{"id":6131,"date":"2024-04-11T07:52:51","date_gmt":"2024-04-11T07:52:51","guid":{"rendered":"https:\/\/hacto.umh.es\/2024\/04\/11\/tipos-de-errores-en-los-estudios-de-investigacion\/"},"modified":"2026-05-29T09:54:51","modified_gmt":"2026-05-29T09:54:51","slug":"types-of-errors-in-research-studies","status":"publish","type":"post","link":"https:\/\/hacto.umh.es\/en\/2024\/04\/11\/types-of-errors-in-research-studies\/","title":{"rendered":"Types of errors in research studies"},"content":{"rendered":"<p>[et_pb_section fb_built=&#8221;1&#8243; _builder_version=&#8221;4.17.4&#8243; global_colors_info=&#8221;{}&#8221;][et_pb_row _builder_version=&#8221;4.17.4&#8243; global_colors_info=&#8221;{}&#8221;][et_pb_column type=&#8221;4_4&#8243; _builder_version=&#8221;4.16&#8243; custom_padding=&#8221;|||&#8221; global_colors_info=&#8221;{}&#8221; custom_padding__hover=&#8221;|||&#8221;][et_pb_text admin_label=&#8221;Texto&#8221; _builder_version=&#8221;4.17.4&#8243; vertical_offset_tablet=&#8221;0&#8243; horizontal_offset_tablet=&#8221;0&#8243; z_index_tablet=&#8221;0&#8243; text_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; text_text_shadow_vertical_length_tablet=&#8221;0px&#8221; text_text_shadow_blur_strength_tablet=&#8221;1px&#8221; link_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; link_text_shadow_vertical_length_tablet=&#8221;0px&#8221; link_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ul_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ul_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ul_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ol_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ol_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ol_text_shadow_blur_strength_tablet=&#8221;1px&#8221; quote_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; quote_text_shadow_vertical_length_tablet=&#8221;0px&#8221; quote_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_2_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_2_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_2_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_3_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_3_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_3_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_4_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_4_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_4_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_5_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_5_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_5_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_6_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_6_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_6_text_shadow_blur_strength_tablet=&#8221;1px&#8221; box_shadow_horizontal_tablet=&#8221;0px&#8221; box_shadow_vertical_tablet=&#8221;0px&#8221; box_shadow_blur_tablet=&#8221;40px&#8221; box_shadow_spread_tablet=&#8221;0px&#8221; global_colors_info=&#8221;{}&#8221;]<\/p>\n<p style=\"text-align: justify;\">What determines whether a study is valid? The validity of a study depends on the extent to which the results obtained are accurate in answering the research question posed. There are two validity criteria: <u>external validity <\/u> refers to the study&#8217;s ability to generalise the results obtained from the study sample to the reference population, while <u>internal validity <\/u> refers to errors made during the research process. With this in mind, there are two types of error that can affect the validity of a study:<\/p>\n<ul style=\"text-align: justify;\">\n<li><strong>Random error: <\/strong> this is due to chance and cannot be avoided, though it can be reduced. It may arise from biological variability between individuals. In this case, the error can be reduced by increasing the sample size, choosing more precise measurement instruments, or taking measurements on multiple occasions.<\/li>\n<li><strong>Systematic error or bias: <\/strong>this occurs in the design or data analysis of the study. It is a predictable error and must therefore be avoided. The most well-known biases are selection bias, information bias, and confounding bias, although many others exist.<\/li>\n<\/ul>\n<p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=&#8221;1_4,1_2,1_4&#8243; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_column type=&#8221;1_4&#8243; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][\/et_pb_column][et_pb_column type=&#8221;1_2&#8243; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_image src=&#8221;https:\/\/hacto.umh.es\/files\/2024\/04\/1.png&#8221; title_text=&#8221;1&#8243; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][\/et_pb_image][et_pb_button button_url=&#8221;https:\/\/drive.google.com\/uc?export=download&amp;id=1stOSKlsH-zWe1Wb3MZLooQZ-6QpYtsSA&#8221; button_text=&#8221;Download&#8221; button_alignment=&#8221;center&#8221; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; hover_enabled=&#8221;0&#8243; global_colors_info=&#8221;{}&#8221; sticky_enabled=&#8221;0&#8243;][\/et_pb_button][\/et_pb_column][et_pb_column type=&#8221;1_4&#8243; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_column type=&#8221;4_4&#8243; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_text