Kuliah 1 - Statistika

Pengantar Statistik

Rusdha Muharar

Jurusan Teknik Elektro dan Komputer

Fakultas Teknik, Unyiah
Banda Aceh
 Outline

Pengantar Statistik

Statistik Sampel
Pengantar Statistik

Statistik Sampel
Pengantar Statistik Statistik Sampel

Statistik

DEFINISI
Statistik: Ilmu yang berhubungan dengan koleksi, organisasi, pre-
sentasi, analysis, dan interpretasi data yang digunakan untuk:
• mengambil keputusan (decision)
• memecahkan masalah (problem solving)
• perancangan produk dan proses

• Science of learning information from Data

• Data =⇒ Ketidak-pastian (uncertainty) & ke-acakan (variability)
• Tugas: Apakah perbedaan antara uncertainty dan variability?

1 / 21
 falling in each class interval. The number of class intervals chosen should be a trade-off
Pengantar Statistik between (1) choosing too few classes at a cost of losing too much information about the Statistik Sampel

actual data values in a class and (2) choosing too many classes, which will result in the
frequencies of each class being too small for a pattern to be discernible. Although 5 to 10
Contoh
TABLE 2.3 Life in Hours of 200 Incandescent Lamps

Item Lifetimes
1,067 919 1,196 785 1,126 936 918 1,156 920 948
855 1,092 1,162 1,170 929 950 905 972 1,035 1,045
1,157 1,195 1,195 1,340 1,122 938 970 1,237 956 1,102
1,022 978 832 1,009 1,157 1,151 1,009 765 958 902
923 1,333 811 1,217 1,085 896 958 1,311 1,037 702
521 933 928 1,153 946 858 1,071 1,069 830 1,063
930 807 954 1,063 1,002 909 1,077 1,021 1,062 1,157
999 932 1,035 944 1,049 940 1,122 1,115 833 1,320
901 1,324 818 1,250 1,203 1,078 890 1,303 1,011 1,102
996 780 900 1,106 704 621 854 1,178 1,138 951
1,187 1,067 1,118 1,037 958 760 1,101 949 992 966
824 653 980 935 878 934 910 1,058 730 980
844 814 1,103 1,000 788 1,143 935 1,069 1,170 1,067
1,037 1,151 863 990 1,035 1,112 931 970 932 904
1,026 1,147 883 867 990 1,258 1,192 922 1,150 1,091
1,039 1,083 1,040 1,289 699 1,083 880 1,029 658 912
1,023 984 856 924 801 1,122 1,292 1,116 880 1,173
1,134 932 938 1,078 1,180 1,106 1,184 954 824 529
998 996 1,133 765 775 1,105 1,081 1,171 705 1,425
610 916 1,001 895 709 860 1,110 1,149 972 1,002

2 / 21
Pengantar Statistik Statistik Sampel

Statistik

Statistik

Statistik deskriptif Statistik inferensial

(descriptive statistics) (inferential statistics)

• berhubungan dengan deskripsi, • berhubungan dengan pengambilan

presentasi dan rangkuman data kesimpulan atau keputusan
o Tabel frekuensi o Regresi linier
o Grafik stem (stem plot) o Regresi multi-linier
o Histogram
o Rata-rata, median, modus, dan
varian dari sampel
o Sample percentile dan box plots

3 / 21
 Stem and Leaf Plots
Pengantar Statistik Statistik Sampel
As seen in Subsection 2.2.2, using a line or a bar graph to plot the frequencies of data values
is often an effective way of portraying a data set. However, for some data sets the number
of distinct values is too large to utilize this approach. Instead, in such cases, it is useful to
Statistik Deskriptif
divide the values into groupings, or class intervals, and then plot the number of data values
falling in each class interval. The number of class intervals chosen should be a trade-off
• mendapatkan pola (pattern) atau kecenderungan (trend) dari data.
between (1) choosing too few classes at a cost of losing too much information about the
actual data values in a class and (2) choosing too many classes, which will result in the
• Contoh: Lifetime dari lampu (jam)
frequencies of each class being too small for a pattern to be discernible. Although 5 to 10

