316 test #2
4 types of nonprobability sampling
Convenience Snowball [network] Quota Purposive [Can quiet pickles sleep?]
Five hospitals were randomly selected from all hospitals in Baltimore City and county. From each of the five hospitals, five units were randomly selected. All staff nurses were interviewed on the 25 units. simple random stratified random systematic random cluster convenience quota
cluster
A sampling strategy that proceeds through a set of stages from larger to smaller sampling units [e.g. from states, to zip codes, to households].
cluster [multistage] sampling
A way to promote internal validity is to ensure ..... of conditions.
constancy
subjects [things, etc.] in an experimental study who do not receive the experimental intervention and whose performance provides a counterfactual against which the effects of interventions can be measured
control
Mothers bringing their children to the diabetic clinic on Mondays were invited to participate in the study. simple random stratified random systematic random cluster convenience quota
convenience
The sample consisted of nursing students enrolled in a Research and Statistics class taught at the undergraduate level at a large university. simple random stratified random systematic random cluster convenience quota
convenience
non-probability sampling most vulnerable to sampling biases uses most easily available people most commonly used in nursing research most inexpensive
convenience sampling
Threat to external validity that makes effects observed in a study unlikely to be replicated in real life. e.g., subjects participating in an intervention program to reduce domestic violence might be less likely to abuse their partner because they know they are being monitored for domestic violence
Expectancy effect (Hawthorne effect)
constancy of conditions
Means that subjects in all experimental groups are exposed to identical conditions except for the differing experimental treatments. CONTROL OVER ENVIRONMENT, SETTING, TIME - Control over intervention via a formal protocol. [for example, you give one group a new med and one group a placebo, but you make sure both groups get it at the same time, place, etc.]
difference between random sampling and random assignment [randomization]
Random sampling refers to the method you use to select individuals from the population to participate in your study. In other words, random sampling means that you are randomly selecting individuals from the population to participate in your study. random assignment [randomization] refers to the method you use to randomly place participants into groups in an experimental study. For example, say you are conducting a study comparing the blood pressure of patients after taking aspirin or a placebo. You have two groups of patients to compare: patients who will take aspirin (the experimental group) and patients who will take the placebo (the control group). Needed in a true experiment in quantitative research.
3 threats to external validity
Selection bias - the sample selected for the study does not accurately represent target population. e.g., a study assessing the effect of physical activity on blood pressure only recruited females, thus it cannot generalize to males Expectancy effect (Hawthorne effect) makes effects observed in a study unlikely to be replicated in real life. e.g., subjects participating in an intervention program to reduce domestic violence might be less likely to abuse their partner because they know they are being monitored for domestic violence Unfortunately, enhancing internal validity can sometimes have adverse effects on external validity. e.g., a trial focused on breast cancer prevention only included Caucasian females living in rural settings who were 25-30 years old and reported no history of obesity, alcohol use, tobacco use or hormonal therapy. How generalizable is this study?
Brady hypothesized that the absence of socioemotional support among the elderly results in a high level of chronic health problems and low morale. She tested this hypothesis by interviewing a sample of 250 residents of one community who were aged 65 years and older. The participants were randomly selected from a list of town residents. Brady asked a series of questions about availability of socioemotional supports [e.g. whether the participants lived with any kin, whether they had any living children who resided within 30 minutes away, etc.]. Based on responses to the various questions on social support participants were classified in one of three groups: low, moderate or high social support. In a 6 month follow-up interview, Brady collected information from 214 participants about the frequency and intensity of the respondent's illnesses in the preceding 6 months, their hospitalization record and their overall satisfaction with life. The data analysis revealed that participants in the low-support group had significantly more health problems and hospitalizations and lower life satisfaction ratings that those in the other two groups. Brady concluded that the availability of social supports resulted in better physical and mental adjustment to old age. Is the researcher justified in concluding that lower levels of social support cause more health problems and lower life satisfaction?