admin_label=&#8221;Texto&#8221; _builder_version=&#8221;4.17.4&#8243; vertical_offset_tablet=&#8221;0&#8243; horizontal_offset_tablet=&#8221;0&#8243; z_index_tablet=&#8221;0&#8243; text_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; text_text_shadow_vertical_length_tablet=&#8221;0px&#8221; text_text_shadow_blur_strength_tablet=&#8221;1px&#8221; link_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; link_text_shadow_vertical_length_tablet=&#8221;0px&#8221; link_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ul_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ul_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ul_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ol_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ol_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ol_text_shadow_blur_strength_tablet=&#8221;1px&#8221; quote_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; quote_text_shadow_vertical_length_tablet=&#8221;0px&#8221; quote_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_2_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_2_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_2_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_3_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_3_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_3_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_4_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_4_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_4_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_5_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_5_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_5_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_6_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_6_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_6_text_shadow_blur_strength_tablet=&#8221;1px&#8221; box_shadow_horizontal_tablet=&#8221;0px&#8221; box_shadow_vertical_tablet=&#8221;0px&#8221; box_shadow_blur_tablet=&#8221;40px&#8221; box_shadow_spread_tablet=&#8221;0px&#8221; global_colors_info=&#8221;{}&#8221;]<\/p>\n<p style=\"text-align: justify;\"><strong><u>Types of bias<\/u><\/strong><\/p>\n<ol style=\"text-align: justify;\">\n<li><strong>Selection bias<\/strong><\/li>\n<\/ol>\n<p style=\"text-align: justify;\">This is a type of systematic error that occurs when study participants are selected incorrectly, resulting in a sample that is not representative of the population due to flawed inclusion and exclusion criteria or an inappropriate recruitment approach. The most important types are summarised below:<\/p>\n<table>\n<tbody>\n<tr>\n<td style=\"text-align: center;\" width=\"189\"><strong>Cause<\/strong><\/td>\n<td style=\"text-align: center;\" width=\"217\"><strong>Definition<\/strong><\/td>\n<td style=\"text-align: center;\" width=\"160\"><strong>Study type where common<\/strong><\/td>\n<\/tr>\n<tr>\n<td width=\"189\"><strong>Incorrect selection of study groups<\/strong><\/td>\n<td width=\"217\">The groups being compared differ in ways beyond the factor being assessed.<\/td>\n<td width=\"160\">Cohort, case-control, and clinical trial studies<\/td>\n<\/tr>\n<tr>\n<td width=\"189\"><strong>Loss to follow-up<\/strong><\/td>\n<td width=\"217\">Participants drop out, but not at random.<\/td>\n<td width=\"160\">Cohort studies, clinical trials<\/td>\n<\/tr>\n<tr>\n<td width=\"189\"><strong>Non-response<\/strong><\/td>\n<td width=\"217\">When data are collected through interviews or surveys, respondents commonly fail to answer all questions.<\/td>\n<td width=\"160\">Cross-sectional, cohort, case-control, and clinical trial studies.<\/td>\n<\/tr>\n<tr>\n<td width=\"189\"><strong>Selective survival<\/strong><\/td>\n<td width=\"217\">Common when individuals who already have the disease are selected rather than those who are at the onset of the disease.<\/td>\n<td width=\"160\">Case-control studies<\/td>\n<\/tr>\n<tr>\n<td width=\"189\"><strong>Self-selection or volunteer bias<\/strong><\/td>\n<td width=\"217\">Volunteers may not meet the same criteria or may have different characteristics from the target population.<\/td>\n<td width=\"160\">Cross-sectional, cohort, and clinical trial studies.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p style=\"text-align: justify;\">Consider an occupational therapy study investigating the effectiveness of a rehabilitation programme for patients with acquired brain injury. The aim is to compare functional outcomes between two groups: one following the rehabilitation programme and one continuing with their usual routine. An example of selection bias would occur if participants were not randomly assigned to the intervention (rehabilitation) or control (usual routine) group, and those allocated to the rehabilitation group happened to have more severe sequelae than those in the control group, with 60% of the rehabilitation group dropping out before completion while all control group participants completed the study. Another example of selection bias would be if, despite randomisation having been carried out, the control group \u2014 not receiving rehabilitation \u2014 chose not to attend the final assessment, thus constituting a dropout. Ways to prevent selection bias in this case:<\/p>\n<ul style=\"text-align: justify;\">\n<li>Randomising study participants.<\/li>\n<li>Ensuring an adequate sample size for randomisation to function correctly (the importance of calculating sample size).<\/li>\n<li>Defining clear inclusion and exclusion criteria.<\/li>\n<li>Minimising loss to follow-up by implementing participant retention strategies.<\/li>\n<li>Prior to allocation, providing participants with detailed information about the study, including the potential issues that may arise if they withdraw, so that they can make a more informed decision about their participation.<\/li>\n<li>Prior to allocation, informing participants that those assigned to the control group will receive the rehabilitation programme after the study has concluded.<\/li>\n<li>Attempting to collect final data from all participants, even those who did not attend all sessions.<\/li>\n<li>Conducting intention-to-treat analyses that is, analysing data according to the group to which participants were originally assigned, including all participants regardless of whether they dropped out.<\/li>\n<li>Performing sensitivity analyses stratified by number of sessions attended or other markers of treatment adherence.<\/li>\n<li>Considering potential confounding variables (see below).