**126**

THE PROBLEM AND ITS BACKGROUND

Introduction

Business firms whether small or big has engaged several challenges before and after its growth. It undergoes study of the entire business. Efficient and effective decisions in business are needed to implement every day. The business manager has the responsibility to make decisions for the improvement of the company.

To make this be possible, forecasting of sales is necessary. Sales forecast is a prediction based on past sales performance and an analysis of expected market conditions (Evetts, 1990).

It can help the marketer develop marketing strategies such as in territorial set-up, target market or the product distribution, pricing schemes or moves, promotions and competition and marketing support. It helps to allocate marketing resources and monitor the productive environment. The marketing company should have the strategies and techniques for achieving the sales target.

This sales target is the company’s sales objective. Sales should be monitored time to time whether they are gaining or loosing investment. Sufficient knowledge in forecasting must acquire by the business manager.

Supervising a sales forecast will yield the business firm with an evaluation of past and current sales levels and annual growth. And this will authorize the company to compare it to other business firms. Through this, the marketer can establish new policies for easy monitoring product’s prices and operating costs to earn profits. And by implementing the accurate sales forecast to the entire firm may increase the company’s efficiency and revenue and may decrease cost. BACKGROUND OF THE STUDY

A corporation located at Manresa, Quezon City, Health-Tech Medical Inc. is one of the exclusive distributors of medical supplies and equipment’s and provides respiratory care and home health services and rentals here in the Philippines. It is recently known as Magwin Marketing Corporation has its five years of providing medical supplies and equipment’s and services. Magwin Marketing Corporation existed for ten years. Health-Tech Medical Inc. is the exclusive distributor of Ansell healthcare, Hudson RCI, Abbott Vascular, Top Corporation, Invacare, Covidien, Apex Medical, Edan Instruments, Primedic, Clevemed, MDF-Instruments. Health-Tech Medical Inc. distributes high quality and branded medical equipment’s and good services for almost 658 hospitals and clinics. It is now serving and improving the quality and affordability of the products and efficient service. In this study, the researcher will use the 2007 to 2009 sales of Ansell Healthcare products in National Capital region branch to predict its 2010 sales.

Measuring the accuracy of the forecasting using different method is done to determine the forecast error. The corporation may use this study for their preparation of decision making. The corporation should have its sales forecast for every product’s groups. It should also have semi-annually or year to year forecast for the reason of the more often the forecast the better the chances of corporation’s efficiency and effectiveness. Objectives of the Study

The study aims to determine the future sales of Health-Tech Medical Inc. in Ansell products for the year 2010. Specifically, the researchers want to achieve the following objectives: 1. To determine the model that will suit the Ansell sales data. 2. To predict the 2010 sales of Ansell Healthcare products.

3. To determine the forecast error for the year 2010.

4. To compare the forecast sales of Ansell products between researchers’ and company’s method.

Statement of the Problem

The researcher would like to answer the following question: 1. What models will suit the Ansell; a. Powdered gloves sales b. Free-Powdered gloves sales? 2. What are the future sales of Ansell Powdered and Free-Powdered gloves sales for the year 2010? 3. What is the forecast error using; a. Actual data sales b. Deseasonalized data sales? 4. Which is more effective method in forecasting the Ansell Healthcare products between the researchers’ and company’s method to be used? Significance of the Study

The study aims to provide a precise sales forecast for Ansell products to help Health-Tech Medical Inc on its management for greater improvement. It will contribute ideas to the manager for making decisions for the preparation in coming years. It helps them in determining the business if it is just surviving or being highly successful. This means that this research can be a company’s tool for their forecasting of sales.