We could say there is a relationship, but we would need a true experimental design study to really determine if there was a true correlation.
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. Was history a possible threat to the internal validity of this study?
We don't really know. A history threat is a threat to internal validity where there are other events co-occurring with causal factor that could also affect outcomes e.g., weight watchers launches media campaign & offers a free six-month trial at the same time as a study providing behavioral counseling to lose weight.
What is a confounding variable?
a factor other than the independent variable that might produce an effect in an experiment [like not taking into account fiber consumption, nutrition, etc. on a weight loss study]
Which of the following provides the best example of meeting criteria to determine causality? a. Intestinal distress occurs after subjects diagnosed with Celiac disease ingest gluten. b. Intuition that computer screen time impairs vision. c. Prospective study showing high correlation between stress and anxiety. d. Increased sodium intake predicted to lower blood pressure.
a. Intestinal distress occurs after subjects diagnosed with Celiac disease ingest gluten.
Which of the following is most likely to be an example of a "true experiment"? a. "The effects of sunlight exposure on Vitamin D levels in preschool children: A retrospective study." b. "The impact of melatonin on sleep regulation in blind adults: A randomized, placebo-controlled study." c. "National survey of children's second-hand smoke exposure in households of smoking adults." d. "Comparison of hospitals with Magnet status versus those without on nursing turnover."
b. "The impact of melatonin on sleep regulation in blind adults: A randomized, placebo-controlled study."
Researchers are looking to recruit nurses who work evening or night shifts, or who rotate shifts, to take part in a study evaluating an online educational program teaching about sleep hygiene. Which of the following sampling strategies is the most practicable for this study? a. Quota b. Convenience c. Random d. Stratified
b. Convenience [maybe the word "practicable" is a clue word for convenience? or maybe because they will all come from one group and one place]
In the article: Horne-Thompson, A. & Grocke, D. (2008).The effect of music therapy on anxiety in patients who are terminally ill, Journal of Palliative Medicine, 11(4), 582-590, the authors used a formal conceptual model. a. True b. False
b. False
What sampling method is most likely to be used for the following study: "Effect of melatonin compared to placebo in regulating sleep in persons who are blind." a. Probability b. Non-probability
b. Non-probability [does not involve the selection of elements at random - they are all blind]
For which of the following research questions would simple random sampling be most appropriate? a. Do attitudes toward shift work differ among male and female nursing students in Maryland? b. What are Maryland nurses' attitudes toward shift work? c. Does a sleep hygiene educational program improve the sleep quality of nurses who work off-shifts? d. What is the lived experience of first-time parent nurses working night shift?
b. What are Maryland nurses' attitudes toward shift work? [I believe this is the answer because it is randomly pulling a sample from the simplest sampling frame - MD nurses]
Type of qualitative research design that focuses on the discovery of a basic social psychological problem that a defined group of people experience.
grounded theory
DIFFERENT PEOPLE are compared. e.g., those getting and those not getting an intervention
between-subjects design
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. What is the dependent variable in the study?
dependent variable = result of independent variable/outcome/what they are measuring menopausal symptoms
phenomenological research that describes human experience based on philosophy of Husserl
descriptive phenomenology
Research design that focuses on the culture of a group of people, with an effort to understand the worldview and customs of those under the study. For instance, studying what the culture of the crafting community is.
ethnographic research
Different types of qualitative research design.
ethnographic research phenomenological research [descriptive and interpretive] grounded theory research
the generalizability of the observed relationships to the target population - conclusions of a scientific study regarding cause and effect can be applied outside the context of that study with the general population as well.
external validity
4 different types of validity
face validity content validity criterion related validity construct validity
Type II error
failing to reject a false null hypothesis [i.e. the researcher concludes that no relationship exists when in fact it does - a false negative]
Threat to internal validity where there are other events co-occurring with causal factor that could also affect outcomes e.g., weight watchers launches media campaign & offers a free six-month trial at the same time as a study providing behavioral counseling to lose weight.
