HKU POP releases a Budget instant pollBack

The Public Opinion Programme (POP) at the University of Hong Kong interviewed 1,005 Hong Kong people last night (26 February) by means of a random telephone survey conducted by real interviewers. After excluding those respondents who said they had heard nothing of the Budget, this year's instant survey shows that people's instant appraisal of the Second Budget of CY Leung's administration is rather negative, with a net satisfaction of negative 20 percentage points, representing a significant drop from the instant survey conducted last year this time, and also registering a new low since 2003. As for the rating of the Budget, this year's instant survey gives a rating of 49.8 marks, which is a record low since such ratings started in 2008. In terms of personal popularity, both the support rating and net approval rate of John Tsang have dropped after his Budget Talk, meaning that he has not gained any popularity from the Budget. Further analysis shows that respondents of age 50 or above are most satisfied with the Budget, and support John Tsang most. How people's reaction will change after knowing more about the Budget will have to be revealed by our next survey. The maximum sampling error of all percentages is +/-4 percentage points at 95% confidence level, while the sampling errors of rating figures and net values need another calculation. The response rate of the survey is 63%.

[2] The sample size of this survey is 1,005 successful interviews, not 1,005 x 62.7% response rate. In the past, many media made this mistake.
[3] The maximum sampling error of all percentages is +/-4 percentage points at 95% confidence level, while the sampling error of rating figures needs another calculation. "95% confidence level" means that if we were to repeat a certain survey 100 times, using the same questions each time but with different random samples, we would expect 95 times getting a figure within the error margins specified. When quoting these figures, journalists can state "sampling error of rating not more than +/-1.7, sampling error of percentages not more than +/-4%, and sampling error of net values not more than +/-6% at 95% confidence level". Because POP introduced "rim weighting" in 2014, during the transition period, whether changes in various figures are beyond sampling errors are based on tests using the same weighting methods. That is, to test whether the first set of figures collected in 2014 is significantly different from that of the previous survey, both sets of data are rim weighted before testing, instead of using simple computation of the published figures.
[4] Because of sampling errors in conducting the survey(s) and the rounding procedures in processing the data, the figures cannot be too precise, and the totals may not be completely accurate. Therefore, when quoting percentages of the survey(s), journalists should refrain from reporting decimal places, but when quoting the rating figures, one decimal place can be used.
[5] The data of this survey is collected by means of random telephone interviews conducted by real interviewers, not by any interactive voice system (IVS). If a research organization uses "computerized random telephone survey" to camouflage its IVS operation, it should be considered unprofessional.

Since 1992, HKUPOP has been conducting Policy Address instant surveys every year. From 1998 onwards, we expanded our instant surveys to cover the Budget Talks. In free and democratic societies, instant surveys are indispensable sources of free information. Combined with appropriate follow-up surveys, and in parallel to expert analyses, they give a multi-dimensional picture of opinion development. They are an important part of a society's interactive development. Starting 2008, we split up previous years' instant survey into two surveys. In our first survey, we measure people's overall appraisal of the Budget, their rating of the Budget, their change in confidence towards Hong Kong's future, and FS's popularity. In our second survey, we focus on people's reactions towards different government proposals, their satisfaction with the government's fiscal policies, and other relevant issues. Starting 2011, we revised our design to concentrate on people's appraisal of the Budget and FS's popularity in our instant survey, and move the remaining questions to our follow-up survey. There is no change to our operation this year.

POP today releases the latest findings of the Budget instant poll. From 2014, POP enhanced the previous simple weighting method based on age and gender distribution to "rim weighting" based on age, gender and education (highest level attended) distribution. The latest figures released today have been rim-weighted according to provisional figures obtained from the Census and Statistics Department regarding the gender-age distribution of the Hong Kong population in mid-year 2013 and the educational attainment (highest level attended) distribution collected in the 2011 Census.
Herewith the contact information of various surveys:

[6] Errors are calculated at 95% confidence level using full sample size. "95% confidence level" means that if we were to repeat a certain survey 100 times, using the same questions each time but with different random samples, we would expect 95 times getting a figure within the error margins specified. Questions using only sub-samples would have bigger sample error. Sampling errors of ratings are calculated according to the distribution of the scores collected.
[7] The figures shown in the "latest change" column of this press release have been tested after "rim weighting" data collected in this and last surveys. The structural effect of using the new weighting method is small, around -1% to +1% for percentage figures, and less than 0.1 mark for rating figures, while statistical significance tests are not affected.