This study not only serves as great part for the completion of the researchers’ course requirement but leads the researchers discover new knowledge partly in the field of mathematics and also in business management. The researchers having this study face a lot of challenges and develop their self-esteem. It gives also knowledge to those students seeing him in the business industry. Scope and Limitation of the Study

This study is focus on predicting the 2010 sales of Ansell Healthcare products of National Capital Region branch using their 2007 to 2009 sales of it. The researchers will use trend projection to predict the product 2010 sales. Mean square error (MSE), Mean Absolute Deviation (MAD), Mean Absolute Percentage Error (MAPE) will be applied to determine the error in a forecast. The researchers also compare the method there used to the company’s method.

CHAPTER II

REVIEW OF RELATED LITERATURE AND STUDIES

This chapter presents the related articles and information which are the partial bases which help development of the study. 2.1 Forecasting

Forecasting can broadly considered as a method or technique for estimating many future aspects of a business or other operation. There are many kinds of forecasting like weather forecasts and those anticipate future economic events, conditions , traffic patterns and even in the size and number of classrooms that will be needed in local schools. In this study the researchers will define forecasting as examining historical data to predict the event that may take place in the future.

Business forecasting uses past figures to predict short term or long term performance. It helps the managers to make better decisions to prepare for the future. Forecast can be classified as either short range, medium or long range forecast. Sales forecasting uses past figures to predict short-term or long-term performance. It’s a tricky job, because so many different factors can affect

future sales: economic downturns, employee turnover, changing trends and fashions, increased competition, manufacturer recalls and other factors.

But there are several standard methods that can produce consistently accurate sales forecasts from year to year.fluctuations might be mistaken for long-term trends if baseline data is from only one year. Before you start forecasting, remember that revenue projections are only as meaningful as your baseline data. Make sure that a.) the data is ordered from earliest to most recent. b.) No data is missing. If data is unavailable for a period, enter an estimate. c.) All periods are for comparable amounts of time, such as weeks, months, or years. Businesses are forced to look well ahead in order to plan their investments, launch new products, and decide when to close or withdraw products and so on.

The sales forecasting process is a critical one for most businesses. Key decisions that are derived from a sales forecast include: Employment levels required, Promotional mix and Investment in production capacity.. The factors that should be consider are (1)The degree of accuracy required – if the decisions that are to be made on the basis of the sales forecast have high risks attached to them, then it stands to reason that the forecast should be prepared as accurately as possible. However, this involves more cost(2) The availability of data and information – in some markets there is a wealth of available sales information (e.g. clothing retail, food retailing, holidays); in others it is hard to find reliable, up-to-date information(3) The time horizon that the sales forecast is intended to cover.

For example, are we forecasting next weeks’ sales, or are we trying to forecast what will happen to the overall size of the market in the next five years?(4) The position of the products in its life cycle. For example, for products at the “introductory” stage of the product life cycle, less sales data and information may be available than for products at the “maturity” stage when time series can be a useful forecasting method. According to Sonny Ramirez there are Seven reasons to practice sales forecasting .A common fault among start-up businesses, especially those in retail and manufacturing, is that they have too much product, too few of a product, or the wrong kind of product available to sell to their customers when they want it or need it.

That’s why it is important for entrepreneurs and business owners to learn and practice sales forecasting, which is nothing like predicting the weather yet is both a science and an art. Making a sales forecast is essentially predicting your sales based on your past sales performance and your analysis of expected market condition Making a forecast forces the entrepreneur to look at the future objectively. Taking note of the past helps the business owner stay aware of the present and helps him analyze precisely that information to see into the future. Forecasting helps you take the “pulse” of your company. Second to world-class customer service, sales forecasting is the lifeblood of a company.

