Scribd
Upload
4 views5 pages

Ling Part 2

Uploaded by

dasgourob550
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
4 views5 pages

Ling Part 2

Uploaded by

dasgourob550
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Descriptive Statistics

• Describing data with tables and graphs


• Describing center of the data
• Describing variability of the data
• Bivariate descriptive statistics

Describing data with tables and graphs:

We organization raw data in frequency tables showing classes, frequencies, relative


frequencies and cumulative frequencies. Then we draw graphs.

Example 1: Categorical (nominal) data


Ten people (𝑛𝑛 = 10) were asked about their marital status.
Data: Single, Single, Divorced, Divorced, Widowed,
Single, Married, Married, Widowed, Single

Class Frequency Relative Percentage


Frequency
Married 2 2/10 = 0.2 20%
Single 4 0.4 40%
Divorced 2 0.2 20%
Widowed 2 0.2 20%
Total 10 1 100%

Example 2: Categorical (ordinal) data


Respondents in a study are categorized as young (Y), middle-aged (M) and old (O).
Data for 20 respondents are given below.

Data: M, M, Y, O, O, M, M, Y, Y, M, Y, M, O, O, M, M, M, Y, O, M

Class Frequency Relative Percentage


Frequency
Y 5 5/20 = 0.25 25%
M 10 0.50 50%
O 5 0.25 25%
Total 20 1 100%

6
Example 3: Discrete data

Data were collected from a sample of families that live in a suburb.


𝑋𝑋 = Number of children per family.
Data: 3, 2, 0, 4, 1, 1, ⋯, 3.

Number of Relative Cumulative


𝑋𝑋
families Frequency Frequency
0 10 0.125 10
1 27 0.338 37
2 15 0.188 52
3 18 0.225 70
4 10 0.125 80

Example 4: Continuous data

𝑋𝑋 = Duration in milliseconds (X) of /i:/ in the word ‘beat’. Data were collected from
𝑛𝑛 = 100 people.
Data: 49.2, 89.7, 41.3, ⋯, 60.9

Relative Cumulative
X Frequency
Frequency Frequency
40-50 10 0.10 10
50-60 20 0.20 30
60-70 40 0.40 70
70-80 20 0.20 90
80-90 10 0.10 100

Here, the class ‘40-50’ means 40 ≤ 𝑋𝑋 < 50 and ‘50-60’ means 50 ≤ 𝑋𝑋 < 60. If
data contain the value 50.0, it is counted in ‘50-60’. That is, the classes are non-
overlapping.

Remarks on Frequency distribution:


• The classes should be non-overlapping.
• Helps view how the data are distributed among different classes.

7
Graphs

• For Categorical variables: Bar chart and Pie chart


• For Discrete variables: Bar Chart
• For Continuous variables: Histogram

Bar Chart for Example 1 (Marital Status)

Pie Chart for Example 1 (Marital Status)

8
Bar chart and pie chart can also be drawn for Example 2 (Ordinal data)

Bar chart for Example 3 (Discrete)

Histogram for Example 4 (Continuous)

9
Difference between bar chart and histogram
1. In a bar chart, bars are separate. In a histogram, bars are attached to each other.
2. In a bar chart, height of bar represents frequency. In a histogram, area of bar
represents frequency.

Shape of a distribution
A histogram can have different shapes:

Symmetric

Positively skewed (rightward skewed)

Negatively skewed (leftward skewed)

10

You might also like