Data Analysis and Interpretation

This section shows how the responses gathered in the sample toothpaste project are organised, analysed and interpreted to produce the final report. After the questionnaires from the sample of 100 households were collected, the raw replies were classified into tables, summarised with averages and standard deviations, and read for their meaning. The main results were as follows.

Coverage and location. Of the 100 households, 67 per cent were urban and 33 per cent rural, so the majority of users belonged to urban areas.

Age distribution. Grouping members by age showed that the largest numbers fell in the 20–50 year band, i.e. most surveyed persons were in the working-age range.

Family size. Most families had 3–6 members.

Monthly family income. The income data were put into classes and the mean was found by the step-deviation method with assumed mean $A = 20000$ and class width $c = 5000$:

So the mean monthly income was about Rs. 18,000 with a standard deviation of about Rs. 9,000, and most families earned between Rs. 10,000 and Rs. 30,000.

Expenditure on toothpaste. Using $A = 100$ and $c = 40$, the mean monthly expenditure was

that is, about Rs. 104 per household per month, with a standard deviation of about Rs. 35.60.

Occupation, brands and preferences. Most families were in service or trade. The most preferred brands were Pepsodent, Colgate and Close-up. Toothpaste was chosen mainly on the basis of standardised markings, quality, price and brand name, and gel and antiseptic-based varieties were preferred. Dissatisfaction among users of the popular brands was relatively low.

Media influence. Television reached the most families, followed by newspapers, as the main sources of information about the product. …