It is a self-assessment tool to help you know how healthy your firm is. A forecast reports, graphs and analyzes the pulse of your business; it can make the difference between just surviving and being highly successful. An accurate forecast can also help launch new products (and discontinue old ones), and chart your company’s future direction. Forecasting enhances your company’s cash flow. A forecast lets you know how much you could earn in a particular period of time. From this, you will know if you will have the cash to afford, for instance, hiring new employees, buying new equipment or expanding your business. A strong forecast also helps businesses make .loans and secure financing, as it demonstrates to lenders the potential revenue the business can make. 2.3 Forecasting by trend projection

This mathematical method fits a trend line to set the past observations projecting the line into the future The first step after gathering of the past data before any forecast , any forecast could be undertaken is to establish the trend equation using the trend equation , forecast could be computed Formula for the trend line :Y=a+bx

2.1 Coefficients

This quantity, R2, is called the coefficient of determination. The R2 value of trend line helps to determine how the trend lines are reliable. You don’t have to understand all about the R2 values you just have to remember where the R2 is at or near to 1 the trend line is more reliable. It also helps to understand the types of trend line that are likely to fit different scenarios. 2.2 Regression analysis

Regression is the study of relationships among variables, principal purpose of which is to predict, or estimate the value of 1 variable related to it. The regression analysis maybe linear or multiple. With the linear regression, analyst develops a relationship between sales and single independent variable and use this relationship to forecast sales. With multiple regression , analyst examine relationship between sales and the number of independent variables.

Usually the latter accomplish with the help of computer that helps the analyst to estimate the values of the independent variables and to incorporate them into a multiple –regression equation. If analyst finds the relationship among various independent variables, they can develop a multiple regression equation for predicting sales for the coming year. 2.3 Analysis of variance

Analysis of variance (ANOVA) is a collection of statistical models, and their associated procedures, in which the observed variance in a particular variable is partitioned into components attributable to different sources of variation. In its simplest form ANOVA provides a statistical test of whether or not the means of several groups are all equal, and therefore generalizes t-test to more than two groups.

ANOVAs are helpful because they possess an advantage over a two-sample t-test. Doing multiple two-sample t-tests would result in an increased chance of committing a type I error. For this reason, ANOVAs are useful in comparing three or more means. Costs of production are affected by internal factors over which management has a large degree of control.

An important job of executive management is to help the members of various management levels understand that all of them are part of the management team. Standard costs and their variances are an aid to keeping management informed of the effectiveness of production effort as well as that of the supervisory personnel. Supervisors who often handle two thirds of three fourth of the dollar cost of the product are made directly responsible for the variance which, show up as materials variances (price, quantity, mix, and yield) or as direct labor variances (rate and efficiency). Materials and labor variances can be computed for each materials item, for each labor operation, and for each worker. Factory overhead variances (spending, controllable, idle capacity, volume, and efficiency) indicate the failure or success of the control of variable and fixed overhead expenses in each department.

Variances are not ends in themselves but springboards for further analysis, investigation, and action. Variances also permit the supervisory personnel to defend themselves and their employees against failures that were not their fault. A variance provides the yardstick to measure the fairness of the standard, allowing management to redirect its effort and to make reasonable adjustments. Action to eliminate the causes of undesirable variances and to encourage and reward desired Variance analysis helps management to understand the present costs and then to control future costs. Variance analysis is also used to explain the difference between the actual sales dollars and the budgeted sales dollars.

2.4 F-test

An F-test is any statistical test in which the test statistic has an F-distribution under the null hypothesis. It is most often used when comparing statistical models that have been fit to a data set, in order to identify the model that best fits the population from which the data were sampled. Exact F-tests mainly arise when the models have been fit to the data using least squares.

An F-test is any statistical test in which the test statistic has an F-distribution under the null hypothesis. It is most often used when comparing statistical models that have been fit to a data set, in order to identify the model that best fits the population from which the data were sampled. Exact F-tests mainly arise when the models have been fit to the data using least squares.

CHAPTER III

Methods and Procedures

Method of Research

The research method used in this study is applied mathematics with a main subject of forecasting. The forecasting method the researchers’ applied is quantitative by trend projection under time series. Data Gathering Procedure

When the manager of Health-Tech Medical Incorporation accede our request to conduct our research referring to their corporation as great part of our subject study, we quiet easily get the list of sales of all the products of Ansell Healthcare under the said corporation. We had a formal conversation to the manager regarding to the corporation such as its history, distribution of products and also information about the sales. The conversation leads the researchers to gain knowledge about sales forecasting. Mathematical Methods and Procedures

The data gathered by the researchers were categorized according to branches of the corporation, months and products’ sales. The data were organized to facilitate the presentation and interpretation of result using the following: Least-Square Methods.