<\/li>\n<\/ul>\n<ol style=\"text-align: justify;\" start=\"2\">\n<li><strong>Information bias<\/strong><\/li>\n<\/ol>\n<p style=\"text-align: justify;\">This is a type of systematic error that occurs during data collection and may lead to incorrect classification of participants with respect to exposure and\/or outcome. It can be <u>non-differential <\/u>, occurring equally across all participants (exposed and unexposed \/ diseased and non-diseased) or <u> differential,<\/u> when it affects only a subgroup (e.g. only those with the disease, or only the unexposed). This type of bias can arise, for example, from using measurement instruments with poor sensitivity or specificity, applying incorrect diagnostic criteria, or imprecision in data collection. An example in occupational therapy would be the use of an assessment tool whose psychometric properties have not been evaluated, or whose properties have been evaluated but not in the population of interest. Ways to prevent it:<\/p>\n<ul style=\"text-align: justify;\">\n<li>Using assessment instruments whose psychometric properties have been evaluated.<\/li>\n<li>Using assessment instruments that are valid and reliable for the population in which they will be applied.<\/li>\n<li>Using instruments capable of discriminating between individuals with and without the condition.<\/li>\n<li>Training the staff who will administer the tools.<\/li>\n<li>Following the administration instructions for the tool faithfully.<\/li>\n<\/ul>\n<p style=\"text-align: justify;\">Consider a study evaluating the effectiveness of an intervention programme on motor function improvement in patients who have undergone surgery for trapeziometacarpal osteoarthritis (rhizarthrosis). During the study, self-administered questionnaires are used to gather information on participants&#8217; pain levels during cooking activities. As the questionnaire is self-administered, information bias could arise for various reasons: participants may underestimate or overestimate their pain, misunderstand the questions, be influenced by emotional factors in their responses, or find that cooking is not a meaningful activity for them. Ways to prevent it:<\/p>\n<ul style=\"text-align: justify;\">\n<li>Ensuring questions are clear for different types of respondents (varying educational levels, ages, cultural backgrounds, etc.).<\/li>\n<li>Ensuring the tools used have been tested for validity and reliability in this population (<a href=\"https:\/\/hacto.umh.es\/2023\/03\/23\/herramientas-de-evaluacion-en-terapia-ocupacional-clinica-e-investigacion\/\">click <\/a> to find out more)<\/li>\n<li>Training those who will explain the tool to participants and following the developers&#8217; instructions faithfully.<\/li>\n<li>Guaranteeing the confidentiality and anonymity of respondents.<\/li>\n<li>Collecting other variables that may help to contextualise participants&#8217; responses.<\/li>\n<\/ul>\n<ol style=\"text-align: justify;\" start=\"3\">\n<li><strong>Confounding bias<\/strong><\/li>\n<\/ol>\n<p style=\"text-align: justify;\">This is a type of systematic error that occurs when an association between two variables is observed without accounting for the influence of a third variable \u2014 known as a confounding variable. This third variable must be independently associated with both variables (the exposure variable and the outcome variable) and must not lie on the causal pathway between them \u2014 that is, the occurrence of one must not require the prior occurrence of the other. An example in occupational therapy would be a study examining the impact of cocaine use on occupational performance in which questions about exposure to other substances (e.g. alcohol) are not collected. Since alcohol use is a risk factor for both occupational performance difficulties and cocaine use, failing to account for this variable in the analysis could distort the results. Ways to prevent or more precisely, to control it:<\/p>\n<ul style=\"text-align: justify;\">\n<li>Identifying and collecting all potential confounding variables in the study, which requires a thorough knowledge of the prior evidence on the topic.<\/li>\n<li>Using statistical analysis models that allow adjustment for the identified confounding variables.<\/li>\n<li>Conducting stratified analyses to examine the association between the exposure and outcome variables within different levels of the confounding variables.<\/li>\n<li>Conducting sensitivity analyses to assess the impact of confounding variables on the study results.<\/li>\n<\/ul>\n<p style=\"text-align: justify;\"><strong>The following table provides a summary of the different types of errors and biases, along with their potential consequences and control measures:<\/strong><\/p>\n<table width=\"576\">\n<tbody>\n<tr>\n<td style=\"text-align: center;\" rowspan=\"2\" width=\"111\"><strong>Type of error<\/strong><\/td>\n<td style=\"text-align: center;\" rowspan=\"2\" width=\"153\"><strong>Consequence<\/strong><\/td>\n<td style=\"text-align: center;\" colspan=\"2\" width=\"312\"><strong>Control<\/strong><\/td>\n<\/tr>\n<tr>\n<td style=\"text-align: center;\" width=\"198\"><strong>Design<\/strong><\/td>\n<td style=\"text-align: center;\" width=\"113\"><strong>Analysis<\/strong><\/td>\n<\/tr>\n<tr>\n<td colspan=\"4\" width=\"576\"><strong>Random error<\/strong><\/td>\n<\/tr>\n<tr>\n<td width=\"111\"><\/td>\n<td style=\"text-align: center;\" width=\"153\">Affects external validity.<\/td>\n<td style=\"text-align: center;\" width=\"198\">Increase sample size or measurement precision.<\/td>\n<td width=\"113\"><\/td>\n<\/tr>\n<tr>\n<td colspan=\"4\" width=\"576\"><strong>Systematic error \/ bias<\/strong><\/td>\n<\/tr>\n<tr>\n<td style=\"text-align: center;\" width=\"111\"><strong>Selection<\/strong><\/td>\n<td style=\"text-align: center;\" width=\"153\">Affects internal validity..<\/td>\n<td style=\"text-align: center;\" width=\"198\">In clinical trials, randomisation can be used. In observational studies, strict selection criteria must be established.<\/td>\n<td style=\"text-align: center;\" width=\"113\"><\/td>\n<\/tr>\n<tr>\n<td style=\"text-align: center;\" width=\"111\"><strong>Classification<\/strong><\/td>\n<td style=\"text-align: center;\" width=\"153\">Affects internal validity.<\/td>\n<td style=\"text-align: center;\" width=\"198\">Designate a single person to assess all participants; ensure they are blinded to participant identity. Use valid and reliable assessment tools.