|
|
|
@ -6,20 +6,6 @@
|
|
|
|
|
#+BEGIN_SRC emacs-lisp-slide
|
|
|
|
|
(org-show-animate '("Quantitative Methods, Part-II" "Vikas Rawal" "Prachi Bansal" "" "" ""))
|
|
|
|
|
#+END_SRC
|
|
|
|
|
* Lecture plan
|
|
|
|
|
** Descriptive Statistics [1 day]
|
|
|
|
|
*** Measures of central tendency
|
|
|
|
|
*** Dispersion
|
|
|
|
|
*** Making Data Meaningful
|
|
|
|
|
**** Cross-tabulations
|
|
|
|
|
**** Data visualisation
|
|
|
|
|
** Probability and Inference [2 days]
|
|
|
|
|
*** Probability/Relevance to statistics
|
|
|
|
|
*** Sampling distributions
|
|
|
|
|
*** Hypothesis testing
|
|
|
|
|
** Correlations and Regression [1 day]
|
|
|
|
|
** All afternoons will be used for workshops
|
|
|
|
|
|
|
|
|
|
* Day 1
|
|
|
|
|
** Title slide
|
|
|
|
|
#+BEGIN_SRC emacs-lisp-slide
|
|
|
|
@ -305,44 +291,6 @@ $cov=\frac{standard.deviation}{mean}$
|
|
|
|
|
hist(b$yield,main="Histogram of wheat yields",ylim=c(0,4000))
|
|
|
|
|
#+END_SRC
|
|
|
|
|
|
|
|
|
|
*** Histogram with smaller bins
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ccpc-wheat-hist11
|
|
|
|
|
[[file:productionhist11.png]]
|
|
|
|
|
|
|
|
|
|
#+NAME: ccpc-wheat-hist11
|
|
|
|
|
#+BEGIN_SRC R :results output graphics :exports results :file productionhist11.png :width 400 :height 300 :type cairo :family Garamond
|
|
|
|
|
subset(ccpc,Year_Agriculture==2009)->b
|
|
|
|
|
subset(b,Crop_code %in% 20 )->b
|
|
|
|
|
b$Main_Product_Qtls*100/b$Crop_Area_Ha->b$yield
|
|
|
|
|
hist(b$yield,main="Histogram of wheat yields",breaks=seq(0,25000,250),ylim=c(0,4000))
|
|
|
|
|
#+END_SRC
|
|
|
|
|
|
|
|
|
|
*** Histogram with smaller bins
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ccpc-wheat-hist12
|
|
|
|
|
[[file:productionhist12.png]]
|
|
|
|
|
|
|
|
|
|
#+NAME: ccpc-wheat-hist12
|
|
|
|
|
#+BEGIN_SRC R :results output graphics :exports results :file productionhist12.png :width 400 :height 300 :type cairo :family Garamond
|
|
|
|
|
subset(ccpc,Year_Agriculture==2009)->b
|
|
|
|
|
subset(b,Crop_code %in% 20 )->b
|
|
|
|
|
b$Main_Product_Qtls*100/b$Crop_Area_Ha->b$yield
|
|
|
|
|
hist(b$yield,main="Histogram of wheat yields",breaks=seq(0,25000,250))
|
|
|
|
|
#+END_SRC
|
|
|
|
|
|
|
|
|
|
*** Histogram (absolute frequencies) with unequal bins distorts the shape
|
|
|
|
|
#+NAME: ccpc-wheat-hist3
|
|
|
|
|
#+BEGIN_SRC R :results output graphics :exports results :file productionhist3.png :width 400 :height 300 :type cairo :family Garamond
|
|
|
|
|
subset(ccpc,Year_Agriculture==2009)->b
|
|
|
|
|
subset(b,Crop_code %in% 20 )->b
|
|
|
|
|
b$Main_Product_Qtls*100/b$Crop_Area_Ha->b$yield
|
|
|
|
|
hist(b$yield,freq=T,main="Histogram of wheat yields",breaks=c(0,1000,1500,2000,2200,2500,3000,3200,3400,3800,4000,5000,10000,21000))
|
|
|
|
|
#+END_SRC
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ccpc-wheat-hist3