Scattered Diagram. The data is displayed as a collection of points, each having the value of one variable determining the position on the horizontal axis and the value of the other variable determining the position on the vertical axis. Trend line. The linear trend equation is = a + bt

–

= Forecast for period t

b = Slope of the line

t = Specified number of time periods from t = 0

Analysis of Variance (ANOVA)- is a collection of statistical models, and their associated procedures, in which the observed variance in a particular variable is partitioned into components attributable to different sources of variation. For easier computation or determining the behavior of the sales data, the researchers used the SPSS. SPSS (Statistical Package for the Social Sciences) – is a computer program used for statistical analysis. Moving average – used with time series data to smooth out short-term fluctuations and highlight longer-term trends or cycles. This method is used to come up with deseasonalized data and this data will use in least- square-method. Forecast Accuracy

Mean Squared Error (MSE) represents the variance of errors in a forecast. This criterion is most useful if you want to minimize the occurrence of a major error(s). where: = actual value in period t,

= forecasted value in period t,

n = number of periods.

Mean Absolute Deviation (MAD) measures the average absolute error of a forecast. A sign of an error, which represents over- or underestimation, is really not important in most cases; we are rather concerned with the value of deviation.

where: actual value in period t,

= forecasted value in period t,

n = number of periods

Mean absolute percentage error (MAPE) is measure of accuracy in a fitted time series value in statistics. It usually expresses accuracy as a percentage, and is defined by the formula:

where :

At = actual value

Ft = the forecast value.

Company method’s in forecasting

where :

= the previous value

= the forecast value

CHAPTER IV

PRESENTATION, ANALYSIS AND INTERPRETATION OF DATA

This chapter presents the tables and graphs with interpretation to obtain the objectives of the study. 4.1 Scattered Diagram of Actual Data Sales

Using a scattered diagram, the researchers observe the relationship between the independent variable x, the period which is quarterly and dependent variable y, the actual sales.

Fig 1.a Actual Sales of Ansell powdered gloves

Fig. 1.b Actual Sales of Ansell free-powdered gloves

The actual data sales of Ansell powdered and free-powdered gloves are plotted

in fig.1.a and fig. 1.b showing a scatter diagram. From an inspection of this scatter diagram, it seen that the points are not closely follow a straight line, indicating that the assumption of linearity between the two variables appear to be weak. 4.2 ANOVA of Actual Sales

Using the software Statistical Package for the Social Sciences (SPSS), researchers interpret the relationship between the independent variable which is the time and the dependent variable sales. Table 1.a. ANOVA of Powdered Gloves Actual Sales

ANOVAb

Model

Sum of Squares

df

Mean Square

F

Sig.

Regression

8.933E12

1

8.933E12

2.972

.115a

Residual

3.005E13

10

3.005E12

Total

3.899E13

11

a. Predictors: (Constant), quarter

b. Dependent Variable: powdered gloves actual sales

Table 1.b. ANOVA of Free-Powdered Gloves Actual Sales

ANOVA

Model

Sum of Squares

Df

Mean Square

F

Sig.

1

Regression

5.583E11

1

5.583E11

2.972

.115a

Residual

1.878E12

10

1.878E11

Total

2.437E12

11

a. Predictors: (Constant), quarter

b. Dependent Variable: free-powder gloves actual sales

The ANOVA tables of actual sales for powdered and free-powdered gloves show that f -value is 2.972; it should be f > 4.84 for it to be have a significant difference. The researcher should accept that there is no significant difference because p-value is 0.115 which is greater than 0.05.Which means that independent variable is not good predictor. 4.3

Coefficients of Actual Sales

Table 2.a Coefficients of Powdered Gloves Actual Sales

Coefficientsa

Model

Unstandardized Coefficients

Standardized

Coefficients

t

Sig.

