Opinion poll - Revision history

Wehpudicabok: /* Wording of questions */

2024-10-23T05:00:56Z

Wording of questions

← Previous revision		Revision as of 05:00, 23 October 2024
Line 70:		Line 70:

	=== Wording of questions ===		=== Wording of questions ===
	Among the factors that impact the results of ~~Opinion~~ ~~Polls,~~ are the wording and order of the questions being posed by the surveyor. Questions that intentionally affect a respondents answer are referred to as [[leading question]]s. Individuals and/or groups use these types of questions in surveys to elicit responses favorable to their interests.<ref>{{cite book \|last1=Asher \|first1=Herbert B. \|title=Polling and the public : what every citizen should know \|date=16 August 2016 \|location=Thousand Oaks, California \|isbn=978-1-5063-5242-8 \|pages=75 \|edition=Ninth}}</ref>		Among the factors that impact the results of opinion polls are the wording and order of the questions being posed by the surveyor. Questions that intentionally affect a respondents answer are referred to as [[leading question]]s. Individuals and/or groups use these types of questions in surveys to elicit responses favorable to their interests.<ref>{{cite book \|last1=Asher \|first1=Herbert B. \|title=Polling and the public : what every citizen should know \|date=16 August 2016 \|location=Thousand Oaks, California \|isbn=978-1-5063-5242-8 \|pages=75 \|edition=Ninth}}</ref>

	For instance, the public is more likely to indicate support for a person who is described by the surveyor as one of the "leading candidates". This description is "leading" as it indicates a subtle bias for that candidate, since it implies that the others in the race are not serious contenders. Additionally, leading questions often contain, or lack, certain facts that can sway a respondent's answer. Argumentative Questions can also impact the outcome of a survey. These types of questions, depending on their nature, either positive or negative, influence respondents' answers to reflect the tone of the question(s) and generate a certain response or reaction, rather than gauge sentiment in an unbiased manner.<ref>{{cite book \|last1=Asher \|first1=Herbert B. \|title=Polling and the public : what every citizen should know \|date=16 August 2016 \|publisher=SAGE CQ Press \|location=Thousand Oaks, California \|isbn=978-1-5063-5242-8 \|pages=82–86 \|edition=Ninth}}</ref>		For instance, the public is more likely to indicate support for a person who is described by the surveyor as one of the "leading candidates". This description is "leading" as it indicates a subtle bias for that candidate, since it implies that the others in the race are not serious contenders. Additionally, leading questions often contain, or lack, certain facts that can sway a respondent's answer. Argumentative Questions can also impact the outcome of a survey. These types of questions, depending on their nature, either positive or negative, influence respondents' answers to reflect the tone of the question(s) and generate a certain response or reaction, rather than gauge sentiment in an unbiased manner.<ref>{{cite book \|last1=Asher \|first1=Herbert B. \|title=Polling and the public : what every citizen should know \|date=16 August 2016 \|publisher=SAGE CQ Press \|location=Thousand Oaks, California \|isbn=978-1-5063-5242-8 \|pages=82–86 \|edition=Ninth}}</ref>

Asilvering: Copyvio revdel completed (RR)

2024-09-27T18:53:29Z

Copyvio revdel completed (RR)

← Previous revision		Revision as of 18:53, 27 September 2024
Line 1:		Line 1:
	{{copyvio-revdel\|url=https://us.sagepub.com/sites/default/files/upm-assets/76580_book_item_76580.pdf\|start1=1247155241\|end1=1247155389}}
	{{Short description\|Type of survey}}		{{Short description\|Type of survey}}
	{{Globalize\|article\|Anglophone\|2name=[[English-speaking world\|the English-speaking world]]\|date=May 2023}}		{{Globalize\|article\|Anglophone\|2name=[[English-speaking world\|the English-speaking world]]\|date=May 2023}}

Tim Starling: /* Nonresponse bias */ fix cite date error

2024-09-26T22:59:16Z

Nonresponse bias: fix cite date error

← Previous revision		Revision as of 22:59, 26 September 2024
Line 61:		Line 61:

	=== Nonresponse bias ===		=== Nonresponse bias ===
	Since some people do not answer calls from strangers, or refuse to answer the poll, poll samples may not be representative samples from a population due to a [[non-response bias]]. Response rates have been declining, and are down to about 10% in recent years.<ref>{{cite magazine\|url=http://www.slate.com/articles/news_and_politics/politics/2012/05/survey_bias_how_can_we_trust_opinion_polls_when_so_few_people_respond_.single.html\| title=Minority Opinions:Hardly anyone responds to public opinion surveys anymore. Can we still trust them?\|author=Will Oremus\| date=2012-05-17\| access-date=2013-11-21\| magazine=Slate}}</ref> Various pollsters have attributed this to an increased skepticism and lack of interest in polling.<ref>{{cite book \|last=Asher \|first=Herb \|title=Polling and the Public \|date=08/16~~/2016~~ \|publisher=CQ Press \|year=2016 \|isbn=978-1506352435 \|edition=9th \|pages=28}}</ref> Because of this [[selection bias]], the characteristics of those who agree to be interviewed may be markedly different from those who decline. That is, the actual sample is a biased version of the universe the pollster wants to analyze. In these cases, bias introduces new errors, one way or the other, that are in addition to errors caused by sample size. Error due to bias does not become smaller with larger sample sizes, because taking a larger sample size simply repeats the same mistake on a larger scale. If the people who refuse to answer, or are never reached, have the same characteristics as the people who do answer, then the final results should be unbiased. If the people who do not answer have different opinions then there is bias in the results. In terms of election polls, studies suggest that bias effects are small, but each polling firm has its own techniques for adjusting weights to minimize selection bias.<ref name="Langer2003">{{cite web\|publisher=ABC News\|author=Langer, Gary\|title=About Response Rates: Some Unresolved Questions\|url=https://abcnews.go.com/images/pdf/responserates.pdf\|date=May 2003\|access-date=2010-05-17\|archive-date=2017-07-20\|archive-url=https://web.archive.org/web/20170720004349/http://abcnews.go.com/images/pdf/responserates.pdf\|url-status=live}}</ref><ref>[http://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-FAQ/Response-Rates-An-Overview.aspx Response Rates: An Overview] {{Webarchive\|url=https://web.archive.org/web/20190712004056/https://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-FAQ/Response-Rates-An-Overview.aspx \|date=2019-07-12 }} American Association for Public Opinion Research, Retrieved 2016-06-05</ref>		Since some people do not answer calls from strangers, or refuse to answer the poll, poll samples may not be representative samples from a population due to a [[non-response bias]]. Response rates have been declining, and are down to about 10% in recent years.<ref>{{cite magazine\|url=http://www.slate.com/articles/news_and_politics/politics/2012/05/survey_bias_how_can_we_trust_opinion_polls_when_so_few_people_respond_.single.html\| title=Minority Opinions:Hardly anyone responds to public opinion surveys anymore. Can we still trust them?\|author=Will Oremus\| date=2012-05-17\| access-date=2013-11-21\| magazine=Slate}}</ref> Various pollsters have attributed this to an increased skepticism and lack of interest in polling.<ref>{{cite book \|last=Asher \|first=Herb \|title=Polling and the Public \|date=2016-08-16 \|publisher=CQ Press \|year=2016 \|isbn=978-1506352435 \|edition=9th \|pages=28}}</ref> Because of this [[selection bias]], the characteristics of those who agree to be interviewed may be markedly different from those who decline. That is, the actual sample is a biased version of the universe the pollster wants to analyze. In these cases, bias introduces new errors, one way or the other, that are in addition to errors caused by sample size. Error due to bias does not become smaller with larger sample sizes, because taking a larger sample size simply repeats the same mistake on a larger scale. If the people who refuse to answer, or are never reached, have the same characteristics as the people who do answer, then the final results should be unbiased. If the people who do not answer have different opinions then there is bias in the results. In terms of election polls, studies suggest that bias effects are small, but each polling firm has its own techniques for adjusting weights to minimize selection bias.<ref name="Langer2003">{{cite web\|publisher=ABC News\|author=Langer, Gary\|title=About Response Rates: Some Unresolved Questions\|url=https://abcnews.go.com/images/pdf/responserates.pdf\|date=May 2003\|access-date=2010-05-17\|archive-date=2017-07-20\|archive-url=https://web.archive.org/web/20170720004349/http://abcnews.go.com/images/pdf/responserates.pdf\|url-status=live}}</ref><ref>[http://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-FAQ/Response-Rates-An-Overview.aspx Response Rates: An Overview] {{Webarchive\|url=https://web.archive.org/web/20190712004056/https://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-FAQ/Response-Rates-An-Overview.aspx \|date=2019-07-12 }} American Association for Public Opinion Research, Retrieved 2016-06-05</ref>


	=== Response bias ===		=== Response bias ===

Egsan Bacon: rv - changes not an improvement, not encyclopedic in tone (especially "we find that"), vagueness of "a large number of citizens"

2024-09-24T23:51:46Z

rv - changes not an improvement, not encyclopedic in tone (especially "we find that"), vagueness of "a large number of citizens"

2601:243:C300:5BC0:516B:BEC0:3BA:21F9 at 23:20, 24 September 2024

2024-09-24T23:20:54Z

← Previous revision		Revision as of 23:20, 24 September 2024
Line 3:		Line 3:
	{{Globalize\|article\|Anglophone\|2name=[[English-speaking world\|the English-speaking world]]\|date=May 2023}}		{{Globalize\|article\|Anglophone\|2name=[[English-speaking world\|the English-speaking world]]\|date=May 2023}}

	An '''opinion poll''', often simply referred to as a '''survey''' or a '''poll''' (although strictly a poll is an actual election), is a [[survey (human research)\|human research survey]] of [[public opinion]] from a particular [[sampling (statistics)\|sample]]. Opinion polls are usually designed to represent the opinions of a population by conducting a series of questions and then extrapolating generalities in ratio or within [[confidence intervals]]. A person who conducts polls is referred to as a '''pollster'''.		An '''opinion poll''', often simply referred to as a '''survey''' or a '''poll''' (although strictly a poll is an actual election), is a [[survey (human research)\|human research survey]] of [[public opinion]] from a particular [[sampling (statistics)\|sample]]. Opinion polls are usually designed to represent the opinions of a population by conducting a series of questions and then extrapolating generalities in ratio or within [[confidence intervals]]. A person who conducts polls is referred to as a '''pollster'''. Polling is especially valued by those who prefer a democracy in which the people govern independently rather than through representatives. <ref>Asher, H. (2017). Polling and the public. CQ Press, https://doi.org/10.4135/9781506352404</ref>

	== History ==		== History ==

2601:243:C300:5BC0:516B:BEC0:3BA:21F9: /* Potential for inaccuracy */

2024-09-24T23:19:15Z

Potential for inaccuracy

← Previous revision		Revision as of 23:19, 24 September 2024
Line 48:		Line 48:
	== Potential for inaccuracy ==		== Potential for inaccuracy ==
	Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref> . The Total Survey Error Paradigm (TSE) conceptualizes the error sources in research sampling that may result in an inaccurate poll result. <ref>Robert M Groves and Lars Lyberg. 2010. Total survey error: Past, present, and future. Public opinion quarterly 74, 5 (2010), 849--879		Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref> . The Total Survey Error Paradigm (TSE) conceptualizes the error sources in research sampling that may result in an inaccurate poll result. <ref>Robert M Groves and Lars Lyberg. 2010. Total survey error: Past, present, and future. Public opinion quarterly 74, 5 (2010), 849--879
			</ref>. Citizens do not need to become experts at sampling, constructing questionnaires, or analyzing data to be better consumers of public opinion research- Instead, they can become aware of the steps involved in conducting a survey and the possible productions of error. <ref>Asher, H. (2017). Polling and the public. CQ Press, https://doi.org/10.4135/9781506352404</ref>
	</ref>.

