SOCC31H3 Lecture : Lecture 2
Document Summary
Raw data is often difficult to synthesize. When distributions being compared are of unequal size. Frequency distribution of nominal data consists of two columns: left: the frequency data cannot be used to make comparisons. Two popular methods are: proportion- # of cases compared to the total size of distribution, percentage- the frequency per 100 cases, percentage is used to show relative side. Nominal data order doesn t matter and interval must be ordered. Categories must be mutually exclusive (1-5,6-10,11-15)not (1-5,5-10) Possible to have too few or too many groups. The following are the steps of constructing a freq. Distr: specify the number of class intervals, when all intervals are to be the same width, the following rule may be used to find the required class interval width: W= class width; l= the largest data, s= the smallest data, k= number of classes. Example: suppose the age of a sample of 10 students are: