Ch19,20,21 Flashcards
“At least ___ types of populations must be considered when preparing to collect data ” What are they?
“At least four types of populations must be considered when preparing to collect data ”
-Target population
-Source population
-Sample population
-Study population
“The broadest group is the ____ population, the broad population to which the results of a study should be applicable.”
target population: (the general population that the study seeks to understand )
“The ____ population, sometimes called a sampling frame, is a well-defined ____ of individuals from the target population from which potential study participants will be sampled.”
“The source population, sometimes called a sampling frame, is a well-defined subset of individuals from the target population from which potential study participants will be sampled.”
“The ___ population consists of the individuals from a source population who are ____ to participate in the research project. When a ____ population is ____, everyone might be ______ to participate. When a source population is very large, only a small ____ of _____ might be ______ for a study.”
“The sample population consists of the individuals from a source population who are invited to participate in the research project. When a source population is small, everyone might be invited to participate. When a source population is very large, only a small subset of members might be recruited for a study.”
“The _____ population comprises the eligible members of the sample population who _____ to participate in the study and complete ______ study activities.”
“The study population comprises the eligible members of the sample population who consent to participate in the study and complete required study activities.”
“19.3 Sample Populations
When the _____ _______ is small, every person who is listed as a member of the _____ population can be asked to participate in the study. When that approach is used, the ____ population is the same as the ______ population. However, a source population is often much ___than the sample size required for a study. When the source population is large, a subset of the source population may serve as a sample population.”
“19.3 Sample Populations
When the source population is small, every person who is listed as a member of the source population can be asked to participate in the study. When that approach is used, the source population is the same as the sample population. However, a source population is often much larger than the sample size required for a study. When the source population is large, a subset of the source population may serve as a sample population.”
summary: when source pop is small, can be used as the sample pop…when source pop is larger than the sample pop, the sample is a subset of the source pop.
“Bias is a ________ problem in the ___, ____, or ____ of a study that can cause the results of the study to be erroneous. Many types of bias are related to the sampling process used for a study. ”
“Bias is a systematic problem in the design, conduct, or analysis of a study that can cause the results of the study to be erroneous. Many types of bias are related to the sampling process used for a study. ”
“Many types of bias are related to the ____ process used for a study.”
“Many types of bias are related to the sampling process used for a study.”
“ ______bias (or ascertainment bias) occurs when the individuals sampled for a study systematically are not representative of the source population as a whole. ”
“ Sampling bias (or ascertainment bias) occurs when the individuals sampled for a study systematically are not representative of the source population as a whole. ”
“ _____ bias occurs when each individual in the source population does not have an equal chance of being selected for the sample population.”
“ Nonrandom-sampling bias occurs when each individual in the source population does not have an equal chance of being selected for the sample population.”
“A variety of _____-______ sampling methods can be used to ensure that all members of a source population have an equal likelihood of being invited to participate in a research study. Examples of some of these types of probability-based samples are shown in Figure 19-2:
-simple random sampling…..
-systematic sampling…..
-stratified sampling….
- cluster sampling….
“A variety of probability-based sampling methods can be used to ensure that all members of a source population have an equal likelihood of being invited to participate in a research study. Examples of some of these types of probability-based samples are shown in Figure 19-2:
-simple random sampling:
each person has an equal chance of being selected
-systematic sampling:
after random start point, every nth person is selected
-stratified sampling:
simple random sampling is selected from each of several strata
-cluster sampling:
area is divided into geographic clusters and some clusters are selected for inclusion
“Probability-based sampling is usually the preferred option for producing a sample population that is ____ to the source population as a whole. ”
“Probability-based sampling is usually the preferred option for producing a sample population that is similar to the source population as a whole. ”
-if they are not similar then this would represent non-random sampling (where sample pop doesn’t adequately represent the source population as a whole)
“If a list of every individual in the ____population is available, a computer program can select at random the individuals who will be invited to participate. ”
What type of sampling does this represent?