	=== Margin of error due to sampling ===		=== Margin of error due to sampling ===
	Polls based on samples of populations are subject to [[sampling error]] which reflects the effects of chance and uncertainty in the sampling process. Sampling polls rely on the [[law of large numbers]] to measure the opinions of the whole population based only on a subset, and for this purpose the absolute size of the sample is important, but the percentage of the whole population is not important (unless it happens to be close to the sample size). The possible difference between the sample and whole population is often expressed as a [[margin of error]] – usually defined as the radius of a 95% confidence interval for a particular statistic. One example is the percent of people who prefer product A versus product B. When a single, global margin of error is reported for a survey, it refers to the maximum margin of error for all reported percentages using the full sample from the survey. If the statistic is a percentage, this maximum margin of error can be calculated as the radius of the confidence interval for a reported percentage of 50%. Others suggest that a poll with a random sample of 1,000 people has margin of sampling error of ±3% for the estimated percentage of the whole population. Studies show that public opinion polls are more confident than accurate- we find that reported 95% confidence intervals are only 60% accurate. <ref>Kotak, A., & Moore, D. A. (2020, October 20). Public Election Polls are 95% Confident but only 60% Accurate. https://doi.org/10.31234/osf.io/rj643</ref>		Polls based on samples of populations are subject to [[sampling error]] which reflects the effects of chance and uncertainty in the sampling process. Sampling polls rely on the [[law of large numbers]] to measure the opinions of the whole population based only on a subset, and for this purpose the absolute size of the sample is important, but the percentage of the whole population is not important (unless it happens to be close to the sample size). The possible difference between the sample and whole population is often expressed as a [[margin of error]] – usually defined as the radius of a 95% confidence interval for a particular statistic. One example is the percent of people who prefer product A versus product B. When a single, global margin of error is reported for a survey, it refers to the maximum margin of error for all reported percentages using the full sample from the survey. If the statistic is a percentage, this maximum margin of error can be calculated as the radius of the confidence interval for a reported percentage of 50%. Others suggest that a poll with a random sample of 1,000 people has margin of sampling error of ±3% for the estimated percentage of the whole population. Studies show that public opinion polls are more confident than accurate- we find that reported 95% confidence intervals are only 60% accurate. <ref>Kotak, A., & Moore, D. A. (2020, October 20). Public Election Polls are 95% Confident but only 60% Accurate. https://doi.org/10.31234/osf.io/rj643</ref>

2601:243:C300:5BC0:516B:BEC0:3BA:21F9: /* Potential for inaccuracy */

2024-09-24T23:17:08Z

Potential for inaccuracy

← Previous revision		Revision as of 23:17, 24 September 2024
Line 48:		Line 48:
	== Potential for inaccuracy ==		== Potential for inaccuracy ==
	Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref> . The Total Survey Error Paradigm (TSE) conceptualizes the error sources in research sampling that may result in an inaccurate poll result. <ref>Robert M Groves and Lars Lyberg. 2010. Total survey error: Past, present, and future. Public opinion quarterly 74, 5 (2010), 849--879		Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref> . The Total Survey Error Paradigm (TSE) conceptualizes the error sources in research sampling that may result in an inaccurate poll result. <ref>Robert M Groves and Lars Lyberg. 2010. Total survey error: Past, present, and future. Public opinion quarterly 74, 5 (2010), 849--879
	</ref>		</ref>.
	=== Margin of error due to sampling ===		=== Margin of error due to sampling ===
	Polls based on samples of populations are subject to [[sampling error]] which reflects the effects of chance and uncertainty in the sampling process. Sampling polls rely on the [[law of large numbers]] to measure the opinions of the whole population based only on a subset, and for this purpose the absolute size of the sample is important, but the percentage of the whole population is not important (unless it happens to be close to the sample size). The possible difference between the sample and whole population is often expressed as a [[margin of error]] – usually defined as the radius of a 95% confidence interval for a particular statistic. One example is the percent of people who prefer product A versus product B. When a single, global margin of error is reported for a survey, it refers to the maximum margin of error for all reported percentages using the full sample from the survey. If the statistic is a percentage, this maximum margin of error can be calculated as the radius of the confidence interval for a reported percentage of 50%. Others suggest that a poll with a random sample of 1,000 people has margin of sampling error of ±3% for the estimated percentage of the whole population.		Polls based on samples of populations are subject to [[sampling error]] which reflects the effects of chance and uncertainty in the sampling process. Sampling polls rely on the [[law of large numbers]] to measure the opinions of the whole population based only on a subset, and for this purpose the absolute size of the sample is important, but the percentage of the whole population is not important (unless it happens to be close to the sample size). The possible difference between the sample and whole population is often expressed as a [[margin of error]] – usually defined as the radius of a 95% confidence interval for a particular statistic. One example is the percent of people who prefer product A versus product B. When a single, global margin of error is reported for a survey, it refers to the maximum margin of error for all reported percentages using the full sample from the survey. If the statistic is a percentage, this maximum margin of error can be calculated as the radius of the confidence interval for a reported percentage of 50%. Others suggest that a poll with a random sample of 1,000 people has margin of sampling error of ±3% for the estimated percentage of the whole population. Studies show that public opinion polls are more confident than accurate- we find that reported 95% confidence intervals are only 60% accurate. <ref>Kotak, A., & Moore, D. A. (2020, October 20). Public Election Polls are 95% Confident but only 60% Accurate. https://doi.org/10.31234/osf.io/rj643</ref>


