Anda di halaman 1dari 30

Bab 14

Peramalan &

Mengurangi Risiko Pengambilan Keputusan

Ringkasan - Tinjau Topik Sebelumnya

• Penelitian didefinisikan sebagai pengujian dalam pencarian untuk suatu produk, sementara pengembangan berarti
menerjemahkan penelitian yang menjadi desain untuk produk baru.

• R & D dapat diklasifikasikan sebagai produk baru , Perangkat tambahan untuk produk saat ini, proyek yang diminta
oleh penjual dan pemasaran, proyek-proyek yang diminta oleh pabrik, dan proyek-proyek fundamental memiliki
tidak ada penggunaan komersial segera.

• Manajer harus terus menilai program R & D. Jika proyek R & D tertentu memiliki biaya yang berlebihan
dan penundaan, kelayakan proyek yang mungkin dipertanyakan.

• Manajer harus memutuskan di mana untuk mengarahkan upaya R & D dan berapa banyak untuk dibelanjakan.
Proyek alternatif terbaik harus dipilih, dan kemajuan pada proyek diawasi secara ketat

• In business, forecasts form the basis for planning capacity, production and
inventory, staffing, sales and market share, finances and budgeting,
research and development, and top management’s strategy.

• The objective of forecasting is to reduce risk in decision making.

• Forecasts are needed for marketing, production, purchasing, staffing, and

financial planning. Further, top management needs forecasts for planning
and implementing long-term strategic objectives and planning for capital

The company may choose from a wide range of forecasting techniques. There are basically two approaches to
forecasting: qualitative and quantitative:

1. Qualitative approach—forecasts based on judgment and opinion & Expert opinions

& Delphi method & Sales-force polling & Consumer surveys

2. Quantitative approach
Forecasts based on historical (time series) data
& Naive methods & Moving
average & Exponential
smoothing & Trend analysis

& Classical decomposition

Associative (causal) forecasts
& Simple regression & Multiple
regression & Econometric

• The choice of a forecasting technique is influenced significantly by the stage of the product life cycle. In the
beginning of the product life cycle, relatively small
expenditures are made for research and market investigation. During the first phase of product introduction,
these expenditures start to increase. In the rapid growth
stage, considerable amounts of money are involved in the decisions, so a high level of accuracy is desirable. After
the product has entered the maturity stage, the decisions are more routine, involving marketing and
manufacturing. These are important considerations when determining the appropriate sales forecast

• What technique or techniques you should select depends on six criteria:

1. What is the cost associated with developing the forecasting model, compared with
potential gains resulting from its use? The choice is one of benefit-cost trade-off .
2. How complicated are the relationships that are being forecasted?
3. Is it for short-term or long-term purposes?
4. How much accuracy is desired?
5. Is there a minimum tolerance level for errors?
6. How much data is available ? Techniques vary in the amount of data they require.

Four of the better-known qualitative forecasting methods are:

1. Expert Opinions

The subjective views of experts from sales, production, finance, purchasing, and administration are averaged to generate a
forecast about future sales. Usually this method is used in conjunction with some quantitative method, such as trend
extrapolation. The management team modifies the resulting forecast, based on their expectations.

• The advantage of this approach is that the forecasting is done quickly and easil y, without need of elaborate statistics. Also,
the jury of executive opinions may be the only means of forecasting feasible in the absence of adequate data.

• The disadvantage, however, is groupthink, a set of problems inherent to those who meet as a group. Foremost among
these problems are high cohesiveness, strong leadership, and the
insulation of the group . Dengan kekompakan yang tinggi, kelompok semakin sesuai melalui tekanan teman sebaya yang menghambat
pertikaian dan pemikiran kritis. Kepemimpinan yang kuat mendorong tekanan kelompok untuk pendapat bulat. Isolasi kelompok
cenderung untuk memisahkan kelompok dari pendapat luar, jika diberikan.