“If a list of every individual in the source population is available, a computer program can select at random the individuals who will be invited to participate. ”
-(simple random sampling)
“If participants are being sampled from the ____ ____ of a national professional organization, every 10th person could be contacted.”
What type of sampling does this represent?
“If participants are being sampled from the membership list of a national professional organization, every 10th person could be contacted.”
-(systemic sampling) note: no order, random start
“If 12 colleges are participating in a health behavior study, the ___ percentage of students from each school could be randomly sampled for the study.”
“If 12 colleges are participating in a health behavior study, the same percentage of students from each school could be randomly sampled for the study.”
“If a cross-sectional study will draw participants from a large geographic area, ____ sampling might be used. ”
“If a cross-sectional study will draw participants from a large geographic area, cluster sampling might be used. ”
“Whole city blocks could be randomly sampled for inclusion in the sample population, and ___of people who live on those blocks could be asked to participate.”
“Whole city blocks could be randomly sampled for inclusion in the sample population, and 100% of people who live on those blocks could be asked to participate.”
“Alternatively, the sample population might consist of all residents in the city who live on every 7th street that runs north to south, starting with a randomly sampled street.”
this represents systemic sampling
“Sometimes a nonprobability-based sample is appropriate. A ______ population is a nonprobability-based source population selected due to ____of access to those individuals, schools, workplaces, organizations, or communities. ”
“Sometimes a nonprobability-based sample is appropriate. A convenience population is a nonprobability-based source population selected due to ease of access to those individuals, schools, workplaces, organizations, or communities. ”
“Convenience sampling must always be used with _____, since convenient sample populations are often systematically _____ from the target and source populations they are intended to _____. Even if a probability-based sample is drawn from a convenience source population, the sample is unlikely to be representative of the target population as a whole. ”
“Convenience sampling must always be used with caution, since convenient sample populations are often systematically different from the target and source populations they are intended to represent. Even if a probability-based sample is drawn from a convenience source population, the sample is unlikely to be representative of the target population as a whole. ”
For example, samples “based on a patient population or an occupational population are _____ to represent health status in the cities and towns where those individuals reside.”
“based on a patient population or an occupational population are unlikely to represent health status in the cities and towns where those individuals reside.”
“No matter which sampling method is used, the goal is to end up with a ______ population that is representative of the ______population and, ideally, of the ____ population, too.”
“No matter which sampling method is used, the goal is to end up with a sample population that is representative of the source population and, ideally, of the target population, too.”
“Being aware of common types of bias enables a researcher to make informed decisions about source populations. For example, ______bias can occur when cases and controls for a study are recruited from hospitals and therefore are more likely than the general population to have comorbid conditions. ”
“Being aware of common types of bias enables a researcher to make informed decisions about source populations. For example, Berkson’s bias can occur when cases and controls for a study are recruited from hospitals and therefore are more likely than the general population to have comorbid conditions. ”
“ _____ ______ bias can occur when participants are recruited from occupational populations and therefore are systematically healthier than the general population. ”
“ Healthy worker bias can occur when participants are recruited from occupational populations and therefore are systematically healthier than the general population. ”
“____ ____ occurs when different eligibility criteria are applied to cases and controls, such as when controls with health conditions related to an exposure are excluded but cases with those comorbidities are not excluded.”
“Exclusion bias occurs when different eligibility criteria are applied to cases and controls, such as when controls with health conditions related to an exposure are excluded but cases with those comorbidities are not excluded.”
-For example, if patients died from toxic effects of an experimental treatment and were subsequently excluded from the trial analysis, perhaps as ‘early deaths’, the estimate of effect would be biased in favour of that experimental treatment.
These study design “may result in ____ bias if the members of a sample population who agree to participate in a study are systematically different from nonparticipants.
“may result in nonresponse bias if the members of a sample population who agree to participate in a study are systematically different from nonparticipants.