history threat
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. What is the independent variable in this study?
independent variable = intervention relaxation and biofeedback
Brady hypothesized that the absence of socioemotional support among the elderly results in a high level of chronic health problems and low morale. She tested this hypothesis by interviewing a sample of 250 residents of one community who were aged 65 years and older. The participants were randomly selected from a list of town residents. Brady asked a series of questions about availability of socioemotional supports [e.g. whether the participants lived with any kin, whether they had any living children who resided within 30 minutes away, etc.]. Based on responses to the various questions on social support participants were classified in one of three groups: low, moderate or high social support. In a 6 month follow-up interview, Brady collected information from 214 participants about the frequency and intensity of the respondent's illnesses in the preceding 6 months, their hospitalization record and their overall satisfaction with life. The data analysis revealed that participants in the low-support group had significantly more health problems and hospitalizations and lower life satisfaction ratings that those in the other two groups. Brady concluded that the availability of social supports resulted in better physical and mental adjustment to old age. What is the independent variable?
independent variable = intervention social support of some kind - not clearly specified
When ..... is enhanced, it can sometimes have adverse effects on external validity. e.g., a trial focused on breast cancer prevention only included Caucasian females living in rural settings who were 25-30 years old and reported no history of obesity, alcohol use, tobacco use or hormonal therapy. How generalizable is this study?
internal validity
the extent to which it can be inferred that the independent variable caused or influenced the dependent variable - conclusions of a scientific study regarding cause and effect can only be applied within the study itself.
internal validity
Phenomenological research that not only describes but interprets experiences. Based on philosophy of Heidegger.
interpretive phenomenology
the treatment being tested - often the I in PICO
intervention
three parts of a true experimental research design
intervention randomization [random assignment] - this one seems to be most important!! control
Brady hypothesized that the absence of socioemotional support among the elderly results in a high level of chronic health problems and low morale. She tested this hypothesis by interviewing a sample of 250 residents of one community who were aged 65 years and older. The participants were randomly selected from a list of town residents. Brady asked a series of questions about availability of socioemotional supports [e.g. whether the participants lived with any kin, whether they had any living children who resided within 30 minutes away, etc.]. Based on responses to the various questions on social support participants were classified in one of three groups: low, moderate or high social support. In a 6 month follow-up interview, Brady collected information from 214 participants about the frequency and intensity of the respondent's illnesses in the preceding 6 months, their hospitalization record and their overall satisfaction with life. The data analysis revealed that participants in the low-support group had significantly more health problems and hospitalizations and lower life satisfaction ratings that those in the other two groups. Brady concluded that the availability of social supports resulted in better physical and mental adjustment to old age. What is the dependent variable?
levels of health problems and hospitalizations life satisfaction ratings [morale]
Threat to internal validity that are the processes that result simply from the passage of time e.g., a study which assesses children's reading ability from pre-K through second grade
maturation threat
Research in which both quantitative and qualitative data are collected and analyzed to addressed different yet related questions. Study combining surveys, interviews, focus groups, etc.
mixed methods research
A threat to internal validity that is differential loss of participants from different groups (by dropping out for any reason). Typically a threat in experimental studies e.g., study testing in-person versus web-based education program to reduce household lead exposure; 30 subjects enrolled to each, 10 withdraw from web-based arm, 2 from in-person arm
mortality threat
What does a double-blinded study involve? WILL BE ON TEST
neither researchers nor subjects know what group subjects are assigned to. a placebo or sham is used
Multi-stage sampling: start with a random sample of school districts, proceed to schools and end up with classrooms. probability or non-probability? simple random, quota, convenience [accidental], systematic random, stratified random, or cluster?
