For Stanford writer only

lken82

ch._13.docx

Home >Business & Finance homework help >Accounting homework help >For Stanford writer only

· Statistics for Business and Economics, Ch. 13

Methods Of Forecasting The thread has 1 unread message.

created by MaDonna Keys

Last updated Mar 07, 2015, 10:59 PM

· Comment on Mar 07, 2015, 10:59 PM

Message collapsed. Message unread Methods Of Forecasting

posted by MaDonna Keys at Mar 07, 2015, 10:59 PM

Last updated Mar 07, 2015, 10:59 PM

According to investopedia when it comes forcasting there are a few different methods in which forecasts can be made. When it comes to the use of any method it falls into one of these two categories. The categories are qualitative and quantitative.

When it comes models that are Qualitative they are usually short term predictions. The forecast scope is limited. The qualitative forecasts is based on expert basis. They are dependent upon market mavens or the market as a whole the weighing of the informed consensus. The best used when it comes to predicting company successes based upon the short term and it meets the reliability measures based on opinions.

Quantitative methods it involves the discount of the expertise and tries to remove the human element out the analysis. This analysis is concerned only with data not much of relying on people. Variables that consist of gross sales, gross domestic products, and others. This kind of method is used on the basis of long terms measured in months to years.

Qualitative methods includes market research which involves polls of large numbers of people when it comes to a specific product and how many people will purchase that product. Delphi methods which includes the analysis of field experts.

Quantitative methods include the indicator approach, Econometric modeling, and Time Series.

Indicator approach this is relationship between particular indicators such as performance lagging or leading data. Econometric which involves the testing of consistency of data over a particular amount of time. Time Series refers to collections of past related data for future predictions of events.

Retrieved From The Basics Of Business Forecasting Accessed March 8,2015

index numers The thread has 4 unread messages.

created by ARIEL SMITH

Last updated Mar 07, 2015, 9:19 PM

· Comment on Mar 04, 2015, 12:42 PM

Message collapsed. Message unread index numers

posted by ARIEL SMITH at Mar 04, 2015, 12:42 PM

Last updated Mar 04, 2015, 12:42 PM

According to the text, a common technique for characterizing a business or economic time series is to compute index numbers. Index numbers measure how time series values change relative to a preselected time period, called the base period. There are two types of indexes used in business and economic: price and quantity indexes. Price indexes measure changes in the price of a commodity or group of commodities over time. One example of a price index is The Consumer Price Index (CPI) is a price index because it measures price changes of a group of commodities that are intended to reflect typical purchases of American consumers. An index constructed to measure the change in the total number of automobiles produced annually by American manufacturers would be an example of a quantity index.

McClave, J. T., Benson, P. G., & Sincich, T. (2010). Statistics for Business and Economics, 11th Edition. [VitalSource Bookshelf version]. Retrieved from http://online.vitalsource.com/books/9781269882163/id/ch13tab01

· Comment on Mar 05, 2015, 6:45 PM

Message collapsed. Message read Re: index numers

posted by LOUIS DAILY at Mar 05, 2015, 6:45 PM

Last updated Mar 05, 2015, 6:45 PM

Ariel,

Yes, and the CPI is the usual measure of inflation in the economy.

thanks

Lou

· Comment on Mar 06, 2015, 1:13 PM

Message collapsed. Message unread Re: index numers

posted by ARACHEAL VENTRESS at Mar 06, 2015, 1:13 PM

Last updated Mar 06, 2015, 1:13 PM

Ariel

Thanks for your thorough explanation of index numbers. An index number is one simple number that we can look at to give us a general overview of what is happening in a particular field. Another example of a real world number index is the Dow Jones International Average. The Dow Jones industrial average or DJIA for short, is a stock index. It measures the performance of 30 large public companies in the United States. These 30 companies are representative of companies in the whole of the United States and therefore, this index is mentioned in relation to how businesses in the United States are doing. If this index goes down, then that means companies in the United States are not doing well. If the index goes up, then that means businesses in the United States are doing well. This index is very important in the forecasting of how well our economy doing in terms of profit or deficit.

Reference

http://study.com/academy/lesson/index-numbers-in-statistics-uses-examples.html

· Comment on Mar 06, 2015, 2:04 PM

Message collapsed. Message unread Re: index numers

posted by STEPHANIE RECTOR at Mar 06, 2015, 2:04 PM

Last updated Mar 06, 2015, 2:04 PM

Hello Ariel and Aracheal, thanks for the insight on index numbers and examples. According to our readings, "Methods of calculating index numbers range from very simple to extremely complex, depending on the numbers and types of commodities represented by the index" (McClave, 2010). Index numbers that are based on price or quantity of one commodity is referred to as a simple index number. This number describes the relative changes through time in the price or quantity of that commodity. An example of this would be to construct a simple index to describe the relative changes in gold prices over the last 15 years. The year 2000 would be considered the "base period." The simple index number can be calculated for any chosen year by dividing that year's price by the price during the base year 2000, then multiplying the remaining by 100.

