nnot b e unders to od. C om munic a te s in a m anner th at is n ot w ell- o rg aniz e d o r h as e nough erro rs in w rit in g m ech anic s th at it in te rfe re s w it h u nders ta ndin g th e id eas pre se nte d. C om munic a te s in a m anner th at is c le ar and w ell o rg aniz e d. C om munic a te s in a c le ar, w ell- o rg aniz e d m anner th at is fr e e o f erro rs in w rit in g m ech anic s a nd A PA fo rm at.
Model BuildingIntroductionIn data analytics, model building refers to assembling the needed data and analyzing it to address your identified problem.For this second course project assignment, you will
5/30/2020 Riverbend City: Data Modeling https://media.capella.edu/CourseMedia/HMSV5316/data-modeling/transcript.asp 1/3 Riv e rb end C it y ® A ctiv it y D ata M od elin g In tro d uctio n M ento r T a lk C onclu sio n I n tro d uctio n Welc o m e b ack t o y o ur v ir tu al in te rn sh ip a t t h e R iv e rb end C om munit y A ctio n C ente r! S o f a r, y o u h ave b een in tro d uce d t o y o ur o ve ra rc h in g p ro je ct o f u sin g d ata a n aly tic s t o h elp R C AC eva lu ate t h e e ff e ctiv e ness o f t h eir R ub y La ke T e en H om ele ssn ess T a sk F o rc e , a n d t h en t a lk e d t o s ta ff m em bers t o g et a s e nse o f th e t y p es o f q uestio ns y o u s h o uld b e t r y in g t o a n sw er w it h d ata . The n ext s te p w il l b e t o t a ke a c lo se r lo ok a t d ata m od elin g . It ‘s t im e f o r a n o th er m eetin g w it h y o ur m ento r, B re nd a. M ento r T a lk R ive rb end C it y Com munit y Act io n C ente r: M ento r’s O ff ice C heck in w it h y o ur C AC M ento r, B re nd a. Com e o n in ! I h o p e y o u’r e f in d in g y o ur in te rn sh ip in te re stin g a n d ch alle ng in g s o f a r. S o , s in ce t h e la st t im e w e t a lk e d , y o u s h o uld h ave a m ore s o lid s e nse o f w hat t h e o ve ra ll p la n is h ere , a n d w hat k in d o f q uestio ns w e n eed t o b e an sw erin g t h ro ug h d ata a n aly tic s. T hat’s t h e f ir s t s te p f o r a n y p ro je ct lik e 5/30/2020 Riverbend City: Data Modeling https://media.capella.edu/CourseMedia/HMSV5316/data-modeling/transcript.asp 2/3 th is , a n d n o w it ’s t im e t o m ove f o rw ard . The n ext t h in g I’d lik e t o d o is t o t a lk t o y o u a lit t le a b out d ata m od elin g . it ’s r e ally im porta n t; it ’s a f o und atio nal t h in g , a n d w e h ave t o m ake s u re e ve ry th in g ’s s tra ig ht b efo re w e c a n p ro ce ed . Li ke , if y o u g et y o ur m od elin g d one c o rre ctly , s u b se q uent s te p s a re t h at m uch e asie r a n d m ore lo g ic a l. G et it w ro ng , a n d t h e w ho le t h in g is lia b le t o b lo w u p o n yo ur f a ce w hen y o u’r e h alf w ay t h ro ug h t h e p ro ce ss a n d y o u r e aliz e y o u ca n ’t a ctu ally a n sw er t h e q uestio ns y o u’r e t ry in g t o a n sw er. F ir s t o ff , w hat is t h is d ata m od elin g t h in g ? It ’s a lit t le a b stra ct. A d ata m od el is a c o nce p tu al r e p re se nta tio n o f t h e s tru ctu re t h at’s g oin g t o g uid e y o ur d ata b ase . O ne w ay t o t h in k o f it is t h at it ’s a n a tte m pt t o p ro p erly r e p re se nt r e alit y t