B

Std. Error

Beta

1

(Constant)

6811083.552

1066961.619

6.384

.000

quarter

249939.081

144971.536

.479

1.724

.115

a. Dependent Variable: powdered gloves actual sales

Coefficientsa

Model

Unstandardized Coefficients

Standardized Coefficients

t

Sig.

B

Std. Error

Beta

1

(Constant)

1702770.888

266740.405

6.384

.000

quarter

62484.770

36242.884

.479

1.724

.115

a. Dependent Variable: free-powder gloves actual sales

Table 2.b Coefficients of Free-Powdered Gloves Actual Sales

The table 2.a and table 2.b show the value of Beta which refers to the slope of the trend line or the regression line. If the Beta is greater than 0, there is a positive slope which means an increasing in sales. If the Beta is less than 0, there is a negative slope which means a decreasing in sales. It shows that the value of Beta is 0.479 which means a weak positive slope or a slowly increasing of sales. 4.4 Forecast Actual Sales Data through Regression Analysis

The researcher used trend analysis under regression as a forecasting model for actual sales of powdered and free-powdered gloves of Ansell products, where in the independent variable x represents the period which is quarterly and the dependent variable y represents the actual sales of powdered and

free-powdered gloves.

Table 3.a Forecasted Powdered Actual Data

Quarter

Powdered gloves actual sales

Forecasted sales

Error

1

6407696.80

7061022.63

653325.83

2

9237339.20

7310961.71

1926377.49

3

5398065.28

7560900.79

2162835.51

4

7610841.60

7810839.87

199998.27

5

7680611.19

8060778.95

380167.76

6

9984032.87

8310718.03

1673314.84

7

6907124.34

8560657.11

1653532.77

8

11218473.90

8810596.19

2407877.71

9

8415425.36

9060535.27

645109.91

10

11466674.32

9310474.35

2156199.97

11

7429096.98

9560413.43

2131316.45

12

9472869.12

9810352.51

337483.39

13

8921114.40

10060291.59

1139177.19

14

10155296.80

10310230.67

154933.87

15

10937636.80

10560169.75

377467.05

16

10986546.68

10810108.83

176437.85

Table 3.b Forecasted Free-Powdered Actual Sales

Quarter

Free-powdered gloves Actual sales

Forecasted Sales

Error

1

1601924.20

1765255.66

163331.46

2

2309334.80

1827740.43

481594.37

3

1349516.32

1890225.20

540708.88

4

1902710.40

1952709.97

49999.57

5

1920152.80

2015194.74

95041.94

6

2496008.22

2077679.51

418328.71

7

1726781.09

2140164.28

413383.19

8

2804618.48

2202649.05

601969.43

9

2103856.34

2265133.82

161277.48

10

2866668.58

2327618.59

539049.99

11

1857274.25

2390103.36

532829.11

12

2368217.28

2452588.13

84370.85

13

2230278.60

2515072.90

284794.30

14

2538824.20

2577557.67

38733.47

15

2734409.20

2640042.44

94366.76

16

2746636.67

2702527.21

44109.46

The table 3.a and table 3.b show the forecasted value and error of the powdered and free-powdered gloves actual sales. The researchers came up with a model Y = ax + b where a is the intercept of the regression line with the y axis, b is the slope of the trend line and x corresponds to the quarterly in a year. Y=6811083.55x + 249939.08 for powdered gloves and Y= 1702770.89 + 62484.77 for free-powdered gloves.

4.5 Scattered Diagram of Deseasonalized Data Sales

The scattered diagram is one way to observe if there is a linear relationship between the independent variable and the dependent variable.