TABLE 2.3 Life in Hours of 200 Incandescent Lamps

Item Lifetimes
1,067 919 1,196 785 1,126 936 918 1,156 920 948
855 1,092 1,162 1,170 929 950 905 972 1,035 1,045
1,157 1,195 1,195 1,340 1,122 938 970 1,237 956 1,102
1,022 978 832 1,009 1,157 1,151 1,009 765 958 902
923 1,333 811 1,217 1,085 896 958 1,311 1,037 702
521 933 928 1,153 946 858 1,071 1,069 830 1,063
930 807 954 1,063 1,002 909 1,077 1,021 1,062 1,157
999 932 1,035 944 1,049 940 1,122 1,115 833 1,320
901 1,324 818 1,250 1,203 1,078 890 1,303 1,011 1,102
996 780 900 1,106 704 621 854 1,178 1,138 951
1,187 1,067 1,118 1,037 958 760 1,101 949 992 966
824 653 980 935 878 934 910 1,058 730 980
844 814 1,103 1,000 788 1,143 935 1,069 1,170 1,067
1,037 1,151 863 990 1,035 1,112 931 970 932 904
1,026 1,147 883 867 990 1,258 1,192 922 1,150 1,091
1,039 1,083 1,040 1,289 699 1,083 880 1,029 658 912
1,023 984 856 924 801 1,122 1,292 1,116 880 1,173
1,134 932 938 1,078 1,180 1,106 1,184 954 824 529
998 996 1,133 765 775 1,105 1,081 1,171 705 1,425
610 916 1,001 895 709 860 1,110 1,149 972 1,002

4 / 21
Pengantar Statistik
700–800 12 Statistik Sampel
800–900 25
900–1000 58
1000–1100 Statistik Deskriptif 41
1100–1200 43
1200–1300 7
• mendapatkan1300–1400
pola (pattern) atau kecenderungan
6 (trend) dari data.
1400–1500 1
• Contoh: Lifetime dari lampu (jam)
Number of
occurrences
60

50

40

30

20

10

0
0 5 6 7 8 9 10 11 12 13 14 15
Life in units of 100 hours

FIGURE 2.5 A frequency histogram.

4 / 21
Pengantar Statistik Statistik Sampel

Statistik Inferensial

• Metode membuat kesimpulan, keputusan, prediksi dari sebuah

populasi berdasarkan sampel yang ada.
• Contoh: Dalam proses pemungutan suara disebuah desa untuk
memilih Bupati (2 calon), terdapat 5 ribu pemilih aktif. Sebuah badan
survey melakukan quick-count dengan mengambil melakukan
interview terhadap 200 pemilih. Hasil quick count menunjukkan
calon A mendapatkan 50.1% suara, sedangkan calon B mendapatkan
49.5% suara
• Statistik Inferensial: Berapa tingkat keyakinan terhadap hasil
quick-count ini setelah semua suara (5 ribu suara) dihitung?

5 / 21
Pengantar Statistik Statistik Sampel

Populasi dan Sampel

• Populasi

DEFINISI
Populasi: Koleksi menyeluruh (total collection) dari objek.

Bagaimana memperoleh populasi?: Sensus

• Bagaimana kalau ukuran populasi terlalu besar?

DEFINISI
Sampel: Sub-grup dari Populasi.

6 / 21
 Pengantar Statistik Statistik Sampel

ature of Statistics Populasi dan Sampel

URE 1.1 Population

pulation
d sample
Sample

Descriptive statistics and inferential statistics are interrelated. You mus

always use techniques of descriptive statistics to organize and summarize the i
Ref:tion
N. A.obtained
Weiss, Introductory
from aStatistics,
sample10th ed., Pearson,
before carrying2017.
out an inferential analysis. Furth
as you will see, the preliminary descriptive analysis of a sample often reveals
7 / 21
 the sample (deductive reasoning), whereas inferential statistics reas
Pengantar Statistik Statistik Sampel

ple to the population (inductive reasoning).

Statistik vs. ProbabilitasThis is illustrated in Fig

Probability

Population Sample
Inferential
statistics

Figure• 1.2 The relationship between probability and inferential statistics

Probability:
▶ Diketahui lebih 50% pengemudi di Banda Aceh memakai sabuk
efore we can pengaman
understand(asumsiwhat a particular
terhadap populasi). sample can tell us about t
▶ Q: Jika terdapat sample 100 pengemudi, berapakah probabilitas
we should first understand the uncertainty associated with taking
(jumlah) pengemudi yang menggunakan sabuk pengaman?
given population. This is why we study probability before statistics
• Statistik (Inferensial):
▶ Jika dari 100 sample (pengemudi) terdapat 65 pengemudi menggunakan
sabuk pengaman.
xample of the
▶ Q:contrasting focus of probability and inferential statis
Apakah ini dapat dijadikan sebagai bukti bahwa ‘lebih 50%
ivers’ use of manual
pengemudi dilap belts
Banda Acehin cars equipped
memakai with
sabuk pengaman’ ? automatic shou
. (The article “Automobile Seat Belts: Usage Patterns in Autom
8 / 21
Pengantar Statistik Statistik Sampel

Variabel (1)

DEFINISI
Variabel: Karakteristik objek dalam populasi yang nilainya bervari-
asi dari satu objek ke objek lainnya

Contoh:
• Tinggi badan mahasiswa Teknik Elektro 2018.
• Pendapatan masyarakat Lamreung, Aceh Besar.