	A 3% margin of error means that if the same procedure is used a large number of times, 95% of the time the true population average will be within the sample estimate plus or minus 3%. The margin of error can be reduced by using a larger sample, however if a pollster wishes to reduce the margin of error to 1% they would need a sample of around 10,000 people.<ref>An estimate of the margin of error in percentage terms can be gained by the formula 100 ÷ square root of sample size</ref> In practice, pollsters need to balance the cost of a large sample against the reduction in sampling error and a sample size of around 500–1,000 is a typical compromise for political polls. (To get complete responses it may be necessary to include thousands of additional participators.)<ref>[http://www.ncpp.org/?q=node/4 20 Questions Journalists Should Ask About Poll Results] {{Webarchive\|url=https://web.archive.org/web/20160604234339/http://www.ncpp.org/?q=node/4 \|date=2016-06-04 }}, National Council on Public Polls Retrieved 2016-06-05</ref><ref>[http://www.aapor.org/Education-Resources/Election-Polling-Resources/Margin-of-Sampling-Error-Credibility-Interval.aspx Margin of Sampling Error and Credibility Interval] {{Webarchive\|url=https://web.archive.org/web/20160707180221/http://www.aapor.org/Education-Resources/Election-Polling-Resources/Margin-of-Sampling-Error-Credibility-Interval.aspx \|date=2016-07-07 }}, American Association for Public Opinion Research, Retrieved 2016-06-05</ref>		A 3% margin of error means that if the same procedure is used a large number of times, 95% of the time the true population average will be within the sample estimate plus or minus 3%. The margin of error can be reduced by using a larger sample, however if a pollster wishes to reduce the margin of error to 1% they would need a sample of around 10,000 people.<ref>An estimate of the margin of error in percentage terms can be gained by the formula 100 ÷ square root of sample size</ref> In practice, pollsters need to balance the cost of a large sample against the reduction in sampling error and a sample size of around 500–1,000 is a typical compromise for political polls. (To get complete responses it may be necessary to include thousands of additional participators.)<ref>[http://www.ncpp.org/?q=node/4 20 Questions Journalists Should Ask About Poll Results] {{Webarchive\|url=https://web.archive.org/web/20160604234339/http://www.ncpp.org/?q=node/4 \|date=2016-06-04 }}, National Council on Public Polls Retrieved 2016-06-05</ref><ref>[http://www.aapor.org/Education-Resources/Election-Polling-Resources/Margin-of-Sampling-Error-Credibility-Interval.aspx Margin of Sampling Error and Credibility Interval] {{Webarchive\|url=https://web.archive.org/web/20160707180221/http://www.aapor.org/Education-Resources/Election-Polling-Resources/Margin-of-Sampling-Error-Credibility-Interval.aspx \|date=2016-07-07 }}, American Association for Public Opinion Research, Retrieved 2016-06-05</ref>

2601:243:C300:5BC0:516B:BEC0:3BA:21F9: /* Potential for inaccuracy */

2024-09-24T23:13:16Z

Potential for inaccuracy

← Previous revision		Revision as of 23:13, 24 September 2024
Line 47:		Line 47:

	== Potential for inaccuracy ==		== Potential for inaccuracy ==
	Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref>		Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref> . The Total Survey Error Paradigm (TSE) conceptualizes the error sources in research sampling that may result in an inaccurate poll result. <ref>Robert M Groves and Lars Lyberg. 2010. Total survey error: Past, present, and future. Public opinion quarterly 74, 5 (2010), 849--879
			</ref>

	=== Margin of error due to sampling ===		=== Margin of error due to sampling ===
	Polls based on samples of populations are subject to [[sampling error]] which reflects the effects of chance and uncertainty in the sampling process. Sampling polls rely on the [[law of large numbers]] to measure the opinions of the whole population based only on a subset, and for this purpose the absolute size of the sample is important, but the percentage of the whole population is not important (unless it happens to be close to the sample size). The possible difference between the sample and whole population is often expressed as a [[margin of error]] – usually defined as the radius of a 95% confidence interval for a particular statistic. One example is the percent of people who prefer product A versus product B. When a single, global margin of error is reported for a survey, it refers to the maximum margin of error for all reported percentages using the full sample from the survey. If the statistic is a percentage, this maximum margin of error can be calculated as the radius of the confidence interval for a reported percentage of 50%. Others suggest that a poll with a random sample of 1,000 people has margin of sampling error of ±3% for the estimated percentage of the whole population.		Polls based on samples of populations are subject to [[sampling error]] which reflects the effects of chance and uncertainty in the sampling process. Sampling polls rely on the [[law of large numbers]] to measure the opinions of the whole population based only on a subset, and for this purpose the absolute size of the sample is important, but the percentage of the whole population is not important (unless it happens to be close to the sample size). The possible difference between the sample and whole population is often expressed as a [[margin of error]] – usually defined as the radius of a 95% confidence interval for a particular statistic. One example is the percent of people who prefer product A versus product B. When a single, global margin of error is reported for a survey, it refers to the maximum margin of error for all reported percentages using the full sample from the survey. If the statistic is a percentage, this maximum margin of error can be calculated as the radius of the confidence interval for a reported percentage of 50%. Others suggest that a poll with a random sample of 1,000 people has margin of sampling error of ±3% for the estimated percentage of the whole population.
Line 116:		Line 116:
	# It is difficult to get co-operation from cellphone users, because in many parts of the US, users are charged for both outgoing and incoming calls. That means that pollsters have had to offer financial compensation to gain co-operation.		# It is difficult to get co-operation from cellphone users, because in many parts of the US, users are charged for both outgoing and incoming calls. That means that pollsters have had to offer financial compensation to gain co-operation.
	# US federal law prohibits the use of automated dialling devices to call cellphones ([[Telephone Consumer Protection Act of 1991]]). Numbers therefore have to be dialled by hand, which is more time-consuming and expensive for pollsters.		# US federal law prohibits the use of automated dialling devices to call cellphones ([[Telephone Consumer Protection Act of 1991]]). Numbers therefore have to be dialled by hand, which is more time-consuming and expensive for pollsters.