Fig.2.a. Deseasonalized Sales of Ansell Powdered data

Fig 2.b Deseasonalized Sales of Ansell Free-Powdered Gloves

After the data undergo to a process called moving average, the researcher noticed in fig. 2.a and fig. 2.b that almost the points are nearer to the trend line. This means that data became smoothes when the seasonal effect was removed. 4.6 ANOVA of Deseasonalized Data Sales

Using the software Statistical Package for the Social Sciences (SPSS), researchers interpret the relationship between the independent variable which is the time and the dependent variable sales. Table 4.a ANOVA of Powdered Gloves

ANOVAb

Model

Sum of Squares

df

Mean Square

F

Sig.

1

Regression

8.837E12

1

8.837E12

17.735

.002a

Residual

4.983E12

10

4.983E11

Total

1.382E13

11

a. Predictors: (Constant), quarter

b. Dependent Variable: powdered gloves deseasonalized data

Table 4.b ANOVA of Free- Powdered Gloves

ANOVAb

Model

Sum of Squares

df

Mean Square

F

Sig.

1

Regression

5.523E11

1

5.523E11

17.735

.002a

Residual

3.114E11

10

3.114E10

Total

8.637E11

11

a. Predictors: (Constant), quarter

b. Dependent Variable: free-powdered gloves deseasonalized data

The ANOVA tables of actual sales for powdered and free-powdered gloves show that f -value is 17.735; it should be f > 4.84 for it to have a significant difference. The researchers should reject that there is no significant difference because p-value is 0.002 which is less than 0.05 which means that independent variable is a good predictor. 4.7 Coefficients of Deseasonalized Data Sales

Table 5.a Coefficients of Powdered Gloves

Coefficientsa

Model

Unstandardized Coefficients

Standardized Coefficients

t

Sig.

B

Std. Error

Beta

1

(Constant)

6814485.976

434432.013

15.686

.000

quarter

248584.478

59027.687

.800

4.211

.002

a. Dependent Variable: powdered gloves deseasonalized data

Table 5.b Coefficients of Free-Powdered Gloves

Coefficientsa

Model

Unstandardized Coefficients

Standardized Coefficients

t

Sig.

B

Std. Error

Beta

1

(Constant)

1703621.494

108608.003

15.686

.000

quarter

62146.120

14756.922

.800

4.211

.002

a. Dependent Variable: free-powdered gloves deseasonalized data The tables 5.a and 5.b show the value of Beta which refers to the slope of the trend line or the regression line. If the Beta is greater than 0, there is a positive slope which means an increasing in sales. If the Beta is less than 0, there is a negative slope which means a decreasing in sales. It shows that the value of Beta is 0.800 which means a positive slope or an increasing of sales. 4.8 Forecast Deseasonalized Data Sales through Regression Analysis The researcher used trend analysis under regression as a forecasting model for deseasonalized data sales of powdered and free-powdered gloves of Ansell products, where in the independent variable x represents the period which is quarterly and the dependent variable y represents the actual sales of powdered and free-powdered gloves. Table 6.a Forecasted Powdered Deseasonalized Data

quarter

Deseasonalized

(Powdered)

Forecasted Deseasonalized

Error

1

6892385.66

7063069.98

170684.32

2

7712524.17

7311654.94

400869.23

3

7044378.52

7560237.98

515859.46

4

6879409.26

7808823.9

929414.64

5

8261585.41

8057405.98

204179.43

6

8335960.51

8305992.86

29967.65

7

9013673.57

8554573.98

459099.59

8

10140333.66

8803161.82

1337171.84

9

9051982.15

9051741.98

240.17

10

9573861.14

9300330.78

273530.36

11

9694838.52

9548909.98

145928.54

12

8562488.48

9797499.74

1235011.26

13

8979800.649

10046077.98

1066277.33

14

9859104.319

10294668.7

435564.38

15

11422694.98

10543245.98

879449.00

16

10782146.79

10791837.66

9690.87

Table 6.b Forecasted Free-Powdered Deseasonalized Data

quarter

Deseasonalized

(Free-Powdered)