9 / 21
Pengantar Statistik Statistik Sampel

Variabel (2)

• Jumlah variabel observasi

▶ Univariate : data observasi terhadap variabel tunggal
▶ Bivariate : data observasi terhadap dua variabel
▶ Multivariate : data observasi terhadap lebih dari satu variabel

• Contoh:
▶ Tinggi badan mahasiswa MTE (Univariate)
▶ Berat dan Tinggi badan mahasiswa MTE (Bivariate)
▶ Berat badan, Tinggi badan, Tekanan darah dari mahasiswa MTE
(Multivariate)

10 / 21
ment
Pengantar Statistik
Continuous variable: A quantitative variable whose
Statistik Sampel
po
some interval of numbers.
Jenis Variabel

URE 2.1 Variable

variables

Qualitative Quantitative

Discrete Continuous

The values of a variable for one or more people or things yie

mation collected, organized, and analyzed by statisticians is da
Ref: N.can be Introductory
A. Weiss, classified as qualitative
Statistics, data,
10th ed., Pearson, 2017. quantitative data, discr
ous data. 11 / 21
Pengantar Statistik Statistik Sampel

Jenis Variabel

• Kualitatif - Ukuran kualitas atau karakteristik dari unit percobaan.

▶ Warna rambut: hitam, coklat, pirang.
▶ Jenis kelamin: pria, wanita
▶ Tempat lahir: Sawang, Samadua, Meukek, Pidie
▶ Pekerjaan: dosen, montir, tukang

• Kuantitatif - ukuran kuantitas numerik dari setiap unit percobaan.

1 Variabel Kontinu - mempunyai nilai yang dapat dihitung (countable)
• jumlah mobil yang parkir
• jumlah anak dalam sebuah keluarga.
2 Variabel Diskret - mempunyai nilai yang sangat banyak (tak-hingga)
dalam satu interval tertentu
• Lamanya sebuah bola lampu tidak berfungsi lagi (mati)
• volume air yang digunakan sebuah keluarga dalam satu bulan.

12 / 21
Pengantar Statistik Statistik Sampel

Data dan Dataset

DEFINISI
• Data: Nilai dari sebuah Variabel
• Dataset: Koleksi semua data dari variabel tertentu atau
seluruh variabel

Jenis Data:
• Data Kualitatif
• Data Kuantitatif
• Data Kontinu
• Data Diskret

13 / 21
Pengantar Statistik

Statistik Sampel
Pengantar Statistik Statistik Sampel

Mean dan Variance

Sebuah data set (sample) memuat n observasi
x1 , x2 , x3 , · · · , xn .
Statistik Sampel yang sangat dikenal:
• Sample Mean (rata-rata sampel)