h ro ug h d ata . M ayb e “ co nce p tu al b lu ep rin t” is a g ood w ay t o t h in k o f it . Y o ur d ata m od el n eed s t o a cco unt f o r t h e n atu re o f t h e d ata y o u’r e g ath erin g , t h e in stit u tio nal r u le s a t p la y in u sin g it , a n d t h e o rg an iz a tio n o f th e d ata it s e lf . T hin k t a b le s, c o lu m ns, r e la tio nsh ip s, c o nstra in ts , a n d t h at so rt o f t h in g . There a re t h re e t y p es o f d ata m od els w e’r e g oin g t o t h in k a b out: re la tio nal, s ta tis tic a l, a n d p re d ic tiv e . T hese a re a ll d if f e re nt a p p ro ach es t o s tru ctu rin g a n d h an d lin g d ata , d ep end in g o n w hat k in d o f in fo rm atio n yo u’r e c o lle ctin g a n d w hat y o u w an t t o d o w it h it . If y o u h ave e xp erie nce u sin g d ata b ase s, a r e la tio nal d ata m od el m ig ht se em lik e t h e m ost in tu it iv e a n d f a m il ia r a p p ro ach . In t h is s e tu p , d ata is – o f c o urs e – s to re d in a r e la tio nal d ata b ase . B asic a lly , y o ur c la ssic d ata b ase se tu p : a s e rie s o f in d exe d t a b le s w it h o ne-to -o ne a n d o ne-to -m an y re la tio ns s e t b etw een t h em , g ove rn e d b y k e ys. Y o u c a n m an ip ula te t h e d ata a n d r e p ort o n it u sin g s o m eth in g lik e S Q L. Next, s ta tis tic a l d ata m od elin g . It liv e s u p t o it s n am e, m ore o r le ss- y o u’r e a m assin g a n d s to rin g la rg e a m ounts o f d ata a lo ng s o m e p re – id entif ie d v a ria b le s, w it h t h e id ea t h at y o u c a n a g gre g ate t h ese d ata p oin ts a n d s u b je ct t h em t o s ta tis tic a l a n aly sis . T his a llo w s y o u t o id entif y p atte rn s a n d c o rre la tio ns, a n d p ossib ly id entif y t re nd s t h at m ay co ntin ue in to t h e f u tu re . A nd f in ally , I’d lik e t o t a lk a b out p re d ic tiv e d ata m od ellin g . Y o u c a n t h in k o f it a s a m od ellin g a p pro ach t h at’s k in d o f a m ean s t o a n e nd … where t h e e nd is b ein g a b le t o p re d ic t f u tu re o utc o m es b ase d o n t h e d ata y o u’r e g ath erin g . In t h is c a se , y o u s tru ctu re y o ur d ata m od el a ro und a s e rie s o f p re d ic to rs t h at y o u’v e id entif ie d ; in o th er w ord s, v a ria b le s t h at are lik e ly t o h ave a n e ff e ct o n t h e o utc o m es t h at y o u’r e c o nce rn ed w it h . T here ’s a n in te rp la y h ere b etw een p re d ic tiv e a n d s ta tis tic a l d ata 5/30/2020 Riverbend City: Data Modeling https://media.capella.edu/CourseMedia/HMSV5316/data-modeling/transcript.asp 3/3 mod ellin g in t h at o ne in fo rm s t h e o th er; a s t h in g s m ove f o rw ard , f o r in sta n ce , y o u m ig ht u se a s ta tis tic a l d ata m od el t o e va lu ate t h e eff e ctiv e ness o f y o ur p re d ic tiv e m od el. I h o p e t h is h elp s! N ext, w e’ll b e t a lk in g a b out p utt in g s o m e o f t h is s tu ff in to p ra ctic e . C onclu sio n Yo u h ave c o m ple te d t h e R iv e rb end C it y : D ata M od elin g a ctiv it y . L ic e nse d u nd er a C re ativ e C om mons A ttrib utio n 3 .0 L ic e nse (h ttp s:/ /c re ativ e co m mons.o rg /lic e nse s/b y-n c-n d /3 .0 /)