However, a less than 100% participation rate is usually not a problem as long as the researcher:”
“Uses acceptable and carefully explained sampling methods
Takes appropriate steps to maximize the participation rate
Recruits an adequately large sample size
Reports the number of potential participants at each stage
Even so, researchers should develop a recruiting strategy that will encourage a high rate of participation.”
“19.5 Populations for Cross-Sectional Studies”
“19.5 Populations for Cross-Sectional Studies”
“The results of cross-sectional studies(observational study design..the investigator measures the outcome and the exposures in the study participants at the same time.)
are often used to make important ______ and ____ _____, so the study population for a cross-sectional study should adequately represent the _____ population.”
“The results of cross-sectional studies are often used to make important resource and policy decisions, so the study population for a cross-sectional study should adequately represent the target population.”
“A ______-_______ study uses a random sampling method to generate a sample population that is representative of a well-defined larger population. The strongest cross-sectional surveys are population-based studies that use probability-based sampling rather than a convenience population. The goal is to select a source population that is reasonably representative of the target population and then to sample and recruit a set of study participants who are reasonably representative of the source population.”
“A population-based study
“The most rigorous population-based studies use probability-based sampling methods to generate sample populations and then confirm that study populations are reasonably representative of the _____ populations from which they were drawn. ”
source
“A ___ is a complete enumeration of a population, such as a count of every resident of a country, the number of inpatients at a particular hospital at noon on a selected day, or the number of employees of a large company.”
census
- count
“When a census of the source or _____population has been recently conducted, the ___ and ____ populations for a cross-sectional study should reflect the demographics of that census.”
“When a census of the source or target population has been recently conducted, the sample and study populations for a cross-sectional study should reflect the demographics of that census.”
“For example, suppose the goal of a study is to quantify the prevalence of tobacco use among high school students in a county. The county’s 14 high schools together serve as the ______ population and the source population. Selecting only 1 high school as the sample population is probably not sufficient. Working intensely with 1 school might ______ participation rates. However, the selected school might enroll students who are different from county students as a whole—more rural or urban, more or less diverse, or from more or less wealthy households. In such a situation, the results from that one high school would not be an accurate reflection of adolescent health across the county.”
“For example, suppose the goal of a study is to quantify the prevalence of tobacco use among high school students in a county. The county’s 14 high schools together serve as the target population and the source population. Selecting only 1 high school as the sample population is probably not sufficient. Working intensely with 1 school might maximize participation rates. However, the selected school might enroll students who are different from county students as a whole—more rural or urban, more or less diverse, or from more or less wealthy households. In such a situation, the results from that one high school would not be an accurate reflection of adolescent health across the county.”
“A better option is to sample some students from each of the 14 schools. For example, 20% of the classes in each high school that meet during the first period of the school day could be randomly sampled, and 100% of the students in those sampled classes could be invited to participate (Figure 19-3). After the data are collected, the researcher can validate the representativeness of the study by confirming that the proportion of students by grade, age, and sex in the study population is similar to the distribution of these characteristics among the county’s total high school student population.”
ok
“FIGURE 19-3 Population Example for a Cross-Sectional Study”
Target population: High school students in north county
Source population: All high school students in north county
Sample population: all students in 20% of homerooms in all high school students in north county
1.Study approach
2.Study question
3.Data collection method
4.Target population
5.Source population
6.Source population list
7.Sample population
8.Study population
9.Confidentiality
1.Study approach
Cross-sectional study(observational study design..the investigator measures the outcome and the exposures in the study participants at the same time.)
2. Study question
-“What proportion of high school students in North County smoke cigarettes?”
3. Data collection method
-Participants will complete their own paper-based questionnaires.
4. Target population
-“Students in grades 9–12 in North County”
5. Source population
-“All students enrolled in any of the 14 high schools in North County”
6. Source population list
-“A list of the number of students in each homeroom provided by each high school”
7.Sample population:
-“Based on estimated sample size requirements, 20% of homerooms will be randomly sampled from the lists provided, and all students in these sampled homerooms will be asked to participate in the study.”