|
|
|
|
|
[[file:productionhist3.png]]
|
|
|
|
|
|
|
|
|
|
*** Histogram with relative densities :slide:
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ccpc-wheat-hist2
|
|
|
|
@ -357,39 +305,12 @@ $cov=\frac{standard.deviation}{mean}$
|
|
|
|
|
hist(b$yield,freq=F,main="Histogram of wheat yields",ylim=c(0,0.00040))
|
|
|
|
|
#+END_SRC
|
|
|
|
|
|
|
|
|
|
*** Histogram with relative densities
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ccpc-wheat-hist21
|
|
|
|
|
[[file:productionhist21.png]]
|
|
|
|
|
|
|
|
|
|
#+NAME: ccpc-wheat-hist21
|
|
|
|
|
#+BEGIN_SRC R :results output graphics :exports results :file productionhist21.png :width 400 :height 300 :type cairo :family Garamond
|
|
|
|
|
subset(ccpc,Year_Agriculture==2009)->b
|
|
|
|
|
subset(b,Crop_code %in% 20)->b
|
|
|
|
|
b$Main_Product_Qtls*100/b$Crop_Area_Ha->b$yield
|
|
|
|
|
hist(b$yield,freq=F,main="Histogram of wheat yields",breaks=seq(0,25000,250),ylim=c(0,0.00040))
|
|
|
|
|
#+END_SRC
|
|
|
|
|
|
|
|
|
|
*** Histogram with unequal bins must use relative densities
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ccpc-wheat-hist4
|
|
|
|
|
[[file:productionhist4.png]]
|
|
|
|
|
|
|
|
|
|
#+NAME: ccpc-wheat-hist4
|
|
|
|
|
#+BEGIN_SRC R :results output graphics :exports results :file productionhist4.png :width 400 :height 300 :type cairo :family Garamond
|
|
|
|
|
subset(ccpc,Year_Agriculture==2009)->b
|
|
|
|
|
subset(b,Crop_code %in% 20 )->b
|
|
|
|
|
b$Main_Product_Qtls*100/b$Crop_Area_Ha->b$yield
|
|
|
|
|
hist(b$yield,freq=F,main="Histogram of wheat yields",breaks=c(0,1000,1500,2000,2200,2500,3000,3200,3400,3800,4000,5000,10000,21000),ylim=c(0,0.00040))
|
|
|
|
|
#+END_SRC
|
|
|
|
|
|
|
|
|
|
*** Boxplot :slide:
|
|
|
|
|
|
|
|
|
|
**** Invented by John Tukey in 1970
|
|
|
|
|
**** Many variations proposed since then, though the essential form and idea as remained intact.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
*** Boxplot of wheat yields :slide:
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ccpc-wheat-box1
|
|
|
|
@ -447,7 +368,6 @@ $cov=\frac{standard.deviation}{mean}$
|
|
|
|
|
boxplot(yield~Crop_code,data=b,main="Boxplots of yields of various crops",las=3,ylim=c(0,8000),outline=F)
|
|
|
|
|
#+END_SRC
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
*** Violin plots :slide:
|
|
|
|
|
|
|
|
|
|
#+RESULTS: ccpc-crop-vio
|
|
|
|
@ -466,16 +386,5 @@ $cov=\frac{standard.deviation}{mean}$
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
* Workshop plan
|
|
|
|
|
** Introduction to R
|
|
|
|
|
** Data Tables
|
|
|
|
|
** ggplot2
|
|
|
|
|
|
|
|
|
|
* Datasets
|
|
|
|
|
|
|
|
|
|
** Census
|
|
|
|
|
** PLFS/Chandan's data
|
|
|
|
|
** Suicides
|
|
|
|
|
** CPI
|
|
|
|
|
** Pulses
|
|
|
|
|
|
|
|
|
|