Descriptive Statistics

Loading...

Intro to

3. Descriptive Statistics

Descriptive Statistics

Explore a dataset: ●

What's in the dataset?



What does it mean?



What if there's a lot of it?

Basic statistical functions in R Wanted: measures of the center and the spread of our numeric data. ●

mean()



median()



range()



var() and sd() # variance, standard deviation



summary()

# combination of measures

mean()

A measure of the data's “most typical” value. ●

Arithmetic mean == average



Divide sum of values by number of values

mean() A measure of the data's “most typical” value.

> f <- c(3, 2, 4, 1) > mean(f) [1] 2.5

# == sum(f)/length(f) == (3+2+4+1)/4

median() A measure of the data's center value. To find it: ●

Sort the contents of the data structure



Compute the value at the center of the data: –

For odd number of elements, take the center element's value.



For even number of elements, take mean around center.

median() Odd number of values: h 1 3 2 1 3 2

h' sort

1 1 2 2

find center

3 3

h' 1 1 2 2 3 3

median(h) = 2

> h <- c(3, 1, 2) > median(h) [1] 2

median() Even number of values: need to find mean() f 1 3 2 2

f' sort

1 1 2 2

find center

f' 1 1 2 2

3 4

3 3

3 3

4 1

4 4

4 4

> f <- c(3, 2, 4, 1) > median(f) [1] 2.50

median(f) = mean(c(2,3)) = 2.5

range(): min() and max() range() reports the minimum and maximum values found in the data structure. > f <- c(3, 2, 4, 1) > range(f) # reports min(f) and max(f) [1] 1 4

var() and sd() ●

Variance: a measure of the spread of the values relative to their mean: Sample variance



Standard deviation: square root of the variance Sample standard deviation

R's summary() function Provides several useful descriptive statistics about the data: > g <- c(3, NA, 2, NA, 4, 1) > summary(g) Min. 1.00

1st Qu. Median 1.75

2.50

Mean

3rd Qu.

Max.

NA's

2.50

3.25

4.00

2

Quartiles: Sort the data set and divide it up into quarters...

Quartiles Quartiles are the three points that divide ordered data into four equal-sized groups: ●

● ●

Q1 marks the boundary just above the lowest 25% of the data Q2 (the median) cuts the data set in half Q3 marks the boundary just below the highest 25% of data

Quartiles

Boxplot and probability distribution function of Normal N(0,1σ2) population

Summary: basic statistical functions ●



Characterize the center and the spread of our numeric data. Comparing these measures can give us a good sense of our dataset.

Statistics and Missing Data If NAs are present, specify na.rm=TRUE to call: ●

mean()



median()



range()



sum()



...and some other functions

R disregards NAs, then proceeds with the calculation.

diamonds data 50,000 diamonds, for example: carat

cut

color clarity depth table price

x

y

z

1 0.23

Ideal

E

SI2 61.5

55 326 3.95 3.98 2.43

2 0.21

Premium E

SI1 59.8

61 326 3.89 3.84 2.31

3 0.23

Good

VS1 56.9

65 327 4.05 4.07 2.31

E

What can we learn about these data?

diamonds data summary() Information provided by summary() depends on the type of data, by column:

carat

cut

color

price

Min. :0.2000 1st Qu.:0.4000 Median :0.7000 Mean :0.7979 3rd Qu.:1.0400 Max. :5.0100

Fair : 1610 Good : 4906 Very Good:12082 Premium :13791 Ideal :21551

D: 6775 E: 9797 F: 9542 G:11292 H: 8304 I: 5422 J: 2808

Min. : 326 1st Qu.: 950 Median : 2401 Mean : 3933 3rd Qu.: 5324 Max. :18823

numeric data: statistical summary

categorical (factor) data: counts

Diamond Price with Size: Scatter Plot Price = Dependent Variable ↑

Carats = Independent variable→

table() function Contingency table: counts of categorical values for selected columns > table(diamonds$cut, diamonds$color) D

E

F

G

H

I

J

Fair

163

224

312

314

303

175 119

Good

662

933

909

871

702

522 307

Very Good 1513

2400 2164 2299 1824 1204 678

Premium

1603

2337 2331 2924 2360 1428 808

Ideal

2834

3903 3826 4884 3115 2093 896

Diamond Color and Cut

Bar Plot: Counts of categorical values

Correlation Do the two quantities X and Y vary together? –

Positively:



Or negatively:

A pairwise, statistical relationship between quantities

Correlation

NOTE: Correlation does not imply causation...

Looking for correlations diamonds data frame: 50,000 diamonds ● ●

carat: weight of the diamond (0.2–5.01) table: width of top of diamond relative to widest point (43–95)



price: price in US dollars



x: length in mm (0–10.74)



y: width in mm (0–58.9)



z: depth in mm (0–31.8)

cor() function Look at pairwise, statistical relationships between numeric data: > cor(diamonds[c(1,6:10)]) carat

table

price

x

y

z

carat

1.0000000 0.1816175 0.9215913 0.9750942

table

0.1816175 1.0000000 0.1271339 0.1953443 0.1837601 0.1509287

price

0.9215913 0.1271339 1.0000000 0.8844352

0.8654209 0.8612494

x

0.9750942

0.1953443 0.8844352 1.0000000

0.9747015 0.9707718

y

0.9517222

0.1837601 0.8654209 0.9747015

1.0000000 0.9520057

z

0.9533874

0.1509287 0.8612494 0.9707718

0.9520057 1.0000000

-1.0: perfectly anticorrelated



0 : uncorrelated

↕ 1.0: perfectly correlated

0.9517222 0.9533874

Interlude Complete descriptive statistics exercises.

Open in the RStudio source editor: /exercises/exercises-descriptive-statistics.R

Loading...

Descriptive Statistics

Intro to 3. Descriptive Statistics Descriptive Statistics Explore a dataset: ● What's in the dataset? ● What does it mean? ● What if there's ...

351KB Sizes 15 Downloads 53 Views

Recommend Documents

Descriptive Statistics (Statistics Toolbox)
Empirical Cumulative Distribution Function. The ksdensity function described in the last section produces an empirical v

Descriptive Statistics
Uncertainty in Engineering. • Uncertainty is inherent in all real world problems. • Two types of uncertainty: – Na

Descriptive Statistics
Descriptive Statistics. 6-1 Numerical Summaries of 6-4 Box Plots. CHAPTER OUTLINE. Chapter 6 Title and Outline. 1. 6-1 N

Descriptive Statistics
Descriptive Statistics. Y520. Robert S Michael. Goal: Learn to calculate indicators and construct graphs that summarize

Descriptive Statistics
The Analyst Application provides several types of descriptive statis- tics and graphical displays. The Summary Statistic

Descriptive Statistics
distinguished from inferential statistics. With descriptive statistics you are simply describing what the data shows. Wi

Descriptive Statistics
Descriptive Statistics. Part 4 – Measures of Dispersion. A measure of location, such as the mean or the median, only d

Descriptive Statistics
May 27, 2010 - Descriptive Statistics. Random Variables and Distributions. Random Variables: X. ▷ A potential measurem

Descriptive Statistics
DESCRIPTIVE STATISTICS. This enables GAUSS to find the DESCRIPTIVE STATISTICS procedures. If you plan to make any right-

Descriptive Statistics
Chapter 200. Descriptive Statistics. Introduction. This procedure summarizes variables both statistically and graphicall