<!DOCTYPE html>

<html data-programme="Research Integrity" data-course="Data Selection, Analysis and Presentation">

	<head>
		<title>Data selection</title>
		<meta charset="UTF-8">
		<meta http-equiv="X-UA-Compatible" content="IE=edge">
		<meta name="viewport" content="width=device-width, initial-scale=1">

		<link rel="stylesheet" type="text/css" href="../css/project.min.css">
		<link id="basic-print" rel="stylesheet" type="text/css" href="../css/print.min.css" disabled>
		<link id="summary-print" rel="stylesheet" type="text/css" href="../css/print_interactive.min.css">
	<script type="text/javascript" src="../scripts_scorm_12/SCORM_12_APIWrapper.js"></script>
<script type="text/javascript" src="../scripts_scorm_12/courseFunctions.js"></script>
</head>

	<body onLoad="javascript:Initialize();" onUnload="javascript:Terminate();">
	  
		<div id="app" v-cloak>
			<base-container
				screen-id="dap_1_20"
				current-module = "Data Selection, Analysis and Presentation"
				page-title = "Data selection"
				screen-time = "4"
				screen-time-period = "mins">

				<page-container>

					<page-row>
						<page-content-main>
							
							<p>There are many different research methodologies, but in general research starts with a carefully formulated research question (or questions). Researchers often don't know what they are going to find in the course of seeking the answer to their question. In principle, everything a researcher discovers, measures or finds could be taken into consideration as the research is undertaken, but what about in practice? Should everything that is found be considered?  </p>
							
							<h3>Selection</h3>
							
							<p>Handling research information properly throughout the collection and interpretation stages of research is crucial to the responsible conduct of research. This begins with making responsible decisions about how data/information is created and/or <glossary content="The process of reviewing raw data and deciding which information should be used in or excluded from the interpretive process that follows.">selected</glossary>.</p>
							<p>Why should any information be excluded from interpretation?</p>
							
							<instructional-text><p>Match the practical scenario on the left-hand side with the reason why this situation might lead to data being excluded on the right-hand side. To link the scenario to the reason, first click on the scenario in the left-hand column and then click on the reason in the right-hand column. Once you have matched a pair correctly, it will move to the top of the activity.</p></instructional-text>
							<instructional-text-accessible><p>Continue on to match the practical scenario with the reason why this situation might lead to data being excluded. Once you have matched each pair, continue on to find out if you were correct.</p></instructional-text-accessible>
							
							<!-- ACTIVITY START -->
							<matching>
								<matching-set>
									<match-left>After 30 days of using a piece of equipment to collect data, you discover that the equipment was not calibrated properly on two of those days.</match-left>
									<match-right>Technical oversight</match-right>
								</matching-set>
								<matching-set>
									<match-left>Some consent forms for a survey research project were not signed.</match-left>
									<match-right>Researcher error</match-right>
								</matching-set>
								<matching-set>
									<match-left>A painting used in the study of an artistic tradition could not be authenticated.</match-left>
									<match-right>Unreliable data/information</match-right>
								</matching-set>
								<matching-set>
									<match-left>A number of participants in a clinical trial did not follow instructions.</match-left>
									<match-right>Protocol did not run as planned</match-right>
								</matching-set>
								<matching-set>
									<match-left>The behaviour of a group of animals studied in the wild could have been disturbed by an outside influence.</match-left>
									<match-right>Unexpected conditions and events</match-right>
								</matching-set>
								<matching-set></matching-set>
							</matching>
							<!-- ACTIVITY END -->
							
							<p>These are examples of some good reasons for excluding information &ndash; most researchers will encounter at least one such scenario when sitting down and sifting through the data they have gathered. The most important thing is to ensure that the reasons behind your selections (and especially your omissions) are explained when you report your findings.</p>
							
							<h3>Irresponsible data selection practices</h3>
							
							<p>Where do researchers go wrong when they select information for analysis? Here are just a few of the ways in which researchers have been known to improperly select the results they go on to interpret and report.</p>
							
							<instructional-text><p>Click on each practice to access a more detailed description.</p></instructional-text>
							<instructional-text-accessible><p>Continue on for a list of some of these practices and their corresponding definitions.</p></instructional-text-accessible>
							