<\/td>\n<td width=\"113\"><\/td>\n<\/tr>\n<tr>\n<td style=\"text-align: center;\" width=\"111\"><strong>Confounding<\/strong><\/td>\n<td style=\"text-align: center;\" width=\"153\">Affects internal validity.<\/td>\n<td style=\"text-align: center;\" width=\"198\"><\/td>\n<td style=\"text-align: center;\" width=\"113\">Stratified and adjusted analyses<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n<p style=\"text-align: justify;\">\u00a0 Since it is very difficult to eliminate all biases, it is important to declare them in the limitations section of the article, and to bear them in mind when reading other publications. The presence of these biases will affect the validity of the study, making it essential to plan an appropriate design and analysis with the aim of minimising them as far as possible.<\/p>\n<p style=\"text-align: justify;\">Now that you know more\u2026 would you like to test yourself anonymously? You can do so using the form we have prepared for you.<\/p>\n<p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=&#8221;1_2,1_2&#8243; _builder_version=&#8221;4.16&#8243; background_size=&#8221;initial&#8221; background_position=&#8221;top_left&#8221; background_repeat=&#8221;repeat&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_column type=&#8221;1_2&#8243; _builder_version=&#8221;4.16&#8243; custom_padding=&#8221;|||&#8221; global_colors_info=&#8221;{}&#8221; custom_padding__hover=&#8221;|||&#8221;][et_pb_image src=&#8221;https:\/\/hacto.umh.es\/files\/2024\/04\/2-1.png&#8221; _builder_version=&#8221;4.17.4&#8243; vertical_offset_tablet=&#8221;0&#8243; horizontal_offset_tablet=&#8221;0&#8243; z_index_tablet=&#8221;0&#8243; box_shadow_horizontal_tablet=&#8221;0px&#8221; box_shadow_vertical_tablet=&#8221;0px&#8221; box_shadow_blur_tablet=&#8221;40px&#8221; box_shadow_spread_tablet=&#8221;0px&#8221; global_colors_info=&#8221;{}&#8221;][\/et_pb_image][et_pb_button button_url=&#8221;https:\/\/drive.google.com\/uc?export=download&amp;id=1p_P0_1JdmJSLFjFPMhpFE7fPId0GWxrc&#8221; button_text=&#8221;Download&#8221; button_alignment=&#8221;center&#8221; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; hover_enabled=&#8221;0&#8243; global_colors_info=&#8221;{}&#8221; sticky_enabled=&#8221;0&#8243;][\/et_pb_button][\/et_pb_column][et_pb_column type=&#8221;1_2&#8243; _builder_version=&#8221;4.16&#8243; custom_padding=&#8221;|||&#8221; global_colors_info=&#8221;{}&#8221; custom_padding__hover=&#8221;|||&#8221;][et_pb_image src=&#8221;https:\/\/hacto.umh.es\/files\/2024\/04\/3.png&#8221; _builder_version=&#8221;4.17.4&#8243; vertical_offset_tablet=&#8221;0&#8243; horizontal_offset_tablet=&#8221;0&#8243; z_index_tablet=&#8221;0&#8243; box_shadow_horizontal_tablet=&#8221;0px&#8221; box_shadow_vertical_tablet=&#8221;0px&#8221; box_shadow_blur_tablet=&#8221;40px&#8221; box_shadow_spread_tablet=&#8221;0px&#8221; global_colors_info=&#8221;{}&#8221;][\/et_pb_image][et_pb_button button_url=&#8221;https:\/\/drive.google.com\/uc?export=download&amp;id=1CxvHxs8rp4_c3ZK5ONZ-0uxOsDqJ2svv&#8221; button_text=&#8221;Download&#8221; button_alignment=&#8221;center&#8221; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; hover_enabled=&#8221;0&#8243; global_colors_info=&#8221;{}&#8221; sticky_enabled=&#8221;0&#8243;][\/et_pb_button][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=&#8221;4.16&#8243; background_size=&#8221;initial&#8221; background_position=&#8221;top_left&#8221; background_repeat=&#8221;repeat&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_column type=&#8221;4_4&#8243; _builder_version=&#8221;4.16&#8243; custom_padding=&#8221;|||&#8221; global_colors_info=&#8221;{}&#8221; custom_padding__hover=&#8221;|||&#8221;][et_pb_text _builder_version=&#8221;4.17.4&#8243; vertical_offset_tablet=&#8221;0&#8243; horizontal_offset_tablet=&#8221;0&#8243; z_index_tablet=&#8221;0&#8243; text_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; text_text_shadow_vertical_length_tablet=&#8221;0px&#8221; text_text_shadow_blur_strength_tablet=&#8221;1px&#8221; link_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; link_text_shadow_vertical_length_tablet=&#8221;0px&#8221; link_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ul_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ul_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ul_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ol_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ol_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ol_text_shadow_blur_strength_tablet=&#8221;1px&#8221; quote_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; quote_text_shadow_vertical_length_tablet=&#8221;0px&#8221; quote_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_2_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_2_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_2_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_3_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_3_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_3_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_4_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_4_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_4_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_5_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_5_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_5_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_6_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_6_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_6_text_shadow_blur_strength_tablet=&#8221;1px&#8221; box_shadow_horizontal_tablet=&#8221;0px&#8221; box_shadow_vertical_tablet=&#8221;0px&#8221; box_shadow_blur_tablet=&#8221;40px&#8221; box_shadow_spread_tablet=&#8221;0px&#8221; global_colors_info=&#8221;{}&#8221;]<\/p>\n<p style=\"text-align: justify;\"><strong>References:<\/strong><\/p>\n<ol>\n<li style=\"text-align: justify;\">Rothman KJ, Greenland S. Modern epidemiology. 2nd. ed. Philadelphia: Lippincott-Raven Publishers; 1998.