probability [random] cluster sampling [goes through stages from big to smaller]
Brady hypothesized that the absence of socioemotional support among the elderly results in a high level of chronic health problems and low morale. She tested this hypothesis by interviewing a sample of 250 residents of one community who were aged 65 years and older. The participants were randomly selected from a list of town residents. Brady asked a series of questions about availability of socioemotional supports [e.g. whether the participants lived with any kin, whether they had any living children who resided within 30 minutes away, etc.]. Based on responses to the various questions on social support participants were classified in one of three groups: low, moderate or high social support. In a 6 month follow-up interview, Brady collected information from 214 participants about the frequency and intensity of the respondent's illnesses in the preceding 6 months, their hospitalization record and their overall satisfaction with life. The data analysis revealed that participants in the low-support group had significantly more health problems and hospitalizations and lower life satisfaction ratings that those in the other two groups. Brady concluded that the availability of social supports resulted in better physical and mental adjustment to old age. Was random assignment used to control extraneous variables?
no
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. Was there blinding or double-blinding in this study?
no
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. Was there random assignment in this study?
no
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. Was mortality a possible threat to the internal validity of this study?
no - no drop out. did not lose any participants
Brady hypothesized that the absence of socioemotional support among the elderly results in a high level of chronic health problems and low morale. She tested this hypothesis by interviewing a sample of 250 residents of one community who were aged 65 years and older. The participants were randomly selected from a list of town residents. Brady asked a series of questions about availability of socioemotional supports [e.g. whether the participants lived with any kin, whether they had any living children who resided within 30 minutes away, etc.]. Based on responses to the various questions on social support participants were classified in one of three groups: low, moderate or high social support. In a 6 month follow-up interview, Brady collected information from 214 participants about the frequency and intensity of the respondent's illnesses in the preceding 6 months, their hospitalization record and their overall satisfaction with life. The data analysis revealed that participants in the low-support group had significantly more health problems and hospitalizations and lower life satisfaction ratings that those in the other two groups. Brady concluded that the availability of social supports resulted in better physical and mental adjustment to old age. Is the design experimental, quasi-experimental, pre-experimental or non-experimental?
non-experimental design [just describing and looking at the relationship of factors - not doing an experiment]
does not involve the selection of elements at random
non-probability
Researcher Jones samples the attitudes of the staff that are waiting in the cafeteria line at the XYZ Hospital. probability or non-probability? simple random, quota, convenience [accidental], systematic random, stratified random, or cluster?
non-probability [no mention of random] convenience [non-probability because of lack of randomization, and convenience because they were all just standing in line at the same place]
Researcher Smith samples the attitudes of 50 male and 50 female staff members who are waiting in the cafeteria line at the XYZ Hospital. probability or non-probability? simple random, quota, convenience [accidental], systematic random, stratified random, or cluster?
non-probability [no mention of random] quota sampling [convenience sampling going an extra step - convenient sampling within specific strata - men and women]
quantitative research design which is observational and descriptive - NO INTERVENTION. may have random SAMPLING - NOT same as random ASSIGNMENT!
nonexperimental quantitative research design
What kind of qualitative design focuses on the lived experiences of humans? key word is LIVED EXPERIENCE!
phenomenological research
a procedure for estimating either the needed sample size for a study or the likelihood of committing a Type II error.
power analysis
Involves random selection of elements: each element has an equal, independent chance of being selected.
probability
The names of all persons in the population are assigned a code number and a table of random numbers is used to select the sample. probability or non-probability? simple random, quota, convenience [accidental], systematic random, stratified random, or cluster?
probability [random] simple random [simple random because sample members are only chosen from one sampling frame. probability because the selection of sample members is random]
Random sampling is done in terms of proportional representation from all subgroups deemed relevant; e.g., in a survey on attitude toward abortion, the researcher gets proportional representation for the 3 major religions and the 2 sexes. probability or non-probability? simple random, quota, convenience [accidental], systematic random, stratified random, or cluster?
probability [random] stratified random [random sampling chosen from different chosen groups]
The names of all persons in the population are listed, a random start is taken, and every Nth name is selected for inclusion in the sample. probability or non-probability? simple random, quota, convenience [accidental], systematic random, stratified random, or cluster?