	== Failures ==		== Failures ==

2601:243:C300:5BC0:516B:BEC0:3BA:21F9: /* Exit polls */

2024-09-24T23:10:01Z

Exit polls

← Previous revision		Revision as of 23:10, 24 September 2024
Line 44:		Line 44:
	Exit polls interview voters just as they are leaving polling places. Unlike general public opinion polls, these are polls of people who voted in the election. Exit polls provide a more accurate picture of which candidates the public prefers in an election because people participating in the poll did vote in the election. Second, these polls are conducted across multiple voting locations across the country, allowing for a comparative analysis between specific regions. For example, in the United States, exit polls are beneficial in accurately determining how the state voters cast their ballot instead of relying on a national survey. Third, exit polls can give journalists and social scientists a greater understanding of why voters voted the way they did and what factors contributed to their vote. <ref name=":1" />		Exit polls interview voters just as they are leaving polling places. Unlike general public opinion polls, these are polls of people who voted in the election. Exit polls provide a more accurate picture of which candidates the public prefers in an election because people participating in the poll did vote in the election. Second, these polls are conducted across multiple voting locations across the country, allowing for a comparative analysis between specific regions. For example, in the United States, exit polls are beneficial in accurately determining how the state voters cast their ballot instead of relying on a national survey. Third, exit polls can give journalists and social scientists a greater understanding of why voters voted the way they did and what factors contributed to their vote. <ref name=":1" />

	Exit polling has several disadvantages that can cause controversy depending on its use. First, these polls are not always accurate and can sometimes mislead election reporting. For instance, during the 2016 U.S. primaries, CNN reported that the Democratic primary in New York was too close to call, and they made this judgment based on exit polls. However, the vote count revealed that these exit polls were misleading, and Hillary Clinton was far ahead of Bernie Sanders in the popular vote, winning the state by 58% to 42% margin. The overreliance on exit polling leads to the second point of how it undermines public trust in the media and the electoral process. In the U.S., Congress and state governments have criticized the use of exit polling because Americans tend to believe more in the accuracy of exit polls. If an exit poll shows that American voters were leaning toward a particular candidate, most would assume that the candidate would win. However, as mentioned earlier, an exit poll can sometimes be inaccurate and lead to situations like the 2016 New York primary, where a news organization reports misleading primary results. Government officials argue that since many Americans believe in exit polls more, election results are likely to make voters not think they are impacted electorally and be more doubtful about the credibility of news organizations.<ref name=":1" />		Exit polling has several disadvantages that can cause controversy depending on its use. First, these polls are not always accurate and can sometimes mislead election reporting. For instance, during the 2016 U.S. primaries, CNN reported that the Democratic primary in New York was too close to call, and they made this judgment based on exit polls. However, the vote count revealed that these exit polls were misleading, and Hillary Clinton was far ahead of Bernie Sanders in the popular vote, winning the state by 58% to 42% margin. The overreliance on exit polling leads to the second point of how it undermines public trust in the media and the electoral process. In the U.S., Congress and state governments have criticized the use of exit polling because Americans tend to believe more in the accuracy of exit polls. If an exit poll shows that American voters were leaning toward a particular candidate, most would assume that the candidate would win. However, as mentioned earlier, an exit poll can sometimes be inaccurate and lead to situations like the 2016 New York primary, where a news organization reports misleading primary results. Due to exit polling, television networks may project election results even before the polls close- Both political elites and a large number of citizens are angered by this practice. <ref>Asher, H. (2017). Polling and the public. CQ Press, https://doi.org/10.4135/9781506352404.</ref> Government officials argue that since many Americans believe in exit polls more, election results are likely to make voters not think they are impacted electorally and be more doubtful about the credibility of news organizations.<ref name=":1" />

	== Potential for inaccuracy ==		== Potential for inaccuracy ==

Citation bot: Altered isbn. Upgrade ISBN10 to 13. | Use this bot. Report bugs. | Suggested by Jay8g | Category:CS1 errors: dates | #UCB_Category 11/39

2024-09-24T06:08:13Z

Altered isbn. Upgrade ISBN10 to 13. | Use this bot. Report bugs. | Suggested by Jay8g | Category:CS1 errors: dates | #UCB_Category 11/39

← Previous revision		Revision as of 06:08, 24 September 2024
Line 47:		Line 47:

	== Potential for inaccuracy ==		== Potential for inaccuracy ==
	Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=~~1464192936~~ \|page=63 \|edition=Ninth}}</ref>		Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref>

	=== Margin of error due to sampling ===		=== Margin of error due to sampling ===
Line 61:		Line 61:

	=== Nonresponse bias ===		=== Nonresponse bias ===
	Since some people do not answer calls from strangers, or refuse to answer the poll, poll samples may not be representative samples from a population due to a [[non-response bias]]. Response rates have been declining, and are down to about 10% in recent years.<ref>{{cite magazine\|url=http://www.slate.com/articles/news_and_politics/politics/2012/05/survey_bias_how_can_we_trust_opinion_polls_when_so_few_people_respond_.single.html\| title=Minority Opinions:Hardly anyone responds to public opinion surveys anymore. Can we still trust them?\|author=Will Oremus\| date=2012-05-17\| access-date=2013-11-21\| magazine=Slate}}</ref> Various pollsters have attributed this to an increased skepticism and lack of interest in polling.<ref>{{cite book \|last=Asher \|first=Herb \|title=Polling and the Public \|date=08/16/2016 \|publisher=CQ Press \|year=2016 \|isbn=~~150635243X~~ \|edition=9th \|pages=28}}</ref> Because of this [[selection bias]], the characteristics of those who agree to be interviewed may be markedly different from those who decline. That is, the actual sample is a biased version of the universe the pollster wants to analyze. In these cases, bias introduces new errors, one way or the other, that are in addition to errors caused by sample size. Error due to bias does not become smaller with larger sample sizes, because taking a larger sample size simply repeats the same mistake on a larger scale. If the people who refuse to answer, or are never reached, have the same characteristics as the people who do answer, then the final results should be unbiased. If the people who do not answer have different opinions then there is bias in the results. In terms of election polls, studies suggest that bias effects are small, but each polling firm has its own techniques for adjusting weights to minimize selection bias.<ref name="Langer2003">{{cite web\|publisher=ABC News\|author=Langer, Gary\|title=About Response Rates: Some Unresolved Questions\|url=https://abcnews.go.com/images/pdf/responserates.pdf\|date=May 2003\|access-date=2010-05-17\|archive-date=2017-07-20\|archive-url=https://web.archive.org/web/20170720004349/http://abcnews.go.com/images/pdf/responserates.pdf\|url-status=live}}</ref><ref>[http://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-FAQ/Response-Rates-An-Overview.aspx Response Rates: An Overview] {{Webarchive\|url=https://web.archive.org/web/20190712004056/https://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-FAQ/Response-Rates-An-Overview.aspx \|date=2019-07-12 }} American Association for Public Opinion Research, Retrieved 2016-06-05</ref>		Since some people do not answer calls from strangers, or refuse to answer the poll, poll samples may not be representative samples from a population due to a [[non-response bias]]. Response rates have been declining, and are down to about 10% in recent years.<ref>{{cite magazine\|url=http://www.slate.com/articles/news_and_politics/politics/2012/05/survey_bias_how_can_we_trust_opinion_polls_when_so_few_people_respond_.single.html\| title=Minority Opinions:Hardly anyone responds to public opinion surveys anymore. Can we still trust them?\|author=Will Oremus\| date=2012-05-17\| access-date=2013-11-21\| magazine=Slate}}</ref> Various pollsters have attributed this to an increased skepticism and lack of interest in polling.<ref>{{cite book \|last=Asher \|first=Herb \|title=Polling and the Public \|date=08/16/2016 \|publisher=CQ Press \|year=2016 \|isbn=978-1506352435 \|edition=9th \|pages=28}}</ref> Because of this [[selection bias]], the characteristics of those who agree to be interviewed may be markedly different from those who decline. That is, the actual sample is a biased version of the universe the pollster wants to analyze. In these cases, bias introduces new errors, one way or the other, that are in addition to errors caused by sample size. Error due to bias does not become smaller with larger sample sizes, because taking a larger sample size simply repeats the same mistake on a larger scale. If the people who refuse to answer, or are never reached, have the same characteristics as the people who do answer, then the final results should be unbiased. If the people who do not answer have different opinions then there is bias in the results. In terms of election polls, studies suggest that bias effects are small, but each polling firm has its own techniques for adjusting weights to minimize selection bias.<ref name="Langer2003">{{cite web\|publisher=ABC News\|author=Langer, Gary\|title=About Response Rates: Some Unresolved Questions\|url=https://abcnews.go.com/images/pdf/responserates.pdf\|date=May 2003\|access-date=2010-05-17\|archive-date=2017-07-20\|archive-url=https://web.archive.org/web/20170720004349/http://abcnews.go.com/images/pdf/responserates.pdf\|url-status=live}}</ref><ref>[http://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-FAQ/Response-Rates-An-Overview.aspx Response Rates: An Overview] {{Webarchive\|url=https://web.archive.org/web/20190712004056/https://www.aapor.org/Education-Resources/For-Researchers/Poll-Survey-FAQ/Response-Rates-An-Overview.aspx \|date=2019-07-12 }} American Association for Public Opinion Research, Retrieved 2016-06-05</ref>

← Previous revision		Revision as of 18:53, 27 September 2024
Line 1:		Line 1:
	{{copyvio-revdel\|url=https://us.sagepub.com/sites/default/files/upm-assets/76580_book_item_76580.pdf\|start1=1247155241\|end1=1247155389}}
	{{Short description\|Type of survey}}		{{Short description\|Type of survey}}
	{{Globalize\|article\|Anglophone\|2name=[[English-speaking world\|the English-speaking world]]\|date=May 2023}}		{{Globalize\|article\|Anglophone\|2name=[[English-speaking world\|the English-speaking world]]\|date=May 2023}}

← Previous revision		Revision as of 23:51, 24 September 2024
Line 3:		Line 3:
	{{Globalize\|article\|Anglophone\|2name=[[English-speaking world\|the English-speaking world]]\|date=May 2023}}		{{Globalize\|article\|Anglophone\|2name=[[English-speaking world\|the English-speaking world]]\|date=May 2023}}

	An '''opinion poll''', often simply referred to as a '''survey''' or a '''poll''' (although strictly a poll is an actual election), is a [[survey (human research)\|human research survey]] of [[public opinion]] from a particular [[sampling (statistics)\|sample]]. Opinion polls are usually designed to represent the opinions of a population by conducting a series of questions and then extrapolating generalities in ratio or within [[confidence intervals]]. A person who conducts polls is referred to as a '''pollster'''. Polling is especially valued by those who prefer a democracy in which the people govern independently rather than through representatives. <ref>Asher, H. (2017). Polling and the public. CQ Press, https://doi.org/10.4135/9781506352404</ref>		An '''opinion poll''', often simply referred to as a '''survey''' or a '''poll''' (although strictly a poll is an actual election), is a [[survey (human research)\|human research survey]] of [[public opinion]] from a particular [[sampling (statistics)\|sample]]. Opinion polls are usually designed to represent the opinions of a population by conducting a series of questions and then extrapolating generalities in ratio or within [[confidence intervals]]. A person who conducts polls is referred to as a '''pollster'''.