Forecasted Deseasonalized

Error

1

1723096.41

1765767.61

42671.20

2

1928131.04

1827913.73

100217.31

3

1761094.63

1890059.85

128965.22

4

1719852.31

1952205.97

232353.66

5

2065396.35

2014352.09

51044.26

6

2083990.13

2076498.21

7491.92

7

2253418.39

2138644.33

114774.06

8

2535083.41

2200790.45

334292.96

9

2262995.54

2262936.57

58.97

10

2393465.29

2325082.69

68382.60

11

2423709.63

2387228.81

36480.82

12

2140622.12

2449374.93

308752.81

13

2244950.16

2511521.05

266570.89

14

2464776.08

2573667.17

108891.09

15

2855673.75

2635813.29

219860.46

16

2695536.70

2697959.41

2422.71

The table 3.a and table 3.b show the forecasted value and error of the powdered and free-powdered gloves deseasonalized data sales. The researchers came up with a model Y = ax + b where a is the intercept of the regression line with the y axis, b is the slope of the trend line and x corresponds to the quarterly in a year. Y = 6814485.98x + 248584.48 for powdered gloves and Y= 1703621.49x + 62146.12 for free-powdered gloves. 4.9 Forecast Error

Table 7 Comparison of Forecast Error

Error

Powdered gloves Actual sales

Free-Powdered gloves

Actual sales

Powdered gloves Deseasonalized data sales

Free-Powdered gloves Deseasonalized data sales

MSE

3.42440604E+10

2140254698

24969250930

1560728303

MAD

1180205.549

295051.3895

505808.6296

207346.0945

MAPE

0.138381882

0.138381882

0.057422852

0.089439481

The table shows that the deseasonalized data has less forecast error compare to the actual data with 8% difference for powdered gloves and 5% for free-powdered gloves. 4.10 Forecast Error Between Company’s Method and Researcher’s Method Table 8 Comparison of Forecast Error

Error

Researchers’ Method

Company’s method

Powdered Gloves

Free-Powdered Gloves

Powdered Gloves

Free-Powdered Gloves

MSE

24969250930

1560728303

3.29E+12

2.06E+11

MAD

505808.6296

207346.0945

1,777,860.57

444465.1427

MAPE

0.057422852

0.089439481

0.19

0.2

The table shows that the researchers’ method has less forecast error compare to the company’s method with 13% difference for powdered gloves and 11% difference for free-powdered gloves based on MAPE (Mean Absolute Percentage Error).

CHAPTER V

SUMMARY, CONCLUSION AND RECOMMENDATION

SUMMARY OF FINDINGS

Health-Tech Medical Incorporation is one of the distributors of medical equipment’s and supplies here in the Philippines. The researcher used one of the products that their distributed and that are the gloves.

The sales of the gloves for three consecutive (2007-2009) were used to predict the 2010 sales of it. The gloves are divided into two classes which are the powdered and free-powdered gloves. The researcher used the forecasting through regression analysis to predict the sales.

In order to achieve the following objectives: a. to determine the model that will suit the Ansell sales data, b. to predict the 2010 sales of Ansell Healthcare products, c.to determine the forecast error for the year 2010, d.to compare the forecast sales of Ansell products between researchers’ and company’s method , the researchers conducted the study.

Through scattered diagram the researcher observed if there is a linear relationship between sales and period of time and through ANOVA it explained the significant difference of sales and period of time. And noticed that there a weak linear relationship in actual sales and a strong linear relationship in deseasonalized sales.

Through moving average method the researchers got the deseasonalized sales.

Using the least square method the researchers came up with a models that suit to Ansell products such as, y = 6814485.98x + 248584.48 for powdered gloves and y = 1703621.49x + 62146.12 for free-powdered gloves.

The Mean Square Error (MSE), Mean Absolute Deviation (MAD) and the Mean Absolute Percentage Error (MAPE) distinguish the forecast error of the Ansell sales.