1∑
n
x1 + x2 + x3 + · · · + xn
x̄ = = xi
n n i=1
• Sample Variance (nilai varian sampel)
(x1 − x̄)2 + (x2 − x̄)2 + (x3 − x̄)2 + · · · + (xn − x̄)2
s2 =
n−1
1 ∑ n
= (xi − x̄)2
n − 1 i=1
• Sample Standard Deviation (standar deviasi sampel)
√
s = s2
14 / 21
 Pengantar Statistik Statistik Sampel
ew and DescriptiveFocus equipped with an automatic transmission (for this model, EPA reports an
Statistics
overall rating of 27 mpg–24 mpg for city driving and 33 mpg for highway driving):
Mean dan
Focus equipped with an automatic Variance
transmission (for this model, EPA reports an
overall rating of 27 mpg–24 mpg for city driving and 33 mpg for highway driving):
Contoh:
Car efisiensi
x i bahan bakarx imobil
2x (x i 2 x )2
1 27.3 25.96 35.522
Car
2 xi
27.9 x25.36
i2x 2 x )2
(x i28.730
3 32.9 20.36 0.130
1 27.3 25.96 35.522
4 35.2 1.94 3.764
2 27.9 25.36 28.730
5 44.9 11.64 135.490
3 32.9 20.36 0.130
6 39.9 6.64 44.090
4 35.2 1.94 3.764
7 30.0 23.26 10.628
5 44.9 11.64 135.490
8 29.7 23.56 12.674
6 39.9 6.64 44.090
9 28.5 24.76 22.658
7
10
30.0
32.0
23.26
21.26
10.628
1.588
8
11 29.7
37.6 23.56
4.34 12.674
18.836
9 28.5 24.76 22.658
10 ox i 32.0
5 365.9 o(x i21.26
2 x) 5 .04 o(x i 2 x)1.588
2
5 314.110 x 5 33.26
11 37.6 4.34 18.836
ox i 5 365.9 o(x i 2 x) 5 .04 o(x i 2 x)2 5 314.110 x 5 33.26
Effects of rounding account for the sum of deviations not being exactly zero. The
numerator of s2 is Sxx 5 314.110, from which
Effects of rounding 2accountSxx for the sum of deviations not being exactly zero. The
314.110
5 31.41, s 5 5.60
numerator of s2 is Ssxx 5
5
314.110,5
n 2 1 from 11 2which
1
Sxxdeviation
The size of a representative 314.110
from the sample mean 33.26 is roughly 5.6 mpg.
s2 5 5 5 31.41, s 5 5.60
Note: Of the nine people n2 who1 also11 reported
21 driving behavior, only three did more
15 / 21
 Pengantar Statistik

Prosedur Komputasi
5 of the two
middle
values if n
is even
5 average of
Median (Nilai2 Tengah)
2 12
n th
and 1
n
11 2
th
ordered values
Statistik Sampel

• Urutkan data dari nilai terkecil ke terbesar

E 1.15 • Nilai
People notmedian
familiaruntuk n observasi
with classical musicadalah:
might tend to believe that a composer’s
 piece are so specific that the duration would
instructions for playing a particular
x n+1 However,
not depend at all on the performer(s). , n ganjil
there is typically plenty of room
x̃
2
=
for interpretation, and orchestral x n + xn
conductors and musicians take full advantage
 2 2 +1
, n genap
of this. The author went to the Web site2ArkivMusic.com and selected a sample
of 12 recordings of Beethoven’s Symphony No. 9 (the “Choral,” a stunningly
Contoh:
beautiful work), yielding the following durations (min) listed in increasing
• sebuah sampel terdiri dari 12 observasi:
order:
62.3 62.8 63.6 65.2 65.7 66.4 67.4 68.4 68.8 70.8 75.7 79.0
• karena n = 12 adalah genap, maka median dari sampel tersebut:
ved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.

x6 + x7 66.4 + 67.4
x̃ = = = 66.90
2 2

16 / 21
 Solution Referring to Table 3.1, we obtain the frequency of each valueStatistik
Pengantar Statistik in Sampel
Data
Set I, as shown in Table 3.3. From Table 3.3, we see that the greatest frequency
is 6, and that 300 is the only value
Mode that occurs with that frequency. So the mode
(Modus)
is $300.
Proceeding in the same way, we find that, for Data Set II, the greatest frequency
Prosedur Komputasi
is 5 and that 300 is the only value that occurs with that frequency. So the mode
• Tentukan frekuensi kemunculan setiap nilai observasi pada data set
is $300.
• Modus dari sebuah data set adalah nilai observasi yang dengan
Interpretation The most frequent salary was $300 both for the employees who
frekuensi kemunculan yang paling besar.
worked in the first half of the summer and those who worked in the second half.
• Jika tidak ada nilai yang muncul lebih dari sekali maka data set
tersebut
A data tidak
set will havemempunyai modus
more than one mode if more than one of its values occurs wi
the greatest frequency. For instance, suppose the first two $300-per-week employe
) whoContoh:
worked in the first half of the summer were promoted to $400-per-week jobs. The
the weekly earnings for the 13 employees would be as follows.
• Tentukan Modus dari data set

$400 400 300 940 300

300 400 300 400
450 800 450 1050

Now, both the value 300 and the value 400 would occur with greatest frequency, 4. Th
new data set would thus have two modes, 300 and 400.
17 / 21
 mean and the median, the median is usually preferred for data sets that have extreme
Pengantar Statistik Statistik Sampel
observations.
Figure 3.1 shows the relative positions of the mean and median for archetypal right-
skewed, symmetric, andMean, Median,
left-skewed and Mode
distributions. Generally, the mean and median are
exactly equal for an exactly symmetric distribution and are approximately equal for a
roughly symmetric distribution. The mean is usually greater than the median for a right-
skewed distribution and is usually less than the median for a left-skewed distribution; the
most common exceptions occur for discrete variables with only a few possible values.