	== History ==		== History ==
Line 44:		Line 44:
	Exit polls interview voters just as they are leaving polling places. Unlike general public opinion polls, these are polls of people who voted in the election. Exit polls provide a more accurate picture of which candidates the public prefers in an election because people participating in the poll did vote in the election. Second, these polls are conducted across multiple voting locations across the country, allowing for a comparative analysis between specific regions. For example, in the United States, exit polls are beneficial in accurately determining how the state voters cast their ballot instead of relying on a national survey. Third, exit polls can give journalists and social scientists a greater understanding of why voters voted the way they did and what factors contributed to their vote. <ref name=":1" />		Exit polls interview voters just as they are leaving polling places. Unlike general public opinion polls, these are polls of people who voted in the election. Exit polls provide a more accurate picture of which candidates the public prefers in an election because people participating in the poll did vote in the election. Second, these polls are conducted across multiple voting locations across the country, allowing for a comparative analysis between specific regions. For example, in the United States, exit polls are beneficial in accurately determining how the state voters cast their ballot instead of relying on a national survey. Third, exit polls can give journalists and social scientists a greater understanding of why voters voted the way they did and what factors contributed to their vote. <ref name=":1" />

	Exit polling has several disadvantages that can cause controversy depending on its use. First, these polls are not always accurate and can sometimes mislead election reporting. For instance, during the 2016 U.S. primaries, CNN reported that the Democratic primary in New York was too close to call, and they made this judgment based on exit polls. However, the vote count revealed that these exit polls were misleading, and Hillary Clinton was far ahead of Bernie Sanders in the popular vote, winning the state by 58% to 42% margin. The overreliance on exit polling leads to the second point of how it undermines public trust in the media and the electoral process. In the U.S., Congress and state governments have criticized the use of exit polling because Americans tend to believe more in the accuracy of exit polls. If an exit poll shows that American voters were leaning toward a particular candidate, most would assume that the candidate would win. However, as mentioned earlier, an exit poll can sometimes be inaccurate and lead to situations like the 2016 New York primary, where a news organization reports misleading primary results. Due to exit polling, television networks may project election results even before the polls close- Both political elites and a large number of citizens are angered by this practice. <ref>Asher, H. (2017). Polling and the public. CQ Press, https://doi.org/10.4135/9781506352404.</ref> Government officials argue that since many Americans believe in exit polls more, election results are likely to make voters not think they are impacted electorally and be more doubtful about the credibility of news organizations.<ref name=":1" />		Exit polling has several disadvantages that can cause controversy depending on its use. First, these polls are not always accurate and can sometimes mislead election reporting. For instance, during the 2016 U.S. primaries, CNN reported that the Democratic primary in New York was too close to call, and they made this judgment based on exit polls. However, the vote count revealed that these exit polls were misleading, and Hillary Clinton was far ahead of Bernie Sanders in the popular vote, winning the state by 58% to 42% margin. The overreliance on exit polling leads to the second point of how it undermines public trust in the media and the electoral process. In the U.S., Congress and state governments have criticized the use of exit polling because Americans tend to believe more in the accuracy of exit polls. If an exit poll shows that American voters were leaning toward a particular candidate, most would assume that the candidate would win. However, as mentioned earlier, an exit poll can sometimes be inaccurate and lead to situations like the 2016 New York primary, where a news organization reports misleading primary results. Government officials argue that since many Americans believe in exit polls more, election results are likely to make voters not think they are impacted electorally and be more doubtful about the credibility of news organizations.<ref name=":1" />

	== Potential for inaccuracy ==		== Potential for inaccuracy ==
	Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref> . The Total Survey Error Paradigm (TSE) conceptualizes the error sources in research sampling that may result in an inaccurate poll result. <ref>Robert M Groves and Lars Lyberg. 2010. Total survey error: Past, present, and future. Public opinion quarterly 74, 5 (2010), 849--879		Over time, a number of theories and mechanisms have been offered to explain erroneous polling results. Some of these reflect errors on the part of the pollsters; many of them are statistical in nature. Some blame respondents for not providing genuine answers to pollsters, a phenomenon known as [[Social-desirability bias\|social desirability-bias]] (also referred to as [[Bradley effect\|the Bradley effect]] or [[Shy Tory factor\|the Shy Tory Factor]]); these terms can be quite controversial.<ref>{{cite book \|last1=Moore \|first1=David S. \|last2=Notz \|first2=William \|title=Statistics: concepts and controversies \|date=2017 \|publisher=W.H. Freeman and Company, Macmillan Learning \|location=New York \|isbn=978-1464192937 \|page=63 \|edition=Ninth}}</ref>
	</ref>. Citizens do not need to become experts at sampling, constructing questionnaires, or analyzing data to be better consumers of public opinion research- Instead, they can become aware of the steps involved in conducting a survey and the possible productions of error. <ref>Asher, H. (2017). Polling and the public. CQ Press, https://doi.org/10.4135/9781506352404</ref>

