Research DesignBack

(A) Self-administered Questionnaire Survey with Secondary School Students

Fifteen secondary schools were selected from the pool of the BOKSS school network and were successfully contacted by BOKSS. Consent to participate in this voluntary study was obtained from the school principals as well as parents of the students coming from the selected classes within each school.

In details, POP had randomly selected two classes for each of the fifteen schools by means of a computer program and all students of these two classes would be invited to take part in this survey. In case any of the first two selected classes was not available, a backup class (i.e. the third one) would be used according to the random order list generated by the computer.

After selecting the target classes, self-administered paper questionnaires were sent to all fifteen schools waiting for dispatch. Letters to parents were distributed to the students involved before the data collection started so as to inform them of the purpose and procedures of the survey. Parents who refused to allow their children to participate in the survey could return a reply slip to the school.

With their parental consent, students in the target classes were asked to fill in the survey questionnaires in class and return to the teacher in-charge on the spot. In other words, no questionnaires were allowed to take away from school.

The data collection was carried out between December 18, 2008 and January 23, 2009. A total of 999 questionnaires were received, while only 947 cases were considered valid after verification by POP. Hence, calculated as if this were a random sample survey, the response rate of this part of survey was 94.8%, and the standard sampling error for percentages based on this sample was less than 1.6 percentage points. In other words, the sampling error for all percentages is less than plus/minus 3.2 percentage points at 95% confidence level.

(B) Random Telephone Survey with General Public

This part targeting at the general public was a random telephone survey conducted by real interviewers under close supervision. To minimize sampling bias, telephone numbers were first drawn randomly from the residential telephone directory as 「seed numbers」, from which another set of numbers was generated using the 「plus/minus one/two」 method, in order to capture the unlisted numbers. Duplicated numbers were then filtered, and the remaining numbers were mixed in random order to produce the final telephone sample.

Target respondents of this part were Hong Kong citizens of age 18 or above who spoke Cantonese. Upon successful contact being made within a target household, one member of the household was selected among those present using the 「next birthday」 rule.

All data for this part of survey were collected by our interviewers using a Computer Assisted Telephone Interview (CATI) system which allowed real-time data capture and consolidation. To ensure data quality, on top of on-site supervision, voice recording, screen capturing and camera surveillance were also used to monitor the interviewers' performance.

The fieldwork was conducted during the period of February 2 to 4, 2009. A total of 1,011 local citizens of age 18 or above were successfully interviewed. The overall response rate of this survey was 73.7%, and the standard sampling error of percentages based on this sample was less than 1.6 percentage points. In order words, the sampling error of all percentages is less than plus/minus 3.1 percentage points at 95% confidence level.

To ensure representativeness, the raw data collected have been adjusted according to provisional figures obtained from the Census and Statistics Department regarding the gender-age distribution of the Hong Kong population in mid-year 2008. All analyses for this part are based on the weighted data in the report.To ensure representativeness, the raw data collected have been adjusted according to provisional figures obtained from the Census and Statistics Department regarding the gender-age distribution of the Hong Kong population in mid-year 2008. All analyses for this part are based on the weighted data in the report.