8. Study population:
-“Eligible individuals from the sample population who agree to participate”
9. Confidentiality
-“No student names will ever be provided to researchers; surveys will be anonymous.”
“When census data are __ _____ for a ____or target population, careful planning can help a researcher recruit a study population that is reasonably representative of the target population. Recruiting participants for a general population survey from among the spectators at a football game, the shoppers in a particular grocery store, or the donors at a volunteer blood drive will likely result in a _____ population that does not represent the target population. Convenience populations are not suitable for most cross-sectional studies because they are not population-based.”
“When census data are not available for a source or target population, careful planning can help a researcher recruit a study population that is reasonably representative of the target population. Recruiting participants for a general population survey from among the spectators at a football game, the shoppers in a particular grocery store, or the donors at a volunteer blood drive will likely result in a sample population that does not represent the target population. Convenience populations are not suitable for most cross-sectional studies because they are not population-based.”
19.6 “Populations for Case–Control Studies”
yes
“When identifying possible participants for a case–control study, the first step is to find ….
an appropriate and available source of cases.
“All cases must have the ___ disease, disability, or other health-related condition.”
same
“The study’s case definition should be very clear about the ______that must be ____ and _____ for an individual to be categorized as a case. For example, a researcher may want to select only candidates with advanced disease or, alternatively, may prefer to study only cases whose symptoms began recently. The case definition should specify both the inclusion and the exclusion criteria. The case and control definitions for a study can be written to exclude borderline cases from serving as either cases or controls.”
“The study’s case definition should be very clear about the characteristics that must be present and absent for an individual to be categorized as a case. For example, a researcher may want to select only candidates with advanced disease or, alternatively, may prefer to study only cases whose symptoms began recently. The case definition should specify both the inclusion and the exclusion criteria. The case and control definitions for a study can be written to exclude borderline cases from serving as either cases or controls.”
“Hospitals, specialty clinics, public health offices, disease support groups, and advocacy organizations may be helpful resources for locating individuals or groups of individuals who are likely to meet the study’s case definition. However, care must be taken to ensure that the ____population is not healthier, sicker, or more or less socially connected than the typical person who meets the case definition. ”
“Hospitals, specialty clinics, public health offices, disease support groups, and advocacy organizations may be helpful resources for locating individuals or groups of individuals who are likely to meet the study’s case definition. However, care must be taken to ensure that the sample population is not healthier, sicker, or more or less socially connected than the typical person who meets the case definition. ”
“Another option may be to conduct a _____ ___-___ study that uses the participants of a large longitudinal cohort study as the source population for both cases and controls. A _____ design minimizes ___ bias because data about past exposures were collected at the time of the exposure and are not based on participants’ ______. However, a cohort study will yield a sufficient number of cases only when the disease being studied is relatively ____.”
“Another option may be to conduct a nested case–control study that uses the participants of a large longitudinal cohort study as the source population for both cases and controls. A nested case–control study design minimizes recall bias because data about past exposures were collected at the time of the exposure and are not based on participants’ memories. However, a cohort study will yield a sufficient number of cases only when the disease being studied is relatively common.”
“Once a source of cases is identified, a valid ____ group must be selected. The _____ must be ____ to the cases in every way except for their _____ status.
-For example, it would be inappropriate to compare cases with heart disease to controls who are marathon runners. A study examining a chronic disease should choose a control population representative of the general public, not a population that is unusually physically active. Similarly, it would be inappropriate to compare older adult women to teenage boys, or to compare big-city businessmen to men who are subsistence farmers in remote areas. All cases and controls for any one study should come from ___ sociodemographic and geographic source populations.”
“Once a source of cases is identified, a valid control group must be selected. The controls must be similar to the cases in every way except for their disease status. For example, it would be inappropriate to compare cases with heart disease to controls who are marathon runners. A study examining a chronic disease should choose a control population representative of the general public, not a population that is unusually physically active. Similarly, it would be inappropriate to compare older adult women to teenage boys, or to compare big-city businessmen to men who are subsistence farmers in remote areas. All cases and controls for any one study should come from similar sociodemographic and geographic source populations.”