	=== Margin of error due to sampling ===		=== Margin of error due to sampling ===
	Polls based on samples of populations are subject to [[sampling error]] which reflects the effects of chance and uncertainty in the sampling process. Sampling polls rely on the [[law of large numbers]] to measure the opinions of the whole population based only on a subset, and for this purpose the absolute size of the sample is important, but the percentage of the whole population is not important (unless it happens to be close to the sample size). The possible difference between the sample and whole population is often expressed as a [[margin of error]] – usually defined as the radius of a 95% confidence interval for a particular statistic. One example is the percent of people who prefer product A versus product B. When a single, global margin of error is reported for a survey, it refers to the maximum margin of error for all reported percentages using the full sample from the survey. If the statistic is a percentage, this maximum margin of error can be calculated as the radius of the confidence interval for a reported percentage of 50%. Others suggest that a poll with a random sample of 1,000 people has margin of sampling error of ±3% for the estimated percentage of the whole population. Studies show that public opinion polls are more confident than accurate- we find that reported 95% confidence intervals are only 60% accurate. <ref>Kotak, A., & Moore, D. A. (2020, October 20). Public Election Polls are 95% Confident but only 60% Accurate. https://doi.org/10.31234/osf.io/rj643</ref>		Polls based on samples of populations are subject to [[sampling error]] which reflects the effects of chance and uncertainty in the sampling process. Sampling polls rely on the [[law of large numbers]] to measure the opinions of the whole population based only on a subset, and for this purpose the absolute size of the sample is important, but the percentage of the whole population is not important (unless it happens to be close to the sample size). The possible difference between the sample and whole population is often expressed as a [[margin of error]] – usually defined as the radius of a 95% confidence interval for a particular statistic. One example is the percent of people who prefer product A versus product B. When a single, global margin of error is reported for a survey, it refers to the maximum margin of error for all reported percentages using the full sample from the survey. If the statistic is a percentage, this maximum margin of error can be calculated as the radius of the confidence interval for a reported percentage of 50%. Others suggest that a poll with a random sample of 1,000 people has margin of sampling error of ±3% for the estimated percentage of the whole population.


	A 3% margin of error means that if the same procedure is used a large number of times, 95% of the time the true population average will be within the sample estimate plus or minus 3%. The margin of error can be reduced by using a larger sample, however if a pollster wishes to reduce the margin of error to 1% they would need a sample of around 10,000 people.<ref>An estimate of the margin of error in percentage terms can be gained by the formula 100 ÷ square root of sample size</ref> In practice, pollsters need to balance the cost of a large sample against the reduction in sampling error and a sample size of around 500–1,000 is a typical compromise for political polls. (To get complete responses it may be necessary to include thousands of additional participators.)<ref>[http://www.ncpp.org/?q=node/4 20 Questions Journalists Should Ask About Poll Results] {{Webarchive\|url=https://web.archive.org/web/20160604234339/http://www.ncpp.org/?q=node/4 \|date=2016-06-04 }}, National Council on Public Polls Retrieved 2016-06-05</ref><ref>[http://www.aapor.org/Education-Resources/Election-Polling-Resources/Margin-of-Sampling-Error-Credibility-Interval.aspx Margin of Sampling Error and Credibility Interval] {{Webarchive\|url=https://web.archive.org/web/20160707180221/http://www.aapor.org/Education-Resources/Election-Polling-Resources/Margin-of-Sampling-Error-Credibility-Interval.aspx \|date=2016-07-07 }}, American Association for Public Opinion Research, Retrieved 2016-06-05</ref>		A 3% margin of error means that if the same procedure is used a large number of times, 95% of the time the true population average will be within the sample estimate plus or minus 3%. The margin of error can be reduced by using a larger sample, however if a pollster wishes to reduce the margin of error to 1% they would need a sample of around 10,000 people.<ref>An estimate of the margin of error in percentage terms can be gained by the formula 100 ÷ square root of sample size</ref> In practice, pollsters need to balance the cost of a large sample against the reduction in sampling error and a sample size of around 500–1,000 is a typical compromise for political polls. (To get complete responses it may be necessary to include thousands of additional participators.)<ref>[http://www.ncpp.org/?q=node/4 20 Questions Journalists Should Ask About Poll Results] {{Webarchive\|url=https://web.archive.org/web/20160604234339/http://www.ncpp.org/?q=node/4 \|date=2016-06-04 }}, National Council on Public Polls Retrieved 2016-06-05</ref><ref>[http://www.aapor.org/Education-Resources/Election-Polling-Resources/Margin-of-Sampling-Error-Credibility-Interval.aspx Margin of Sampling Error and Credibility Interval] {{Webarchive\|url=https://web.archive.org/web/20160707180221/http://www.aapor.org/Education-Resources/Election-Polling-Resources/Margin-of-Sampling-Error-Credibility-Interval.aspx \|date=2016-07-07 }}, American Association for Public Opinion Research, Retrieved 2016-06-05</ref>
Line 118:		Line 116:
	# It is difficult to get co-operation from cellphone users, because in many parts of the US, users are charged for both outgoing and incoming calls. That means that pollsters have had to offer financial compensation to gain co-operation.		# It is difficult to get co-operation from cellphone users, because in many parts of the US, users are charged for both outgoing and incoming calls. That means that pollsters have had to offer financial compensation to gain co-operation.
	# US federal law prohibits the use of automated dialling devices to call cellphones ([[Telephone Consumer Protection Act of 1991]]). Numbers therefore have to be dialled by hand, which is more time-consuming and expensive for pollsters.		# US federal law prohibits the use of automated dialling devices to call cellphones ([[Telephone Consumer Protection Act of 1991]]). Numbers therefore have to be dialled by hand, which is more time-consuming and expensive for pollsters.


	== Failures ==		== Failures ==