McClave, J. T., Benson, P. G., & Sincich, T. (2010). Statistics for Business and Economics, 11th Edition.

· Comment on Mar 07, 2015, 9:19 PM

Message collapsed. Message unread Re: index numers

posted by SAID SHEIK ABDI at Mar 07, 2015, 9:19 PM

Last updated Mar 07, 2015, 9:19 PM

Economists frequently use index numbers when making comparisons over time. An index starts in a given year, the base year, at an index number of 100. In subsequent years, percentage increases push the index number above 100, and percentage decreases push the figure below 100. An index number of 102 means a 2% rise from the base year, and an index number of 98 means a 2% fall.

Using an index makes quick comparisons easy. For example, when comparing house prices from the base year of 2005, an index number of 110 in 2006 indicates an increase in house prices of 10% in 2006.

The best-known index in the United States is the consumer price index, which gives a sort of "average" value for inflation based on price changes for a group of selected products. The Dow Jones and NASDAQ indexes for the New York and American Stock Exchanges, respectively, are also index numbers.

http://mathworld.wolfram.com/IndexNumber.html

Forecasting The thread has 9 unread messages.

created by LOUIS DAILY

Last updated Mar 07, 2015, 9:13 PM

· Comment on Mar 02, 2015, 11:41 AM

Message collapsed. Message unread Forecasting

posted by LOUIS DAILY at Mar 02, 2015, 11:41 AM

Last updated Mar 02, 2015, 11:41 AM

In the previous chapters, we studied Linear Regression. Let's say our Y variable is sales and our X variable is time (perhaps Jan, Feb, March, April, etc). If the X variable is time, we call this a time series. Can you think of a use for a regression line with this time series?

If we had three years of data, how many years ahead do you think we could predict using a regression line?

If each December sales went sky high because of Christmas, how could we adjust for this before constructing the regression line?

· Comment on Mar 03, 2015, 5:42 AM

Message collapsed. Message read Re: Forecasting

posted by ERIK SEIDEL at Mar 03, 2015, 5:42 AM

Last updated Mar 03, 2015, 5:42 AM

A regression line with a time series would be helpful in predicting future sales levels or other trends. For example, medical expenses for our health insurance company tend to fluctuate each year. Some years the flu is worse, and other years there is just heavier utilization than others. But if you create a time series of this data over a few years, you will see in almost every case that there is an overall increasing trend to medical expenses per member. This may be related to increases in our provider contracts, increased utilization of services, or a combination of the two. If we had three years of data, you could probably predict another five years into the future. However, consideration would have to be given to any expected material changes in the data to a change in the business, industry, etc. If trying to project sales and sales are higher each December, I think the best way to account for this would be to either include total year sales as the x variable or only look at year-to-year December sales as the x variable.

· Comment on Mar 03, 2015, 8:23 AM

Message collapsed. Message read Re: Forecasting

posted by LOUIS DAILY at Mar 03, 2015, 8:23 AM

Last updated Mar 03, 2015, 8:23 AM

Erik,

Time is usually the x variable, the independent variable. Then we plot the change in the y variable over time. After that, we "smooth" the data for random fluctuations, seasonality, etc. Finally, we use regression to model the trend (if any).

thanks

Lou

· Comment on Mar 04, 2015, 4:25 PM

Message collapsed. Message unread Re: Forecasting

posted by STEPHANIE RECTOR at Mar 04, 2015, 4:25 PM

Last updated Mar 04, 2015, 4:25 PM

Can you think of a use for a regression line with this time series?

If we had three years of data, how many years ahead do you think we could predict using a regression line?

If each December sales went sky high because of Christmas, how could we adjust for this before constructing the regression line?

A sequence of data points make up a time series and the successive measurements are made over a particular time frame. According to Wikipedia, "Time series are used in statistics, signal processing, pattern recognition, econometrics,mathematical finance, weather forecasting, earthquake prediction, electroencephalography, control engineering, astronomy,communications engineering, and largely in any domain of applied science and engineering which involves temporal measurements" (wikipedia.org). We can use time series forecasting to predict future value based on previous values. If we had three years of data we could predict ahead the next three to five years. It is when it is long term that time series can lag. Before constructing a regression line, we could adjust for the high December sales by "smoothing," which involves removing irregular fluctuations in a time series. This method essentially "smooths" out most residual effects.