URE 3.1
he mean
chetypal
tric, and Median Mean Median Mean Mean Median
ributions
(a) Right skewed (b) Symmetric (c) Left skewed

A resistant measure is not sensitive to the influence of a few extreme observations.

• Dimanakah
The nilai mode
median is a resistant dariof
measure ketiga
center,grafik dimean
but the atas?is not. A trimmed mean can
pplet 3.1
improve the resistance of the mean: removing a percentage
• Dari ketiga parameter di atas (mean, median, mode) of the smallest and largest
manakah
observations before computing the mean gives a trimmed mean. In Exercise 3.54, we
parameter
discuss trimmedyang
meanstepat untuk
in more menyatakan nilai ’center’?
detail.
The mode for each of Data Sets I and II differs from both the mean and the median.
Whereas the mean and the median are aimed at finding the center of a data set, the mode
is really not—the value that occurs most frequently may not be near the center.
It should now be clear that the mean, median, and mode generally provide different
information. There is no simple rule for deciding which measure of center to use in a
18 / 21
 Pengantar Statistik

Prosedur Komputasi
5 of the two
middle
values if n
is even Quartile1 2(Kuartil)
5 average of 2 and 12 1 12
n th n th
ordered values
Statistik Sampel

• Urutkan observasi dari nilai terkecil ke terbesar

• bagi jumlah observasi menjadi empat bagian yang sama besar
LE 1.15 People not familiar with classical music might tend to believe that a composer’s
instructions for playing a particular piece are so specific that the duration would
not depend at all on the performer(s). However, there is typically plenty of room
for interpretation, and orchestral conductors and musicians take full advantage
of this. The author went to the Web site ArkivMusic.com and selected a sample
of 12 recordings of Beethoven’s q1 Symphony No. 9 (the “Choral,”
q3 a stunningly
q2 = x̃
beautiful work), yielding the following durations (min) listed in increasing
Contoh:
order:
62.3 62.8 63.6 65.2 65.7 66.4 67.4 68.4 68.8 70.8 75.7 79.0
x +x 63.6 + 65.2
3 rights,4some third party content may be suppressed from the eBook and/or eChapter(s).
eserved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic
q =
ent does not materially affect the overall learning experience. Cengage 1
= = 64.4
Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.
2 2
x6 + x7 66.4 + 67.4
q2 = x̃ = = = 66.90
2 2

x9 + x10 68.8 + 70.8

q3 = = = 69.80
2 2

19 / 21
 5
middle
1 2
n 1 1 th
Pengantar Statistik
value if n 5 ordered value Statistik Sampel

is odd 2
,
x 5 The average Percentile (Persentil)
of the two
middle
12 1 2
n th n th
• Jika 0 ≤values
p ≤ 1,ifmaka
n xpaverage
5 adalahofpersentil
andke-100p,
1 1 jikaordered
100p%values
data
2 2
bernilai is
dieven
bawah xp dan 100(1 − p)% data bernilai diatasnya.

E 1.15 People not familiar with classical music might tend to believe that a composer’s
q1
instructions for playing a particular piece q3 that the duration would
arex̃so specific
q2 =
not depend at all on the performer(s). However, there is typically plenty of room
for interpretation, and orchestral conductors and musicians take full advantage
Persentil
of this. The author went to theke-25 Persentil ke-75
Web site ArkivMusic.com and selected a sample
of 12 recordings of Beethoven’s Symphony No. 9 (the “Choral,” a stunningly
Persentil ke-50
beautiful work), yielding the following durations (min) listed in increasing
• Contoh: Tentukan persentil ke-40 dari observasi:
order:
62.3 62.8 63.6 65.2 65.7 66.4 67.4 68.4 68.8 70.8 75.7 79.0

ved. May not be copied, scanned, or duplicated, in whole or in part. Due to electronic rights, some third party content may be suppressed from the eBook and/or eChapter(s).
does not materially affect the overall learning experience. Cengage Learning reserves the right to remove additional content at any time if subsequent rights restrictions require it.

20 / 21
Pengantar Statistik Statistik Sampel

Take away points

• Definisi dan cabang-cabang Statistik

• Istilah-istilah dalam statistik:
▶ Populasi
▶ Sampel
▶ Variabel dan jenis-jenisnya.
▶ Statistik Sampel: Mean, Variance, Median, Modus, Quartile, Percentile.

21 / 21