2. Metode Delphi

Dalam teknik kelompok metode Delphi, sebuah panel ahli dipertanyakan secara individual tentang persepsi mereka tentang peristiwa masa depan.
Para ahli tidak memenuhi sebagai kelompok, yang mengurangi kemungkinan bahwa
konsensus tercapai karena faktor kepribadian yang dominan. Sebaliknya, perkiraan dan argumen yang menyertainya
dirangkum oleh pihak luar dan kembali ke ahli, bersama dengan pertanyaan lebih lanjut. Ini terus berlanjut sampai
konsensus tercapai.

jenis metode yang berguna dan cukup efektif untuk peramalan jangka panjang. Karena dilakukan dalam format kuesioner,
menghilangkan kerugian dari groupthink. Tidak ada komite atau debat; para ahli tidak dipengaruhi oleh tekanan teman sebaya
untuk meramalkan dengan cara tertentu.

keandalan rendah dan kurangnya konsensus dari hasil dikutip sebagai kelemahan utama dari metode Delphi.

3. Penjualan-Force Polling

• Beberapa perusahaan menggunakan sebagai tenaga penjualan sumber perkiraan yang memiliki kontak terus-menerus dengan pelanggan. Mereka percaya
bahwa tenaga penjual yang yang paling dekat kepada pelanggan akhir mungkin memiliki wawasan yang signifikan mengenai keadaan pasar masa depan.

• Keuntungan dari perkiraan ini adalah:

• ini mudah digunakan dan mengerti; Ia menggunakan pengetahuan khusus dari orang-orang terdekat tindakan.

• It can place responsibility for attaining the forecast in the hands of those who most affect the actual results.

• The information can be broken down easily by territory, product, customer, or salesperson.

The disadvantages include salespeople’s being overly optimistic or pessimistic regarding their predictions, as well as
inaccuracies due to broader economic events that are largely beyond their control.

4. Consumer Surveys

• Some companies conduct their own market surveys regarding specific consumer purchases. Surveys may use telephone
contacts, personal interviews, or questionnaires as a means of obtaining data.

• Extensive statistical analysis usually is applied to survey results to test hypotheses regarding consumer behavior.

There are six basic steps in the forecasting process:

1. Determine the what and why of the forecast and what will be needed. This will indicate
the level of detail required in the forecast (e.g., forecast by region, by product), the amount of resources (e.g.,
computer hardware and software, staff) that can be justified, and the level of accuracy desired.

2. Establish a time horizon , short-term or long-term. More specifically, project for the next year or next five years.

3. Select a forecasting technique. Refer to the criteria discussed before.

4. Gather the data and develop a forecast.

5. Identify any assumptions that had to be made in preparing the forecast and using it.

6. Monitor the forecast to see if it is performing in a manner desired. Develop an evaluation

system for this purpose . If not, go back to Step 1.
Chapter 15
Moving Averages &
Smoothing Techniques
Quantitative Forecasting

• Naive forecasting models are based exclusively on historical observation of sales or other variables, such as earnings and cash
flows. They do not attempt to explain the underlying causal relationships that produce the variable being forecasted.

• Naive models may be classified into two groups. One group consists of simple projection models. These models require inputs of
data from recent observation, but no statistical analysis is performed. The second group is made up of models that, while naive,
are complex enough to require a computer. Traditional methods such as classical decomposition, moving average, and
exponential smoothing
models are some examples.

• The advantage of naive models is that they are

inexpensive to develop and operate. The disadvantage is
that they do not consider any possible causal relationships
that underlie the forecasted variable.

• The naive models can be applied, with little need of a computer, to develop forecasts for sales,
earnings, and cash flows. They must be compared with more sophisticated models, such as the
regression method, for forecasting efficiency.
Smoothing TEKNIK

• Smoothing techniques are a higher form of naive model. The two typical forms are
moving averages and exponential smoothing.

• Moving averages are averages that are updated as new information is received. With the moving average, a
manager simply employs the most recent observations to calculate an average, which is used as the forecast for
the next period.

• Advantages and Disadvantages

Rata-rata bergerak adalah mudah digunakan dan mudah dimengerti. Namun, ada dua

1. Hal ini membutuhkan pengguna untuk mempertahankan banyak data dan membawanya bersama mereka dari perkiraan
periode untuk meramalkan masa.

2. Semua data dalam sampel yang equall tertimbang y. Jika data yang lebih baru yang lebih valid dari data yang lebih tua, mengapa tidak memberi mereka
bobot yang lebih besar?