References:

http://en.wikipedia.org/wiki/Time_series

· Comment on Mar 05, 2015, 6:39 PM

Message collapsed. Message unread Re: Forecasting

posted by LOUIS DAILY at Mar 05, 2015, 6:39 PM

Last updated Mar 05, 2015, 6:39 PM

Stephanie,

With three years of data, I think we can be comfortable with predicting one year ahead--any further out would be "on a limb".

thanks

Lou

· Comment on Mar 06, 2015, 1:06 PM

Message collapsed. Message unread Re: Forecasting

posted by ARACHEAL VENTRESS at Mar 06, 2015, 1:06 PM

Last updated Mar 06, 2015, 1:06 PM

Professor:

A time series is a sequence of data points, typically consisting of successive measurements made over a time interval. Examples of time series are ocean tides, counts of sunspots, and the daily closing value of the Dow Jones Industrial Average. Time series are very frequently plotted via line charts. Time series are used in statistics, signal processing, pattern recognition, econometrics, mathematical finance, weather forecasting, earthquake prediction, astronomy, and largely in any domain of applied science and engineering which involves temporal measurements.

Time series analysis comprises methods for analyzing time series data in order to extract meaningful statistics and other characteristics of the data. Time series forecasting is the use of a model to predict future values based on previously observed values. While regression analysis is often employed in such a way as to test theories that the current values of one or more independent time series affect the current value of another time series, this type of analysis of time series is not called "time series analysis", which focuses on comparing values of a single time series or multiple dependent time series at different points in time.

Reference

http://en.wikipedia.org/wiki/Time_series

· Comment on Mar 06, 2015, 11:56 PM

Message collapsed. Message unread Re: Forecasting

posted by Jynx Gresser at Mar 06, 2015, 11:56 PM

Last updated Mar 06, 2015, 11:56 PM

According to Gellert (n. d.), "it can be highly beneficial for companies to develop a forecast of the future values of some important metrics, such as demand for its products or variables that describe the economic climate" (para. 1). At my company, we have an actual daily, weekly, and monthly sales goal as well as a forecast which is based on previous sales data with a little lift. This would be an example of time series analysis because it provides an estimate of what we could achieve in sales. Another example could be gift set store inventory based on past dollar sales and this is particularly evident during important sales holidays, like Mother's Day. "It is possible to develop a linear regression model that simply fits a line to the variables historical performance and extrapolates that into the future" (Gellert, n. d., para. 4). Although, this line is unable to account for holidays where there are extreme values and nonlinearity (Gellert, n. d.). I would probably only predict one year out even with multiple years of data because this involves the most up to date knowledge for analysis. For December sales, I would adjust for the sky high sales by switching to a weekly sales liner regression. Unfortunately, December could be thrown out as an extreme value for the year, but if each week or another busy month was analyzed then we could understand its impact more effectively in regards to forecasting.

Reference

Gellert, A. (n. d.). Linear regression forecasting methods by companies. The Houston Chronicle. Retrieved from http://smallbusiness.chron.com/linear-regression-forecasting-method-companies-73112.html

Jynx Gresser

· Comment on Mar 07, 2015, 8:26 AM

Message collapsed. Message unread Forecasting

posted by CRYSTAL RAMOS at Mar 07, 2015, 8:26 AM

Last updated Mar 07, 2015, 8:26 AM

The use of historic data to determine the direction of future trends. Forecasting is used by companies to determine how to allocate their budgets for an upcoming period of time. This is typically based on demand for the goods and services it offers, compared to the cost of producing them. Investors utilize forecasting to determine if events affecting a company, such as sales expectations, will increase or decrease the price of shares in that company. Forecasting also provides an important benchmark for firms which have a long-term perspective of operations.

Stock analysts use various forecasting methods to determine how a stock's price will move in the future. They might look at revenue and compare it to economic indicators, or may look at other indicators, such as the number of new stores a company opens or the number of orders for the goods it manufactures. Economists use forecasting to extrapolate how trends, such as GDP or unemployment, will change in the coming quarter or year. The further out the forecast, the higher the chances that the estimate will be less accurate.

· Comment on Mar 07, 2015, 10:16 AM

Message collapsed. Message unread Re: Forecasting

posted by ERIK SEIDEL at Mar 07, 2015, 10:16 AM

Last updated Mar 07, 2015, 10:16 AM

There are numerous applications of using historical data to predict future results. Some of these include forecasting sales or expenses for future years, months, weeks, or even days. I think there are also many operational applications of using statistics to forecast future events that companies should take into consideration in order to maximize efficiency. For example, the customer service areas of companies often have peaks and valleys in workload. These may vary by time of day, week, month, or year. Companies that do not take these variations into account can be very inefficient and spend money and resources unnecessarily. Customer service departments that are most efficient will have a flexible staff and use statistical data from past experience to determine when to increase or decrease staffing.