<\/li>\n<li style=\"text-align: justify;\">Gordis L. Epidemiolog\u00eda. 3\u00aa ed. Madrid. Elsevier; 2005.<\/li>\n<li style=\"text-align: justify;\">Bases metodol\u00f3gicas de la investigaci\u00f3n cl\u00ednica y epide\u00admiol\u00f3gica. En: Argim\u00f3n Pall\u00e1s JM, Jim\u00e9nez Villa J (eds.). M\u00e9\u00adtodos de investigaci\u00f3n cl\u00ednica y epidemiol\u00f3gica. Madrid: Elsevier; 2004. p. 8-15.<\/li>\n<li style=\"text-align: justify;\">Errores en epidemiolog\u00eda. Errores sistem\u00e1ticos. Factores de confusi\u00f3n y modificaci\u00f3n del efecto. Evid Pediatr. 2016; 12:16<\/li>\n<li style=\"text-align: justify;\">Hern\u00e1ndez-Avila M, Garrido F, Salazar-Mart\u00ednez E. Sesgos en estudios epidemiol\u00f3gicos. Salud p\u00fablica M\u00e9x. 2000;42(5).<\/li>\n<\/ol>\n<p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row column_structure=&#8221;1_2,1_2&#8243; _builder_version=&#8221;4.16&#8243; background_size=&#8221;initial&#8221; background_position=&#8221;top_left&#8221; background_repeat=&#8221;repeat&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_column type=&#8221;1_2&#8243; _builder_version=&#8221;4.16&#8243; custom_padding=&#8221;|||&#8221; global_colors_info=&#8221;{}&#8221; custom_padding__hover=&#8221;|||&#8221;][et_pb_text admin_label=&#8221;Texto&#8221; _builder_version=&#8221;4.17.4&#8243; vertical_offset_tablet=&#8221;0&#8243; horizontal_offset_tablet=&#8221;0&#8243; link_option_url=&#8221;https:\/\/www.linkedin.com\/in\/rocmusan\/&#8221; z_index_tablet=&#8221;0&#8243; text_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; text_text_shadow_vertical_length_tablet=&#8221;0px&#8221; text_text_shadow_blur_strength_tablet=&#8221;1px&#8221; link_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; link_text_shadow_vertical_length_tablet=&#8221;0px&#8221; link_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ul_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ul_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ul_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ol_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ol_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ol_text_shadow_blur_strength_tablet=&#8221;1px&#8221; quote_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; quote_text_shadow_vertical_length_tablet=&#8221;0px&#8221; quote_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_2_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_2_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_2_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_3_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_3_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_3_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_4_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_4_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_4_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_5_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_5_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_5_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_6_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_6_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_6_text_shadow_blur_strength_tablet=&#8221;1px&#8221; box_shadow_horizontal_tablet=&#8221;0px&#8221; box_shadow_vertical_tablet=&#8221;0px&#8221; box_shadow_blur_tablet=&#8221;40px&#8221; box_shadow_spread_tablet=&#8221;0px&#8221; global_module=&#8221;3733&#8243; saved_tabs=&#8221;all&#8221; global_colors_info=&#8221;{}&#8221;]<\/p>\n<div id=\"attachment_2469\" style=\"width: 210px\" class=\"wp-caption aligncenter\"><img aria-describedby=\"caption-attachment-2469\" loading=\"lazy\" class=\"wp-image-2469 size-medium aligncenter\" src=\"https:\/\/hacto.umh.es\/files\/2024\/04\/PFE1557-2-200x300.jpg\" alt=\"\" width=\"200\" height=\"300\" \/><p id=\"caption-attachment-2469\" class=\"wp-caption-text\"><strong>Roc\u00edo Mu\u00f1oz S\u00e1nchez<\/strong><br \/>Terapeuta Ocupacional, M\u00e1ster en Terapia Ocupacional en Neurolog\u00eda y M\u00e1ster en Salud P\u00fablica. Investigadora predoctoral en el programa de Doctorado en Salud P\u00fablica, Ciencias M\u00e9dicas y Quir\u00fargicas.<br \/>Colaboradora en InTeO.<\/p><\/div>\n<p>[\/et_pb_text][\/et_pb_column][et_pb_column type=&#8221;1_2&#8243; _builder_version=&#8221;4.16&#8243; custom_padding=&#8221;|||&#8221; global_colors_info=&#8221;{}&#8221; custom_padding__hover=&#8221;|||&#8221;][et_pb_text admin_label=&#8221;Texto&#8221; _builder_version=&#8221;4.17.4&#8243; vertical_offset_tablet=&#8221;0&#8243; horizontal_offset_tablet=&#8221;0&#8243; link_option_url=&#8221;https:\/\/www.linkedin.com\/in\/empar-casa%C3%B1a-escriche-4365b3237\/&#8221; link_option_url_new_window=&#8221;on&#8221; z_index_tablet=&#8221;0&#8243; text_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; text_text_shadow_vertical_length_tablet=&#8221;0px&#8221; text_text_shadow_blur_strength_tablet=&#8221;1px&#8221; link_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; link_text_shadow_vertical_length_tablet=&#8221;0px&#8221; link_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ul_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ul_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ul_text_shadow_blur_strength_tablet=&#8221;1px&#8221; ol_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; ol_text_shadow_vertical_length_tablet=&#8221;0px&#8221; ol_text_shadow_blur_strength_tablet=&#8221;1px&#8221; quote_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; quote_text_shadow_vertical_length_tablet=&#8221;0px&#8221; quote_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_2_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_2_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_2_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_3_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_3_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_3_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_4_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_4_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_4_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_5_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_5_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_5_text_shadow_blur_strength_tablet=&#8221;1px&#8221; header_6_text_shadow_horizontal_length_tablet=&#8221;0px&#8221; header_6_text_shadow_vertical_length_tablet=&#8221;0px&#8221; header_6_text_shadow_blur_strength_tablet=&#8221;1px&#8221; box_shadow_horizontal_tablet=&#8221;0px&#8221; box_shadow_vertical_tablet=&#8221;0px&#8221; box_shadow_blur_tablet=&#8221;40px&#8221; box_shadow_spread_tablet=&#8221;0px&#8221; global_module=&#8221;3739&#8243; saved_tabs=&#8221;all&#8221; global_colors_info=&#8221;{}&#8221;]<\/p>\n<div