probability [random] systematic random [every Nth, every 3rd, etc. ]
An evaluation of the quality of a measuring instrument.
psychometric assessment
Type of nonprobability sampling where sample members are hand-picked by researcher to achieve certain goals Used more often by QUALITATIVE than quantitative researchers Can be used in quantitative studies to select experts or to achieve other goals
purposive [judgmental] sampling
What kind of research design is ethnographic research?
qualitative research
To investigate the effect of relaxation training on anxiety levels, a nurse investigator gives relaxation training to a group of 25 expectant moms. She measures their anxiety level both before and after training sessions. quasi or true experiment? Why?
quasi-experiment - people are not randomly assigned.
A new drug is being tested for its effectiveness in reducing psychotic behavior. The researcher gives the drug to schizophrenic patients from Ward B and gives placebo to schizophrenic patients in Ward D. Nursing staff records the number of psychotic behaviors following administration of the drug. quasi or true experiment? Why?
quasi-experiment because the patients were not randomly assigned
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. Is the design experimental, quasi-experimental, pre-experimental, or non-experimental?
quasi-experimental [quantitative research design that includes intervention, but lacks randomization and sometimes even a control]
An investigator who is interested in studying attitude change presents a slide/lecture presentation on the topic of "Do Not Resuscitate Orders" to a group of nursing students. Following the lecture, the investigator administers an attitude scale to each student. quasi or true experiment? Why?
quasi-experimental all are nursing students - no randomization [random assignment]
quantitative research design that includes intervention, but lacks randomization and sometimes even a control
quasi-experimental quantitative research design
convenience sampling that goes an extra step - sampling within specified strata of the population enhances representativeness of sample
quota sampling
the assignment of subjects to treatment conditions in a random manner [i.e. in a manner determined by chance alone]. also called random assignment
randomization
another name for a true experimental research design
randomized controlled trial
key criteria in a psychometric assessment
reliability validity
Threat to external validity where the sample selected for the study does not accurately represent target population. e.g., a study assessing the effect of physical activity on blood pressure only recruited females, thus it cannot generalize to males
selection bias
Threat to internal validity where biases arising from pre-existing differences between groups being compared are present. This is the single biggest threat to studies that do not use an experimental design. e.g., a study with the purpose of evaluating high school students' access to web-based resources recruits through cell phone text messages Who would this exclude?
selection threat
4 types of probability sampling
simple random stratified random systematic random cluster [multistage] [sr, sr, sr, c]
Using a random table of numbers, 50 names were selected from the list of 200 staff nurses at ACG Hospital. Questionnaires were sent to the 50 selected nurses. simple random stratified random systematic random cluster convenience quota
simple random [random table of numbers]
basic probability sampling involving the selection of sample members from a sampling frame at random
simple random sampling
The selection of participants through referrals from earlier participants; also called network sampling QUALITATIVE
snowball sampling [its like the snowball effect where as you roll a snowball in the snow it gets bigger]
The sample consisted of 50 staff nurses working at JH Hospital. 45 participants were randomly selected from the female staff nurses working at the hospital and 5 participants were randomly selected from the male staff nurses working at the hospital. simple random stratified random systematic random cluster convenience quota
stratified random [random sampling chosen from different previously chosen groups]
Probability sampling where a population is first divided into strata, then random selection is done from the stratified sampling frames Enhances representativeness -Can sample proportionately or disproportionately from the strata
stratified random sampling
Potential participants were selected from the MNA membership list. Every fifth name was selected after choosing the first name at random. simple random stratified random systematic random cluster convenience quota
systematic random [every 5th name]
Potential participants' names were taken from the daily hospital admissions list. Beginning at a random point, every third patient was invited to participate. simple random stratified random systematic random cluster convenience quota
systematic random [every third indicates systematic]
The selection of sample members such that every kth [e.g. every 10th] person or element in a sampling frame is chosen.