“Many _____ types of populations may be suitable sources of controls for a case–control study. For some hospital-based studies, it may be appropriate to use as controls individuals hospitalized with a condition other than the one being studied. For some population-based studies, random-digit telephone dialing may yield a representative population—or, because many people will refuse to answer personal questions over the telephone, this strategy may result in a very unrepresentative population. In some situations, friends or family members of the cases may be the best controls because they are likely to have sociodemographic characteristics similar to the cases. When making this important decision, the researcher should consider the possibilities for matching cases to controls using group or individual matching.”
“Many different types of populations may be suitable sources of controls for a case–control study. For some hospital-based studies, it may be appropriate to use as controls individuals hospitalized with a condition other than the one being studied. For some population-based studies, random-digit telephone dialing may yield a representative population—or, because many people will refuse to answer personal questions over the telephone, this strategy may result in a very unrepresentative population. In some situations, friends or family members of the cases may be the best controls because they are likely to have sociodemographic characteristics similar to the cases. When making this important decision, the researcher should consider the possibilities for matching cases to controls using group or individual matching.”
“The eligibility criteria for a study comprise the inclusion criteria that must be present for an individual (or, for a systematic review, a research manuscript) to be allowed to participate in a study and the exclusion criteria that require an individual (or manuscript) to be removed from the study population. All cases and all controls in a case–control study must meet the same eligibility criteria, except for the ones relating to disease status. For example, a study targeting septuagenarian women should require both cases and controls to be women in their 70s who live in the same general area”
“to participate in a study and the exclusion criteria that require an individual (or manuscript) to be removed from the study population. All cases and all controls in a case–control study must meet the same eligibility criteria, except for the ones relating to disease status. For example, a study targeting septuagenarian women should require both cases and controls to be women in their 70s who live in the same general area”
Excerpt From: Jacobsen, Kathryn H.;. “Introduction to Health Research Methods.” Apple Books.
“FIGURE 19-4 Population Example for a Case–Control Study”
Target population: American women ages 70-79
Source population: All women ages 70-79 years admitted to St lukes hospital system in central city with an incident hip fracture in the past 12 months (cases) and their friends (control)
Sample population:All women ages 70-79 years admitted to St lukes hospital system in central city with an incident hip fracture in the past 12 months (cases) and 3 friends per case (control)
1. Study approach
2. Study question
3. Data collection method
4. Target Population
5. Source population (cases)
6. Source populations list
7. Sample populations (cases)
8. Source population (controls)
9. Sample population (controls)
10. Study population
11. Confidentiality
- Study approach
Case–control study - Study question
“What are the risk factors for hip fractures in adult women in the United States?” - Data collection method
participants will be interviewed in person or by telephone - Target Population
“Women ages 70–79 years living in the United States” - Source population (cases)
“All women ages 70–79 who were admitted to St. Luke’s Hospital System in Center City with an incident (new) hip fracture in the past 12 months” - Source populations list
“A list of the hospital registration numbers for each inpatient female ages 70–79 at admission whose electronic medical record indicates a diagnosis of a hip fracture (ICD10 code S72) during the eligible 12-month period” - Sample populations (cases)
“All members of the source population for cases will be asked to participate in the study.” - Source population (controls)
“Each case will be asked to provide the names of three female friends in the same age range who live in the same county and might be able to serve as controls.” - Sample population (controls)
“All of the friends listed by cases in the study will be invited to serve as controls.” - Study population
“Eligible individuals from the sample populations who agree to participate” - Confidentiality
“The hospital will provide the researcher with the names, addresses, and phone numbers of potential case participants. Personally identifying information will not be included in the electronic file that contains questionnaire responses.”
“19.7 Populations for Cohort Studies”