Microsoft Word research method fm doc

iv. Programming
A certain amount of basic knowledge of computer programming is needed to give the 
appropriate commands. 
v. Computer outputs
The computer can do most of the analysis and the results can be printed. It is important to 
decide whether each of the tables, graphs, and statistical tests that can be produced makes 
sense and should be used in your report. That is why we PLAN the data analysis 
BEFOREHAND!

---

Research methodology 
75
Data analysis – quantitative data 
Analysis of quantitative data involves the production and interpretation of frequencies, tables, 
graphs, etc., that describe the data. 
1. Frequency counts 
From the data master sheets, simple tables can be made with frequency counts for each 
variable. A frequency count is an enumeration of how often a certain measurement or a 
certain answer to a specific question occurs. 
For example,
Smokers 51 
Non-smokers 93 
Total
144 
If numbers are large enough it is better to calculate the frequency distribution in percentages 
(relative frequencies)
: 51/144 x 100 = 35% are smokers and 93/144 x 100 = 65% non-
smokers. This makes it easier to compare groups than when only absolute numbers are 
given. In other words, percentages standardise the data. 
It is usually necessary to summarise the data from numerical variables by dividing them into 
categories. This process may include the following steps: 
(1) Inspect all the figures: What is their range? (The range is the difference 
between the largest and the smallest measurement.) 
(2) Divide the range into three to five categories. You can either aim at having a 
reasonable number in each category (e.g. 0-2 km, 3-4 km, 5-9 km, 10+ km 
for home-clinic distance) or you can define the categories in such a way that 
they are each equal in size (e.g., 20-29 years, 30-39 years, 40-49 years, 
etc.). Sometimes one looks actively for a ‘critical’ value, when making 
different categories. For example, in a study relating family income to 
prevalence of diarrhoea over a certain period, there appeared to be no 
statistical relation when income was arbitrarily subdivided into four 
categories. When the average income was calculated, however, this 

---

Research methodology 
76
appeared to be a critical value. The children in families with an income 
above average had had significantly less diarrhoea than the children in 
families with an income below average. 
(3) Construct a table indicating how data are grouped and count the number of 
observations in each group.