systematic random sampling
Threat to internal validity where it is unclear whether presumed cause occurred before outcome e.g., study shows that women who drink moderate daily caffeine have lower depression scores Which came first: depression or moderate caffeine intake?
temporal ambiguity
5 threats to internal validity
temporal ambiguity selection threat history threat maturation threat mortality threat
What is the hallmark of a quasi-experiment?
the implementation of an intervention in the absence of randomization [random assignment]
In order to determine what effect the type of nursing duty has on burnout [as measured by the number of reported sick days] nurses were randomly assigned to a three month rotation in either the ICU, emergency room, or geriatric unit. At the end of the three month period the number of sick days were calculated. quasi or true experiment? Why? dependent variable?
true experiment - nurses were randomly assigned burnout
An investigator randomly assigns patients to 1 of 3 pre-op education programs and assesses their anxiety level prior to surgery by use of a self-report measure. Assume there are posttests as well. quasi or true experiment? Why?
true experiment - patients were randomly assigned
In order to study the effects of a new drug on memory, a researcher using patients at a geriatric clinic randomly assigns patients to either Group 1 [new drug] or Group 2 [sugar pill]. The patients are given memory test both prior to and following the intervention. quasi or true experiment? Why? what is the control? what is the intervention?
true experiment because patients are randomly assigned into different groups sugar pill is control new medication is intervention
3 quantitative research design options
true experimental quasi-experimental nonexperimental
What is the highest level, "golden" standard, most rigorous form of research? why?
true experimental design randomization, intervention, control
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. Is the study design within-subjects or between-subjects?
within-subjects
Same people compared at different times or under different conditions. e.g., same subjects tested preoperatively and postoperatively.
within-subjects design
2 types of comparisons used in quantitative research design
within-subjects design between-subjects design
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. Would it be possible to address the same research question with a stronger research design?
yes - do some randomization for a more rigorous study design
Janosy wanted to test the effectiveness of a new relaxation/biofeedback intervention on menopausal symptoms. They invited women who presented themselves in an outpatient clinic with complaints of severe hot flashes to participate in the study of the experimental treatment. These 30 women were asked to record, every day for 2 weeks before their treatment, the frequency and duration of their hot flashes. The intervention involved five 1-hour sessions over a period of a week. Then, for the 2 weeks after the treatment, the women were asked to record their hot flashes again every day. At the end of the study, Janosy found that both the frequency and average duration of the hot flashes had been significantly reduced in this sample of 30 women. They concluded that their intervention was an effective alternative to estrogen replacement therapy in treating menopausal hot flashes. Was selection a possible threat to the internal validity of this study?
yes - selection threats are biases arising from pre-existing differences between groups being compared [random ladies just walked in - no specific data like white, age 30-40, rich, etc.]
Brady hypothesized that the absence of socioemotional support among the elderly results in a high level of chronic health problems and low morale. She tested this hypothesis by interviewing a sample of 250 residents of one community who were aged 65 years and older. The participants were randomly selected from a list of town residents. Brady asked a series of questions about availability of socioemotional supports [e.g. whether the participants lived with any kin, whether they had any living children who resided within 30 minutes away, etc.]. Based on responses to the various questions on social support participants were classified in one of three groups: low, moderate or high social support. In a 6 month follow-up interview, Brady collected information from 214 participants about the frequency and intensity of the respondent's illnesses in the preceding 6 months, their hospitalization record and their overall satisfaction with life. The data analysis revealed that participants in the low-support group had significantly more health problems and hospitalizations and lower life satisfaction ratings that those in the other two groups. Brady concluded that the availability of social supports resulted in better physical and mental adjustment to old age. Would it be possible to address the same research question with an experimental design?
yes [I'm thinking maybe you could improve the social support of some and see if health improved. Don't think it would be ethical to go the other way]