id=\"attachment_2472\" style=\"width: 210px\" class=\"wp-caption aligncenter\"><img aria-describedby=\"caption-attachment-2472\" loading=\"lazy\" class=\"wp-image-2472 size-medium\" src=\"https:\/\/hacto.umh.es\/files\/2024\/04\/PFE0179-200x300.jpg\" alt=\"\" width=\"200\" height=\"300\" \/><p id=\"caption-attachment-2472\" class=\"wp-caption-text\"><strong>Empar Casa\u00f1a Escriche<\/strong><br \/>Terapeuta Ocupacional, M\u00e1ster en Terapia Ocupacional en Neurolog\u00eda. Investigadora predoctoral FPU en el programa de Doctorado en Salud P\u00fablica, Ciencias M\u00e9dicas y Quir\u00fargicas. Contratada en InTeO.<\/p><\/div>\n<p>[\/et_pb_text][\/et_pb_column][\/et_pb_row][et_pb_row _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_column type=&#8221;4_4&#8243; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;][et_pb_text _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;]<\/p>\n<p>Casa\u00f1a Escriche, E., &amp; Mu\u00f1oz S\u00e1nchez, R (2024, abril 11).\u00a0<em>Types of errors in research studies.<\/em>\u00a0PublicaTO \u2013 Scientific Skills in Occupational Therapy by InTeO.<a href=\"https:\/\/hacto.umh.es\/2024\/04\/11\/tipos-de-errores-en-los-estudios-de-investigacion\/\">https:\/\/hacto.umh.es\/2024\/04\/11\/tipos-de-errores-en-los-estudios-de-investigacion\/<\/a><\/p>\n<p>[\/et_pb_text][et_pb_code admin_label=&#8221;C\u00f3digo&#8221; _builder_version=&#8221;4.17.4&#8243; _module_preset=&#8221;default&#8221; global_colors_info=&#8221;{}&#8221;]<!-- [et_pb_line_break_holder] --><\/p>\n<p>This work is licensed under a Creative Commons Licence.<!-- [et_pb_line_break_holder] --><!-- [et_pb_line_break_holder] --><a href=\"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/\" target=\"_blank\" rel=\"license noopener\"><!-- [et_pb_line_break_holder] --><!-- [et_pb_line_break_holder] --><img src=\"https:\/\/licensebuttons.net\/l\/by-nc-sa\/4.0\/88x31.png\" alt=\"Licencia Creative Commons\" \/><\/a><\/p>\n<p>[\/et_pb_code][\/et_pb_column][\/et_pb_row][\/et_pb_section]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>What determines whether a study is valid? The validity of a study depends on the extent to which the results obtained are accurate in answering the research question posed. There are two validity criteria: external validity refers to the study&#8217;s ability to generalise the results obtained from the study sample to the reference population, while [&hellip;]<\/p>\n","protected":false},"author":21252,"featured_media":5245,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_et_pb_use_builder":"on","_et_pb_old_content":"<p>\u00bfDe qu\u00e9 depende que un estudio sea v\u00e1lido? La validez de un estudio va a depender del grado en el que los resultados obtenidos son correctos para responder la pregunta de investigaci\u00f3n que nos hemos planteado. Existen dos criterios de validez, en primer lugar, la <u>validez externa<\/u> hace referencia a la capacidad del estudio para generalizar los resultados obtenidos en la muestra de estudio a la poblaci\u00f3n de referencia, mientras que la <u>validez interna<\/u> hace referencia a los errores cometidos durante el proceso de investigaci\u00f3n. Teniendo en cuenta esto, hay dos tipos de errores que pueden afectar a la validez del estudio:<\/p><ul><li><strong>Error aleatorio:<\/strong> se debe al azar, por lo que este tipo de error no se puede evitar, pero si reducir. Este error puede deberse a la variabilidad biol\u00f3gica entre personas. En este caso, el error se reducir\u00eda aumentando la muestra o escogiendo instrumentos de medici\u00f3n m\u00e1s precisos y, en su defecto, tomando la medida en varias ocasiones.<\/li><li><strong>Error sistem\u00e1tico o sesgo<\/strong>: se produce en el dise\u00f1o o en el an\u00e1lisis de los datos del estudio planteado, es un error predecible y, por lo tanto, debemos evitarlo. Los sesgos m\u00e1s conocidos en este sentido son el sesgo de selecci\u00f3n, el sesgo de informaci\u00f3n o el sesgo de confusi\u00f3n, aunque hay muchos m\u00e1s.<\/li><\/ul><p><a href=\"https:\/\/hacto.umh.es\/files\/2024\/04\/1.png\"><img class=\"aligncenter wp-image-2454 size-large\" src=\"https:\/\/hacto.umh.es\/files\/2024\/04\/1-724x1024.png\" alt=\"\" width=\"724\" height=\"1024\" \/><\/a><\/p><p><strong><u>Tipos de sesgos:<\/u><\/strong><\/p><ol><li><strong>Sesgo de selecci\u00f3n<\/strong><\/li><\/ol><p>Es un tipo de error sistem\u00e1tico que se produce cuando se seleccionan los participantes del estudio de forma incorrecta. La muestra obtenida no es representativa de la poblaci\u00f3n por un error en los criterios de inclusi\u00f3n y exclusi\u00f3n o por la manera de realizar el reclutamiento. \u00a0A continuaci\u00f3n, resumimos los m\u00e1s importantes:<\/p><table><tbody><tr><td width=\"189\"><strong>Motivo<\/strong><\/td><td width=\"217\"><strong>Definici\u00f3n<\/strong><\/td><td width=\"160\"><strong>Tipo de estudio donde es frecuente<\/strong><\/td><\/tr><tr><td width=\"189\"><strong>Selecci\u00f3n incorrecta de los grupos de estudio<\/strong><\/td><td width=\"217\">Los grupos comparados presentan m\u00e1s diferencias a parte del factor evaluado.<\/td><td width=\"160\">Cohortes, casos y controles y ensayos cl\u00ednicos<\/td><\/tr><tr><td width=\"189\"><strong>P\u00e9rdidas durante el seguimiento de los participantes<\/strong><\/td><td width=\"217\">Se pierden sujetos, pero no de forma aleatoria.