							<!-- ACTIVITY START -->
							<labelled-text show-in-accessible-version="false">
								<p><text-label content="Ignore some interviews or pick selective documents from a record that includes contradictory information." placement="top">Pick and choose evidence</text-label></p>
								<p><text-label content="Arbitrarily select one time period within a study conducted over a longer period of time." placement="top">Selective use of time periods</text-label></p>
								<p><text-label content="Delete data without disclosure before performing data analysis." placement="top">Delete unwanted data</text-label></p>
								<p><text-label content="Make up data to fill in gaps or simulate work that has not been undertaken." placement="top">Fabricate data</text-label></p>
								<p><text-label content="Ignore results or evidence suggesting that the study could not be replicated." placement="top">Ignore conflicting evidence</text-label></p>
								<p><text-label content="Use the wrong control data." placement="top">Improper controls</text-label></p>
								<p><text-label content="Omit information from the full scope of the data collection specified in the original protocol." placement="top">Ignore protocol requirements</text-label></p>
								<p><text-label content="Stop data collection earlier than planned (unless a provision is made for early termination in the protocol, as is the case in some clinical trials)." placement="top">Terminate study prematurely</text-label></p>
							</labelled-text>
							<!-- ACCESSIBLE BLOCK -->
							<accessible-block>
								<h4>Pick and choose evidence</h4>
								<p>Ignore some interviews or pick selective documents from a record that includes contradictory information.</p>
								<hr>
								<h4>Selective use of time periods</h4>
								<p>Arbitrarily select one time period within a study conducted over a longer period of time.</p>
								<hr>
								<h4>Delete unwanted data</h4>
								<p>Delete data without disclosure before performing data analysis.</p>
								<hr>
								<h4>Fabricate data</h4>
								<p>Make up data to fill in gaps or simulate work that has not been undertaken.</p>
								<hr>
								<h4>Ignore conflicting evidence</h4>
								<p>Ignore results or evidence suggesting that the study could not be replicated.</p>
								<hr>
								<h4>Improper controls</h4>
								<p>Use the wrong control data.</p>
								<hr>
								<h4>Ignore protocol requirements</h4>
								<p>Omit information from the full scope of the data collection specified in the original protocol.</p>
								<hr>
								<h4>Terminate study prematurely</h4>
								<p>Stop data collection earlier than planned (unless a provision is made for early termination in the protocol, as is the case in some clinical trials).</p>
							</accessible-block>
							<!-- ACTIVITY END -->
							
						</page-content-main>
					</page-row>
					
					<page-row>
						<page-content-main>
							
							<p>In each of these situations, selection is being used to cover up contradictory information or strengthen the significance of the results. It is irresponsible to do this, particularly if the selection process is not fully explained and justified.</p>
							
							<h3>Summary</h3>
							
							<p>Only using some of the information/data collected when you conducted your research is not necessarily irresponsible. Researchers are expected to look carefully at their results and select information that is relevant to their study. If you do make selections, you should ensure you:</p>
							
							<ul>
								<li>Know the best practices for your field </li>
								<li>Discuss your data selection plans with colleagues, peers and mentors to gain their advice and expertise</li>
								<li>Are completely clear about what you have done, and the decisions you have made, when you present or discuss your data</li>
								<li>Are aware of and take steps to avoid <glossary content="The natural human tendency to select data that supports the conclusions you would like to reach.">confirmation bias</glossary> (for a link to an article covering more types of bias, refer to the "Additional information" pod).</li>
							</ul>
							
						</page-content-main>

						<page-content-sidebar>

							<!-- Additional information START -->
                            <pod variant="b" has-modal="true">
                                <pod-heading>Additional information</pod-heading>
                                <pod-content></pod-content>
                                <!-- pop-up pod content -->
                                <pod-modal-heading>Additional information</pod-modal-heading>
                                <pod-modal-content>
									<hosted-link id="RI_INT_dap_1_20">
										<p>For an introduction to types of bias in research, see the BMJ article titled <a href="https://ebn.bmj.com/content/ebnurs/17/4/100.full.pdf" target="_blank">Bias in Research</a>.</p>
									</hosted-link>
                                </pod-modal-content>
                            </pod>
                            <!-- Additional information END -->

						</page-content-sidebar>
					</page-row>
					
				</page-container>
			</base-container>
		</div> <!-- END content wrapper -->
		
		<!-- scripts -->
		<script src="../js/vendor.min.js"></script>
		<script src="../js/vue-components.min.js"></script>
		<script>
			new Vue({
			  el: "#app",
			  data: {},
			  mounted: function () {
				var core = document.createElement('script');
				core.src = "../js/core.min.js";
				document.getElementsByTagName('head')[0].appendChild(core);

				var project = document.createElement('script');
				project.src = "../js/project.min.js";
				document.getElementsByTagName('head')[0].appendChild(project);
			  }
			});
		</script>

	</body>
</html>