People's satisfaction figures with this year's Budget are summarized below together with the previous findings:

[8] Sub-samples exclude those respondents who said they had heard nothing of the Budget, while "recognition rates" used to indicate people's knowledge level further exclude those who answered "don't know / hard to say".
[9] Collapsed from a 5-point scale, all errors in the table are calculated at 95% confidence level. "95% confidence level" means that if we were to repeat a certain survey 100 times, using the same questions each time but with different random samples, we would expect 95 times getting a figure within the error margins specified. Questions using only sub-samples would have bigger sample error.
[10] Sub-sample base has excluded those who said they had heard nothing of the Budget. Sampling errors of ratings are calculated according to the distribution of the scores collected. Since the base is smaller, the sampling error is bigger.
[11] Such changes have gone beyond the sampling errors at the 95% confidence level under the same weighting method, meaning that they are statistically significant prima facie. However, whether numerical differences are statistically significant or not is not the same as whether they are practically useful or meaningful.

After excluding those respondents who said they had heard nothing of the Budget, this year's instant survey shows that 24% are satisfied with the Budget, 45% are dissatisfied and 26% say "half-half", giving a net satisfaction rate of negative 20 percentage points. The average rating registered for the Budget is 49.8 marks, with a recognition rate of 66%.

Figures on various Financial Secretaries' popularity before and after their Budget Speeches since 2001^[12] are summarized as follows:

[12] FS rating was introduced in our Budget instant poll in 2001, while approval rate was introduced in 2005. This table therefore starts from 2001.
[13] These questions only use the concerned sub-samples for the tracking surveys between 2006 and 2010.
[14] All errors in the table are calculated at 95% confidence level. "95% confidence level" means that if we were to repeat a certain survey 100 times, using the same questions each time but with different random samples, we would expect 95 times getting a figure within the error margins specified. Questions using only sub-samples would have bigger sample error. Sampling errors of ratings are calculated according to the distribution of the scores collected.
[15] The frequency of FS rating and approval rate was different before November 2005.
[16] Such changes have gone beyond the sampling errors at the 95% confidence level under the same weighting method, meaning that they are statistically significant prima facie. However, whether numerical differences are statistically significant or not is not the same as whether they are practically useful or meaningful.
[17] This was the first Budget by Henry Tang after Donald Tsang became the Acting Chief Executive.
[18] This was the first Budget by John Tsang after CY Leung became the Chief Executive.

The survey shows that the latest popularity rating of FS John Tsang after his Budget Talk is 54.0 marks, with an approval and disapproval rates of 44% and 17% respectively, giving a net approval of positive 27 percentage points.

In the survey, we also asked respondents for their age. If they were reluctant to give their exact age, they could give us a range. According to their answers, we grouped them into 18-29, 30-49, and 50 years or older. Herewith further analysis of public's satisfaction rate of the Budget, and John Tsang's rating and approval rates by respondents' age:

[19] Differences among sub-groups are tested to be statistically significant at 95% confidence level.

Robert Ting-Yiu Chung, Director of Public Opinion Programme, observed, "Based on those who understand the Budget, our survey finds that people's instant appraisal of the Second Budget of CY Leung's administration is rather negative, with a net satisfaction of negative 20 percentage points, representing a significant drop from the instant survey conducted last year this time, and also registering a new low since 2003. As for the rating of the Budget, this year's instant survey gives a rating of 49.8 marks, which is a record low since such ratings started in 2008. In terms of personal popularity, both the support rating and net approval rate of John Tsang have dropped after his Budget Talk, meaning that he has not gained any popularity from the Budget. Further analysis shows that respondents of age 50 or above are most satisfied with the Budget, and support John Tsang most. How people's reaction will change after knowing more about the Budget will have to be revealed by our next survey."

• March 4, 2014 (Tuesday) 1pm to 2pm: Budget first follow-up survey

• March 6, 2014 (Thursday) 1pm to 2pm: Ratings of top 10 political group