<\/td><td width=\"160\">Cohortes, ensayos cl\u00ednicos<\/td><\/tr><tr><td width=\"189\"><strong>Ausencia de respuesta<\/strong><\/td><td width=\"217\">Cuando se recoge informaci\u00f3n mediante entrevistas, es habitual que los encuestados no respondan a todas las preguntas.<\/td><td width=\"160\">Estudios transversales, cohortes, casos y controles y ensayos cl\u00ednicos.<\/td><\/tr><tr><td width=\"189\"><strong>Supervivencia selectiva<\/strong><\/td><td width=\"217\">Es habitual cuando se seleccionan personas que tienen previamente la enfermedad en vez de personas que inician la enfermedad.<\/td><td width=\"160\">Casos y controles<\/td><\/tr><tr><td width=\"189\"><strong>Sesgo de autoselecci\u00f3n o participaci\u00f3n de voluntarios<\/strong><\/td><td width=\"217\">Puede ser que las personas voluntarias no cumplan los mismos criterios o tengan caracter\u00edsticas diferentes.<\/td><td width=\"160\">Transversales, estudios de cohortes y ensayos cl\u00ednicos.<\/td><\/tr><\/tbody><\/table><p>Imagina un estudio en terapia ocupacional que investiga la efectividad de un programa de rehabilitaci\u00f3n para pacientes con da\u00f1o cerebral adquirido. El objetivo es comparar la evoluci\u00f3n funcional entre dos grupos: uno que sigue el programa de rehabilitaci\u00f3n y otro que sigue con su rutina habitual.<\/p><p>Un ejemplo de sesgo de selecci\u00f3n ser\u00eda si en este estudio no se ha realizado asignaci\u00f3n aleatoria al grupo intervenci\u00f3n (rehabilitaci\u00f3n) o control (rutina habitual) y resulta que la personas que van al grupo del programa de rehabilitaci\u00f3n tienen un mayor grado de secuelas que los que siguieron con su rutina habitual y el 60% de los que est\u00e1n en ese grupo abandonan el estudio antes de finalizar mientras que en el otro grupo todos finalizan el estudio.<\/p><p>Otro ejemplo de sesgo de selecci\u00f3n ser\u00eda que a pesar de que se ha realizado una asignaci\u00f3n aleatoria, el grupo control como no est\u00e1 recibiendo rehabilitaci\u00f3n, decide no ir a la evaluaci\u00f3n final del estudio y por lo tanto debemos considerarlo un abandono.<\/p><p>Formas de prevenir sesgo de selecci\u00f3n en este caso:<\/p><ul><li>Realizar una aleatorizaci\u00f3n de los participantes del estudio.<\/li><li>Tener un tama\u00f1o muestral adecuado para que la aleatorizaci\u00f3n funcione correctamente (la importancia de calcular el tama\u00f1o muestral).<\/li><li>Inclusi\u00f3n de criterios de inclusi\u00f3n y exclusi\u00f3n.<\/li><li>Minimizaci\u00f3n de las p\u00e9rdidas de seguimiento implementando estrategias para la retenci\u00f3n de participantes.<\/li><li>Antes de la asignaci\u00f3n, informar detalladamente del estudio a los participantes, indic\u00e1ndoles los problemas que pueden surgir si se abandona el estudio para que puedan tomar una decisi\u00f3n m\u00e1s consciente de su participaci\u00f3n en el mismo.<\/li><li>Antes de la asignaci\u00f3n, informar que los participantes que vayan al grupo control recibir\u00e1n el programa de rehabilitaci\u00f3n tras la finalizaci\u00f3n del estudio.<\/li><li>Intentar recoger la informaci\u00f3n final de todas las personas participantes, aunque no hayan asistido a todas las sesiones.<\/li><li>Realizar an\u00e1lisis por intenci\u00f3n a tratar, es decir, analizar los datos teniendo en cuenta el grupo que se les asign\u00f3 al inicio del estudio, incluyendo a todos los participantes independientemente si abandonaron o no el estudio.<\/li><li>Hacer an\u00e1lisis de sensibilidad estratificando por n\u00famero de sesiones u otros marcadores de adherencia al tratamiento.<\/li><li>Considerar posibles factores de confusi\u00f3n (ver m\u00e1s abajo).<\/li><\/ul><p>\u00a0<\/p><ol start=\"2\"><li><strong>Sesgo de informaci\u00f3n<\/strong><\/li><\/ol><p>Es un tipo de error sistem\u00e1tico que se produce al recoger la informaci\u00f3n de los participantes y que puede llevar a una clasificaci\u00f3n err\u00f3nea respecto a la exposici\u00f3n y\/o enfermedad. Puede ser <u>no diferencial<\/u>, es decir, cuando se produce por igual en todos los participantes del estudio (expuestos y no expuestos\/ enfermos y no enfermos) o <u>diferencial,<\/u> cuando solo se produce en un subgrupo de participantes (solo en los enfermos\/solo en los no expuestos). Este tipo de sesgo se puede producir por ejemplo por usar instrumentos de medida con poca sensibilidad o especificidad, utilizar criterios diagn\u00f3sticos incorrectos o por la imprecisi\u00f3n en la recogida de datos.<\/p><p>Un ejemplo de este tipo de sesgo en Terapia Ocupacional, se podr\u00eda cometer cuando se utiliza una herramienta de evaluaci\u00f3n de la que no se ha comprobado sus propiedades psicom\u00e9tricas o que se ha comprobado sus propiedades psicom\u00e9tricas, pero no en la poblaci\u00f3n en la queremos utilizar.<\/p><p>Formas de prevenirlo:<\/p><ul><li>Utilizar instrumentos de evaluaci\u00f3n que cuenten con una evaluaci\u00f3n de las propiedades psicom\u00e9tricas.<\/li><li>Utilizar instrumentos de evaluaci\u00f3n que sean v\u00e1lidos y fiables para la poblaci\u00f3n en la que la vamos a usar.<\/li><li>Utilizar instrumentos que permitan discriminar entre personas con y sin la patolog\u00eda.<\/li><li>Entrenamiento del personal que va a administrar las herramientas.<\/li><li>Ser fiel a las instrucciones para la administraci\u00f3n de la herramienta.<\/li><\/ul><p>Imagina un estudio que eval\u00faa la efectividad de un programa de intervenci\u00f3n en la mejora de la funci\u00f3n motora en pacientes que han sido operados tras una rizartrosis. Durante el estudio, se utilizan cuestionarios autoadministrados para recopilar informaci\u00f3n sobre el nivel de dolor de las personas al realizar la actividad de cocinado. Como el cuestionario es autoadministrado, podr\u00eda ocurrir un posible sesgo de informaci\u00f3n por diversas razones: que haya participantes que infraestimen o sobrestimen el dolor, por falta de comprensi\u00f3n de las preguntas, por la influencia de factores emocionales en las respuestas o porque la actividad de cocinar no fuera una actividad con significado para la persona.