Beruflich Dokumente
Kultur Dokumente
STATISTIKA DESKRIPTIF
Arranged By :
Latif Irfan (4163312015)
Tira Kristy Pane (4163312028)
Nur raudhatul jannah (41633120 )
The purpose of this research mini writing is to meet one of the tasks in the course of
descriptive statistics. As for the given task that is about "descriptive statistics".
The author is very aware that this project is still very far from the perfection caused by
the limitations and ability of the author. Because the authors apologize if there is a mistake in
writing and the authors also expect criticism and suggestions that are building for the
perfection of this project.
Finally, the authors say thank you hopefully this project can be useful and can increase
knowledge for the readers.
Author
CHAPTER I
PRELIMINARY
1.1 Background
In recent years more research has been done in many ways field, whether done by
individuals or groups of individuals, as well as acting alone or in the name of the academy,
university, institute, company and so forth. One of the things that feels very important in
connection with the research done is how - how the data should be obtained, presented,
analyzed and summarized. It turns out that for this required knowledge separately known as
statistics.
Statistics is the Science that studies how to plan, collect, analyze, interpret and present
data aimed at drawing conclusions based on data collection and analyzing which is
conducted. Therefore researchers must understand and master bagamana process data, present
data, analyze data and find conclusions as well provide input to those who need the
information.
1.3 Objectives
The purpose of this report is as follows:
a) Learn the collection and processing of data, both discrete data and data
continuous.
b) Learn how to present data in the form of frequency distribution, histogram, barchart,
central and dispersed frequency polygons.
Information:
b = the lower boundary of the madian class, is the class where the median is located.
P = median class length.
n = sample size or lots of data.
F = number of all frequencies with class mark smaller than class mark
median.
f = median class frequency
Mode
The mode of a data set is the most common data value (the largest frequency) in the data set.
Example:
1. Data: 2 3 4 5 6
Because of this data each frequency (occurrence) is only 1, then said to have no mode.
2. Data: 2 3 4 4 5 6
The largest frequency is 2 (four values appear twice). So the mode is 4. A data set that has
one mode is called Mono-mode.
3. Data: 2 3 4 4 5 6 6 7
The largest frequency is two (appears twice) that is number 4 and 6. So the data circuit mode
is 4 and 6. This data set has 2 Mode or called Bi-mode.
2.5 Dispersions
Dispersion is the measure of the distribution of a group of data to the data center.
Type:
a) Absolute dispersion
- Range (Range)
- Mean Deviation
- Variance (Variance)
- Standard Deviation (Standart Deviation)
- Quartile Deviation
b) Relative dispersion
- Coefficient of Variation
3.1 Method
In the collection of data paktikan using survey / observation method directly, where
the results of direct observations recorded on the worksheets that have been prepared
beforehand. Based on the results of research I have done in the village Dukupuntang,
Keramat sub-district, Cirebon district, then obtained the discrete data derived from data car /
vehicle that passes on the road Nyi Agung Serang per 30 sec and continuous data derived
from the height data of 5th grade elementary school children in SDN 1 Dukupuntang.
3.2 Data
The data collected is data from the results of research that I have done, the data
consists of discrete data and continuous data, the data is the following:
Discrete Data
From the data we can know the range of data cars / vehicles that cross on the road Nyi
Agung Serang is 11 cars per 30 seconds.
From these data we can know that the number of interval classes of data cars /
vehicles that cross on the road Nyi Agung Serang is as much as 6 or 7 interval class.
The length of the class ranges from 1 or 2.
Although many cars that pass at least 0, at most 11 cars per 30 seconds.
The average number of cars passing on the road Nyi Agung Serang is 4.86 or 5 cars
per 30 seconds.
While the middle value of data cars / vehicles that cross on the road Nyi Agung The
attack is 4.96 or 5 cars.
The most dominant frequency of car / vehicle data is traversed at Nyi Agung Serang
road is a 4-5 car that passes as many as 15 cars
The distance between the cars if in for 4 parts, among others, is 3.2 cars, then 5.5 cars
and 8.3 cars.
By where the 45th percentile is 5.1
With the variance of its many cars as much as 266.85
And standard deviation (standard deviation) of the car as much as 16.33
And the slope coefficient graph is -0.048
4. 2 Discrete Data Discussion
4.2.1 Frequency Distribution List
A. Specify Range is the largest data minus the smallest data, in this case because the largest
data = 11 and the smallest data = 0, then the range = 11 - 0 = 11.
B. Determine the many interval classes required. Many classes are often used in at least 5
classes and at most 15 classes, chosen according to need. Another way is good enough for
large n ≥ 200 for example to use rules sturges, namely:
Many classes = 1 + (3.3) log n
By n represents the number of data and the final result is made into integers.
Then: many classes = 1 + (3.3) log 50 = 6.6
We can create a list of frequency distributions with many classes of 6 or 7 pieces
C. Determine the length of the interval class p. This, by ancer - ancer is specified by the rule:
range
P many classes
the price p is taken in accordance with the accuracy of data units used. If data shaped unit,
take the price p per through units. For data up to one decimal, this p is also taken up to one
decimal, and so on. So if a lot of classes are taken 6, it gets:
11
𝑝 = 1,8 and from here we can take p = 1 or 2
6
CHAPTER V
CLOSING
1. Conclusion
Statistics are studied in various disciplines because statistics is a set of data analysis
tools that can help decision makers to make informed decisions based on conclusions on data
analysis of data collected. In addition, with statistics we can predict future circumstances
based on past data.
Descriptive Statistics provides limited information, which provides information that
is limited to the data as it is. Therefore descriptive statistical users can not take general
conclusions on limited data.
2. Suggestion
In terms of aspects of the scope of the article should be improved again so that the project
can be a relevant reference source.