· Comment on Mar 07, 2015, 5:25 PM

Message collapsed. Message unread Re: Forecasting

posted by TAMARQUES PORTER at Mar 07, 2015, 5:25 PM

Last updated Mar 07, 2015, 5:25 PM

Products that exhibit slow-moving demand or have sporadic demand require a specific type of statistical forecast model. Intermittent model works for products with erratic demand. Products with erratic demand do not exhibit a seasonal component; instead a graph drawn of the products demand attributes shows peaks and flat periods at intermittent points along the time series. The goal of this model is to provide a safety stock value instead of a forecast value. The safety stock value allows for just enough inventories to cover needs.

Forecasting new products remains one of the toughest forecasting tasks available. New product forecasting requires input from human and computer generated sources. New product forecasting methods seek to manage the high ramp up period associated with a new product introduction. These methods also work for maturing products approaching the end of their life cycle.

· Comment on Mar 07, 2015, 9:13 PM

Message collapsed. Message unread Re: Forecasting

posted by SAID SHEIK ABDI at Mar 07, 2015, 9:13 PM

Last updated Mar 07, 2015, 9:13 PM

Forecasting is the prediction of future events and conditions and is a key element in service organizations, especially banks, for management decision-making. There are typically two types of events: 1) uncontrollable external events - originating with the national economy, governments, customers and competitors and 2) controllable internal events (e.g., marketing, legal, risk, new product decisions) within the firm.

If we had three years of data, how many years ahead do you think we could predict using a regression line? I think we can easily predict a year

If each December sales went sky high because of Christmas, how could we adjust for this before constructing the regression line? We know the December is the peak sale month and we easily smooth by changing Y variable and then construct the regression line.

http://www.isixsigma.com/tools-templates/risk-management/use-forecasting-basics-predict-future-conditions/

Composite index number The thread has 4 unread messages.

created by ARIEL SMITH

Last updated Mar 07, 2015, 4:54 PM

· Comment on Mar 04, 2015, 12:51 PM

Message collapsed. Message unread Composite index number

posted by ARIEL SMITH at Mar 04, 2015, 12:51 PM

Last updated Mar 04, 2015, 12:51 PM

According to the text, a composite index number represents combinations of the prices or quantities of several commodities. The booked used a great example. To construct an index for the total number of sales of two major automobile manufacturers: General Motors and Ford. The first step you would have to do is collect data on the sales of each manufacturer during the period in which you are interested in. To summarize the information from both time series in a single index, we add the sales of each manufacturer for each year, we form a new time series consisting of the total number of automobiles sold by the two manufacturers. Then we construct a simple index for the total of the two series. The resulting index is called a simple composite index.

A simple composite index is a simple index for a time series consisting of the total price or total quantity of two or more commodities.

· Comment on Mar 05, 2015, 6:47 PM

Message collapsed. Message unread Re: Composite index number

posted by LOUIS DAILY at Mar 05, 2015, 6:47 PM

Last updated Mar 05, 2015, 6:47 PM

Ariel,

That example is a time series showing the fluctuation in the price of silver.

thanks

Lou

· Comment on Mar 07, 2015, 8:25 AM

Message collapsed. Message unread Composite index number

posted by CRYSTAL RAMOS at Mar 07, 2015, 8:25 AM

Last updated Mar 07, 2015, 8:25 AM

A grouping of equities, indexes or other factors combined in a standardized way, providing a useful statistical measure of overall market or sector performance over time.

Also known simply as a "composite".

Usually, a composite index has a large number of factors which are averaged together to form a product representative of an overall market or sector. For example, the Nasdaq Composite index is a market capitalization-weighted grouping of approximately 5,000 stocks listed on the Nasdaq market. These indexes are useful tools for measuring and tracking price level changes to an entire stock market or sector. Therefore, they provide a useful benchmark against which to measure an investor's portfolio. The goal of a well diversified portfolio is usually to outperform the main composite indexes.

· Comment on Mar 07, 2015, 4:54 PM

Message collapsed. Message unread Re: Composite index number

posted by JUDEENE WALKER at Mar 07, 2015, 4:54 PM

Last updated Mar 07, 2015, 4:54 PM

Compose index numbers are in dices calculated to reflect the change in activity of a number of items from the base period to the period under consideration. CIN allows us to measure with a single number, the relative variations within a group of variables upon moving from on situation to another. The aim of using composite index numbers is to summarize all the simple index numbers contained in a complex number into just one index.

Example: the index of prices for taxi is 100 compared to a given base year. The index for rental is 160 (using the same base year). Calculate the composite index for taxi and rent using a weighting of 55 for taxi and 45 for rental using the composite index formula: total of index/ total weighting.

CI= (100*55+ 160*45)/ (55+45) = 12,700/100= 127

The first message in the thread has been removed

created by ARIEL SMITH

Last updated Mar 04, 2015, 12:51 PM

· Comment on Mar 04, 2015, 12:50 PM

This message has been removed

Message collapsed.