The company’s method compares to the researcher’s has a big difference based on the forecast error, which mean the researcher’s method is more effective to predict the sales of Ansell products. CONCLUSION

Using ANOVA with F-test in SPSS, the actual sales shows a weak linear relationship between the independent variable which is the time and dependent variable which is the sales. The researchers used the moving average method to remove the seasonal effect and smoothen fluctuates of actual data sales and noticed that the there is a strong positive linear relationship.

Using Mean Square Error (MSE), Mean Absolute Deviation (MAD) and the Mean Absolute Percentage Error (MAPE), the researchers observed that the forecast errors of the deseasonalized data sales of powdered and free-powdered gloves are less compare to the actual sales for powdered and free-powdered gloves. After different computations, verification, and analysis, the researchers concluded that the good model for Ansell sales is Y=6814485.98x + 248584.48 for powdered gloves and Y=1703621.49x + 62146.12 for free-powdered gloves. Through comparison of the computed forecast error between the method of the researchers and company in forecasting of sales, the researchers found out that their method has lesser forecast error with 13% and 11% error difference for powdered gloves and free-powdered gloves respectively than to the company which implies that the researchers have used better method.

RECOMMENDATION

After thorough analysis of data, the researchers would recommend the Health-Tech Medical Inc. to apply the trend projection under time series in forecasting of sales in which moving average is used that resulted to a minimal error. The researchers would also recommend other researchers to work on this study and use other methods in forecasting to compare the results and conclude the best method to forecast sales of the said company.

referencEs

Small Business Encyclopedia. The Gale Group, Inc. 2002

Marketing Dictionary. Barron’s Educational Series, Inc. 2000 Kress, George, and John Snyder. Forecasting and Market Analysis Techniques: A Practical Approach. Westport, CT: Quorum Books, 1994. Mentzer, John T., and Carol C. Bienstock. Sales Forecasting Management. Thousand Oaks, CA: Sage Publications, 1997. Aston, Adam, and Joseph Weber. “The Worst Isn’t Over: Smarter science is helping companies and insurers plan for hurricanes. The Bad News: This year could be another doozy.” Business Week. 16 January 2006. Chase, Charles W. Jr. “Composite Forecasting: Combining Forecasts for Improved Accuracy.” Journal of Business Forecasting.Summer 2000. Engerman, Stanley. “On the Accuracy of Some Past and Present Forecasts.”International Monetary Fund Staff Papers.Annual 2005. Evans, Michael.

Practical Business Forecasting.Blackwell Publishing, 2002. Gaber, Tal, Jacob Goldenberg, Barak Libai, and EitanMullerray. “From Density to Destiny: Using spatial dimension of sales data for early prediction of new product success.” Marketing Science.Summer 2004. Gray, Andi. “How Forecasting Can Help the Bottom Line.” Fairfield County Business Journal. 27 June 2005. Jones, Vernon Dale, Stuart Bretschneider, and Wilpen L. Gorr. “Organization Pressures on Forecast Evaluation: Managerial, Political, and Procedural Influences.” Journal of Forecasting. July 1997. Mentzer, John T., and Mark A. Moon.Sales Forecasting Management. Sage Publications, Inc., 2004. O’Connor, Marcus, William Remus, and Ken Griggs. “Going Up—Going Down: How Good are People at Forecasting Trends and Changes in Trends?” Journal of Forecasting. May 1997. Sanders, Nada R., and Karl B. Manrodt.”The Efficacy of Using Judgmental versus Quantitative Forecasting Methods in Practice.”Omega. December 2003. Rasmussen, Rasmus. “On Time Series Data and Optimal Parameters.”Omega. April 2004 www.va-interactive.com/inbusiness/editorial/sales/ibt/sales_fo.html

### Cite this PUP MANILA THESIS FOR SALES FORECASTING

PUP MANILA THESIS FOR SALES FORECASTING. (2016, May 05). Retrieved from https://graduateway.com/pup-manila-thesis-for-sales-forecasting/

This is just a sample.

You can get your custom paper from
our expert writers