The use of job costing as a tool for the pricing and cost control decisions in the printing industry: the case of Société de Presse et d'Editions (SOPECAM)

b) Data collection

Data will be collected from primary and secondary sources.

i. The primary sources will be made of the results of the interviews of the executives and employees of SOPECAM and the results of the observations made by the researcher.

ii. Concerning the secondary sources of data, they constitute the most important source of data for this study. They had been collected through the company accounting, financial and managerial reports and statements.

c) Variables of the study:

In this study we will pay a particular attention to the evolution of the unit cost of the newspaper Cameroon Tribune and its effects on the pricing and cost control policies.

d) Data analysis

Data will be analysed using both qualitative and quantitative models. But much of the analysis will be done using quantitative tools.

e) Model specification

In this study, we will make use of the Student's-t distribution in order to test our hypothesis.

The Student's-t-distribution is a probability distribution used to test the research hypothesis for situations involving the comparison of two means when the sample size is small or when the variances are not known.

As stated by Grais^23(*) (2000), the model assumes that there are two populations P1 and P2 from which two samples are collected:

· A sample X₁₁, X₁₂...X_1n of size N₁ taken from P₁

· A sample X₂₁...X_2n of sizeN₂ taken from P₂

In our case, the populations will be represented by the monthly production of the newspaper and we will draw a sample production week from that month. Let us assume that ì₁and ì₂ are the respective mean unit costs of the week obtained by applying absorption and variable costing respectively and ó²₁ and ó²₂ are the respective unknown variances whose sample estimates suggest relatively equal variances that is S²₁=S²_2.

The sample sizes, represented by the number of production days per week, that is 5, being known and less than 30, there is a need to estimate a pooled weighted variance denoted S²

(N₁-1) S²₁ +(N₂-1) S²₂

N₁+N₂-2

S² = ........equation 3.1

? (X1i-A₁) ²+? (X2i-A₂) ²

N₁+N₂-2

= ...........equation 3.2

It appears that the difference in means A₁-A₂ is normally distributed with mean and variance expressed as follows:

(1/N₁+1/N₂)

(N₁-1) S²₁ + (N₂-1) S²₂

N₁+N₂-2

A₁-A₂ ~N [ì₁-ì₂, .eq.3.3

From this information, it is now possible to state our hypothesis in mathematical terms such that it can be tested using the afore-mentioned test.

H_o: (Null hypothesis) A₁-A₂=0, there is no difference between the sample means and both can be used for the same purposes.

H₁: (Alternative Hypothesis) A₁-A₂?0 the two sample means are different and cannot be used for the same purposes.

It is now necessary to start with the analysis of the data collected and the test of the research hypotheses; this will be done in the next chapter, which is mainly about the presentation and the analysis of the results of the study.

* ²³ Grais, B.(2000), Méthodes Statistiques (3^rd edition), Dunod, Paris.