<\/p><p>Formas de prevenirlo:<\/p><ul><li>Asegurarme que las preguntas son claras para distintos tipos de personas (diferente nivel educativo, edad, cultural etc).<\/li><li>Que las herramientas que utilizo hayan sido testadas en cuanto a la validez y la fiabilidad para este colectivo (para saber m\u00e1s <a href=\"https:\/\/hacto.umh.es\/2023\/03\/23\/herramientas-de-evaluacion-en-terapia-ocupacional-clinica-e-investigacion\/\">https:\/\/hacto.umh.es\/2023\/03\/23\/herramientas-de-evaluacion-en-terapia-ocupacional-clinica-e-investigacion\/<\/a>)<\/li><li>Entrenar a las personas que vayan a explicar la herramienta y seguir fielmente las instrucciones que nos dieron sus creadores.<\/li><li>Garantizar la confidencialidad y el anonimato de las personas que responden al cuestionario.<\/li><li>Recoger otras variables que puedan ayudarnos a entender las respuestas de las personas.<\/li><\/ul><p>\u00a0<\/p><ol start=\"3\"><li><strong>Sesgo de confusi\u00f3n<\/strong><\/li><\/ol><p>Es un tipo de error sistem\u00e1tico que se produce cuando se observa una asociaci\u00f3n entre dos variables sin tener en cuenta la influencia de una tercera variable a la que se denomina variable de confusi\u00f3n. Esta tercera variable tiene que estar asociada con las dos variables (variable exposici\u00f3n y variable respuesta) de forma independiente y no estar en el camino causal entre las dos variables, es decir, para que ocurra una de ellas no tiene que haber ocurrido previamente la otra.<\/p><p>Un ejemplo en Terapia Ocupacional podr\u00eda ser, que al realizar un estudio para conocer c\u00f3mo impacta el consumo de coca\u00edna en el desempe\u00f1o ocupacional de las personas, no se recojan preguntas sobre la exposici\u00f3n a otras sustancias (ej.: alcohol). Sabemos que el consumo de alcohol es un factor de riesgo tanto para el desempe\u00f1o ocupacional como para el consumo de la coca\u00edna, y si en el an\u00e1lisis de los datos no tenemos en cuenta esta variable, podr\u00eda estar confundiendo nuestros resultados.<\/p><p>Formas de prevenirlo, mejor dicho, de controlarlo.<\/p><ul><li>Identificar y recoger todas las potenciales variables de confusi\u00f3n del estudio, y para ello, ser\u00e1 importante conocer la evidencia previa en el tema de estudio.<\/li><li>Realizar modelos de an\u00e1lisis estad\u00edsticos que permitan ajustar por las variables de confusi\u00f3n identificadas.<\/li><li>Realizar an\u00e1lisis estratificados para examinar la asociaci\u00f3n entre la variable de exposici\u00f3n y la variable de respuesta dentro de diferentes niveles de las variables de confusi\u00f3n.<\/li><li>Realizar an\u00e1lisis de sensibilidad para evaluar el impacto de las variables de confusi\u00f3n en los resultados del estudio.<\/li><\/ul><p><strong>A continuaci\u00f3n, se muestran en la siguiente tabla un resumen de los diferentes tipos de errores y sesgos, as\u00ed como las posibles consecuencias y medidas de control:<\/strong><\/p><table width=\"576\"><tbody><tr><td rowspan=\"2\" width=\"111\"><strong>Tipo de error<\/strong><\/td><td rowspan=\"2\" width=\"153\"><strong>Consecuencia<\/strong><\/td><td colspan=\"2\" width=\"312\"><strong>Control<\/strong><\/td><\/tr><tr><td width=\"198\"><strong>Dise\u00f1o<\/strong><\/td><td width=\"113\"><strong>An\u00e1lisis<\/strong><\/td><\/tr><tr><td colspan=\"4\" width=\"576\"><strong>Error aleatorio<\/strong><\/td><\/tr><tr><td width=\"111\">\u00a0<\/td><td width=\"153\">Afecta a la validez externa.<\/td><td width=\"198\">Aumento muestra o precisi\u00f3n de las medidas.<\/td><td width=\"113\">\u00a0<\/td><\/tr><tr><td colspan=\"4\" width=\"576\"><strong>Error sistem\u00e1tico o sesgo<\/strong><\/td><\/tr><tr><td width=\"111\"><strong>Selecci\u00f3n<\/strong><\/td><td width=\"153\">Afecta a la validez interna.<\/td><td width=\"198\">En los ensayos cl\u00ednicos se puede aleatorizar. En los estudios observacionales hay que establecer unos criterios de selecci\u00f3n estrictos.<\/td><td width=\"113\">\u00a0<\/td><\/tr><tr><td width=\"111\"><strong>Clasificaci\u00f3n<\/strong><\/td><td width=\"153\">Afecta a la validez interna.<\/td><td width=\"198\">Establecer una persona para diagnosticar a todos los participantes y evitar que los conozca. Utilizar herramientas de evaluaci\u00f3n v\u00e1lidas y confiables.<\/td><td width=\"113\">\u00a0<\/td><\/tr><tr><td width=\"111\"><strong>Confusi\u00f3n<\/strong><\/td><td width=\"153\">Afecta a la validez interna.<\/td><td width=\"198\">\u00a0<\/td><td width=\"113\">An\u00e1lisis estratificados y ajustados<\/td><\/tr><\/tbody><\/table><p>\u00a0<\/p><p>Puesto que es muy dif\u00edcil reducir todos los sesgos, es importante declararlos en el apartado de limitaciones del art\u00edculo, as\u00ed como tenerlos en cuenta cuando leemos otras publicaciones. Cabe destacar que la presencia de estos sesgos afectar\u00e1 a la validez del estudio, por lo que resulta indispensable plantear un dise\u00f1o y an\u00e1lisis adecuado con el fin de minimizarlos al m\u00e1ximo.<\/p><p>Y ahora que sabes m\u00e1s\u2026 \u00bfte gustar\u00eda ponerte a prueba de manera totalmente an\u00f3nima? Puedes hacerlo en este formulario que hemos preparado para ti. https:\/\/forms.gle\/acvU45WhbSwAuSPs5\u00a0<\/p><p>\u00a0<\/p>","_et_gb_content_width":"","_links_to":"","_links_to_target":""},"categories":[332145],"tags":[],"_links":{"self":[{"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/posts\/6131"}],"collection":[{"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/users\/21252"}],"replies":[{"embeddable":true,"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/comments?post=6131"}],"version-history":[{"count":0,"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/posts\/6131\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/media\/5245"}],"wp:attachment":[{"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/media?parent=6131"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/categories?post=6131"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hacto.umh.es\/en\/wp-json\/wp\/v2\/tags?post=6131"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}