Metode peramalan dikenal sebagai pemulusan eksponensial mendapat sekitar kelemahan ini.
Exponential Smoothing

• pemulusan eksponensial adalah populer teknik di antara manajer untuk peramalan jangka pendek . Ini menggunakan rata-rata
tertimbang dari data masa lalu sebagai dasar untuk perkiraan. Prosedur memberikan bobot terberat untuk informasi yang lebih
baru dan kurang berat badan pengamatan di lebih
jauh masa lalu . Alasannya adalah bahwa masa depan lebih tergantung pada masa lalu dari pada masa lalu.

• This method is known to be effective when there is randomness and no seasonal

fluctuation in the data.

• One disadvantage of the method,

however, is that it does not include industrial

or economic factors such as market conditions,

prices, or the effects of competitors’ actions.

Exponential Smoothing
Exponential Smoothing
Chapter 16
Regression Analysis
Popular Sales Forecast System
Regression Analysis is …………………..

• A statistical procedure for mathematically estimating the average

relationship between the dependent variable and the independent variable(s).

• Simple regression involves one independent variable, price or advertising in a demand

function, whereas multiple regression involves two or more variables, such as price and
advertising together.

• In this chapter, we will discuss simple (linear) regression (i.e.,Y ¼ a þ bX) to illustrate the
least-squares method. Multiple regression is reserved for a forecasting text.

• The least-squares method is widely used in regression analysis for estimating the parameter values
in a regression equation. The regression method includes all the observed data and attempts to find
a line of best fit. To find this line, a technique called the least-squares method is used. Exhibit 16.1
shows the regression relationship

Regression analysis is a statistical method. Therefore, it uses a variety of statistics to tell about
the accuracy and reliability of the regression results. They include:

• Correlation coefficient (r) and coefficient of determination (R2)

• Standard error of the estimate (Se) and prediction confidence interval
• Standard error of the regression coefficient (Sb) and t-statistic

Correlation Coefficient (r) and Coefficient of Determination (R2)

• The correlation coefficient r measures the degree of correlation between Y

and X. The range of values it takes on is between -1 and 1.

• More widely used, however, is the coefficient of determination, designated R2. Simply put, R2 tells us
how good the estimated regression equation is. In other words, it is a measure of goodness of fit in
the regression. Therefore, the
higher the R2, the more confidence we have in our estimated equation.

• More specifically, the coefficient of determination represents the proportion of the total variation in Y
that is explained by the regression equation. It has a range of values between 0 and 1 .
Correlation Coefficient (r) and Coefficient of Determination
Standar Kesalahan dari Estimate (Se) dan Prediksi
Confidence Interval
Standar Kesalahan dari Estimate (Se) dan Prediksi
Confidence Interval
Standar Kesalahan dari Estimate (Se) dan Prediksi
Confidence Interval
Standar Kesalahan dari Koefisien Regresi (Sb) dan
Standar Kesalahan dari Koefisien Regresi (Sb) dan
Kelompok diskusi

• Silahkan meramalkan jangka pendek dan jangka panjang (5 tahun) Anda (masing-masing) 7 perusahaan menggunakan:

• Kualitatif (Pilih satu)

• Kuantitatif (Pilih satu)


14-16: Peramalan & Perencanaan

• Manajer menggunakan perkiraan untuk tujuan penganggaran. Sebuah ramalan bantu dalam menentukan volume produksi, kebutuhan
persediaan, jam kerja yang dibutuhkan, kebutuhan kas, dan kebutuhan pembiayaan.

• Berbagai metode peramalan yang tersedia. Namun, pertimbangan harus diberikan untuk biaya, waktu persiapan,
akurasi, dan periode waktu.

• Manajer harus memahami dengan jelas asumsi yang metode perkiraan tertentu berdasarkan untuk
mendapatkan manfaat maksimal.

• Berbagai metode peramalan kuantitatif ada. teknik naif hanya didasarkan pada
pengalaman sebelumnya . Smoothing pendekatan termasuk rata-rata bergerak dan eksponensial
smoothing. Moving average dan pemulusan eksponensial mempekerjakan rata-rata tertimbang dari data masa lalu sebagai sarana
menurunkan ramalan

• analisis regresi adalah pemeriksaan efek dari perubahan variabel independen terhadap variabel
dependen. Ini adalah metode yang populer digunakan untuk meramalkan penjualan. Bab ini membahas
teknik estimasi terkenal, disebut metode leastsquares.