Shiny Application and Reproducible Pitch

Steve Dubois
December 16, 2017

Course Project

This is the presentation pitch for app created as part on the final project for the Developing Data Products course project in the Data Science specialization track. The course consists of two parts:

  • Shiny app with supporting documentation
  • A presentation made through Rstudio Presentation to pitch the shiny app.
  • The Shiny app: **
  • The source code for ui.R and server.R files: **

The app itsel produces a prediction of child's heights given the parents height based previously collected parent/child height data.

Summary of Galton Family Dataset 

     family        father         mother      midparentHeight
 185    : 15   Min.   :62.0   Min.   :58.00   Min.   :64.40  
 066    : 11   1st Qu.:68.0   1st Qu.:63.00   1st Qu.:68.14  
 120    : 11   Median :69.0   Median :64.00   Median :69.25  
 130    : 11   Mean   :69.2   Mean   :64.09   Mean   :69.21  
 166    : 11   3rd Qu.:71.0   3rd Qu.:65.88   3rd Qu.:70.14  
 097    : 10   Max.   :78.5   Max.   :70.50   Max.   :75.43  
 (Other):865                                                 
    children         childNum         gender     childHeight   
 Min.   : 1.000   Min.   : 1.000   female:453   Min.   :56.00  
 1st Qu.: 4.000   1st Qu.: 2.000   male  :481   1st Qu.:64.00  
 Median : 6.000   Median : 3.000                Median :66.50  
 Mean   : 6.171   Mean   : 3.586                Mean   :66.75  
 3rd Qu.: 8.000   3rd Qu.: 5.000                3rd Qu.:69.70  
 Max.   :15.000   Max.   :15.000                Max.   :79.00

App Directions

The app is a simple and straight forward in terms of structure and use.

You see basically 2 columns. The left column for inputing the father and mother heights, needed for the app to calculate a child heigh prediction. This done by moving 2 slider items to the desired height to explore. Do not forget to click on “Submit Button”, start app calculations.

The right colunm displays of summary the child height prediction at the top, and also a barplot the showing the the children predicted heigh vis-a-si the parents. Both items reactively change eacht time one enters input and clicks the submit button - don't forget.

Parent vs Child Height Scatter Plut--containg regression line

plot of chunk unnamed-chunk-1

Other Observations

As one can see frmo the plot (with regression line) and the summary table above, there is a positive correlation between child height and parent heights Also, predictons of child prediction is not necssarily intuitive as tall father does not alway mean a taller son.. This plot may also be an exmaple of reression to the mean.

Sources:

Galton's notebook, http://www.medicine.mcgill.ca/epidemiology/hanley/galton/notebook/, transcribed by Beverley Shipley in 2001.

References

Galton, F. (1886). Regression Towards Mediocrity in Hereditary Stature Journal of the Anthropological Institute, 15, 246-263

THANK YOU.