Research Methods

How can you demonstrate possible causal relationships that could explain a correlation that is formed between two variables, A and B? (3)

1) A ---> B 2) B ---> A 3) C ---> B, C--->A

What are the general advantages and disadvantages of non-experimental designs? (2)

1) A: in general, they tend to offer the benefit of observing phenomena in a more naturalistic setting --> this means that they may offer benefits in external validity 2) D --> reduced control of the variables of interest, which tends to reduce the internal validity

What are the advantages and disadvantages of the experimental design for the step of selecting the population?

1) D --> the researchers have compromised the reach and scope of their experiment 2) A --> they now have the advantage of a large pool of willing participants that they can sample for their experiment

What are the most frequently tested non-experimental designs on the MCAT? (6)

1) correlational studies 2) ethnographic studies 3) twin studies 4) longitudinal studies 5) case studies 6) phenomenological studies

What are the disadvantages of longitudinal studies? (4)

1) costly 2) difficult to execute 3) time and resource intensive 4) have high attrition rates

What is the most commonly used type of correlational study?

the PEARSON CORRELATION

What is one of the many phenomena that can complicate social research and lead to incorrect results?

the PLACEBO EFFECT

What is an advantage of longitudinal studies?

the ability to detail how an effect or factor can develop over time

Sample Size

the direct count of the number of samples measured or observations being made --> number of participants

Internal Validity

the extent to which a piece of evidence supports a claim about cause and effect, within the context of a particular study

What is one of the most common flaws in social research?

the fact that most studies are done on undergraduate students, and the results are then applied to the greater population

What might a flaw in external validity result in?

the flaw or limitation might make it difficult to apply our conclusion to the real world

Experimental Group

the group of participants that receives treatment

Attrition

the loss of study participants over time --> participants dropping out of the study

What are the requirements for an independent variable to qualify as an experimental design?

this variable must be DIRECTLY MANIPULATED by the researchers --> researchers want to have maximum control over the experimental environment so that they can be sure that differences between the groups actually lead to the effect, assuming one is measured

What is the purpose of measuring the results (step 6)?

to check to make sure that their measurements are valid

What is necessary in order to make sure that the experiment picks up an effect?

to have a large enough SAMPLE SIZE or number of participants --> usually 30 or more participants are necessary to meet the mathematical requirements needed to conduct statistical tests

What is the objective of homogeneity (similarity) for experimental design?

to rule out EXTRANEOUS (or CONFOUNDING) VARIABLES

How is this a threat to external validity? --> the fact that only students of Healthy Living U can participate in a study

we cannot be absolutely sure that a result that rejects the null hypothesis applies to ALL healthy young adults in mid 20s

How is this a threat to external validity? --> the fact that no high school dropouts or Ph.D. students were included in a study

we cannot be sure that the findings also apply to these educational brackets

In what kinds of situations are investigations considered phenomenological?

when they attempt to understand an individual's own perceptions and understandings --> rather than make a comparison between variables or draw causal conclusions

To obtain rigorous results from the dependent variable, what must the researchers do? (3)

1) create an OPERATIONAL DEFINITION 2) the independent variable was operationalized as a very specific set of foods consumed over a 6-month period --> the dependent variable must be equally well-defined 3) the dependent variable must also meet the criteria of being QUANTITATIVE, or numerical, as opposed to QUALITATIVE, or descriptive --> quantitative data will be necessary later to conduct statistical analyses that will test the research hypothesis

Explain the optimal experimental design for operationalization of the dependent variable for our experiment... (3)

1) dependent variable --> cardiovascular health 2) the researchers decide that the dependent variables they will measure are --> heart rate, blood pressure, peak oxygen uptake, etc. 3) each of these will produce a numerical value that they will measure before and after the 6-month period --> the difference in these values will test the effect of the dietary regiment on health

the researcher decided that their population of interest would be "all humans" --> How could this compromise the experiment? (4)

1) this would involve finding older (and younger) participants 2) incentivizing (encouraging) them to participate in the research 3) following through to make sure they follow the experimental protocols correctly 4) OVERALL --> this would be very taxing in terms of resources and logistics

What problems tend to come up in experimental methodology? (2)

1) threats to internal and external validity 2) ethical considerations

Explain a longitudinal non-experimental design needed if you wanted to conduct this study --> want to answer this research question: What effect does our disposition at birth have on the life we lead? (2)

1) to test this, researchers need to categorize newborns according to their disposition --> were they agreeable or irritable, healthy or sickly, regular or irregular in biological functions? 2) then, they need to check on subjects over periodic intervals to see if temperament at birth is consistent throughout life

Explain the design needed to perform this case study --> a researcher from healthy Living U met a native Sicilian in her late-90s with extraordinary health and fitness. They might want to know everything about this person's diet and lifestyle to understand how they were able to obtain such a high level of fitness (2)

1) to understand this individual, they might look at dietary habits over time, exercise frequency, interaction with family, etc. 2) then, they would need to compile this data and offer a report for critique by the scientific community

to help counter the placebo effect, studies must be...

DOUBLE-BLIND

twin studies are the best way to measure...

HERITABILITY

Why do researchers need a control group for our experiment?

How would the researchers know that being given ANY dietary regiment might not also have the same results of improvement in cardiovascular health? --> the researchers need a point of comparison (control group) to rule this possibility out

What is needed for researchers to draw conclusions about the effect of the treatment?

a CONTROL group

Ethnographic Studies

a branch of anthropology (the study of human societies and cultures and their development) and the systematic study of individual cultures --> a qualitative method in which researchers immerse themselves completely in the lives, culture, or way of life of the people they are studying

What type of sample size is usually preferred? Why?

a larger sample size --> this increases the POWER of the experiment

What might a flaw in internal validity result in?

a limitation in the study such that the experiment is not "well done", and we cannot be sure about the conclusion because of some inherent flaw in the design

Pearson Correlation

a measure of linear correlation between two sets of data --> assigns a number from -1 to +1 to a pair of variables

Longitudinal Method

a non-experimental research design that involves repeated observations of the same variables over short or long periods of time --> involves intervallic (sporadic) measurements of a dependent variable over long time frames

Longitudinal Studies

a non-experimental study used by researchers who may be interested in how individuals develop over time along some research method

Case Studies

a process or record of research in which detailed consideration is given to the development of a particular person, group, or situation over a period of time --> involve in-depth exploration of one individual or case

Disclosure

a requirement in research in which the researcher provides full disclosure of their identity and purpose in collecting data --> an outlining of the nature of the experiment to participants before they are subject to experimental procedures that clarifies incentives and expectations while reminding them of their right to terminate the experiment at any time

Debriefing

a researcher explains the purpose of the study --> participants are told after the experiment exactly what was done and why the experiment was conducted

Heritability

a statistic used in the fields of breeding and genetics that estimates the degree of variation in a phenotypic trait in a population that is due to genetic variation between individuals in that population --> the extent to which an observed trait is due to genetics vs. the environment

What happens if an experiment does not have a control group?

a study is not experimental and causal relationships cannot be drawn

Experimental Design

a technical term for a SPECIFIC TYPE of research

Correlational Studies

a type of non-experimental research method in which a researcher measures two variables, and understands and assesses the statistical relationship between them with no influence from any extraneous variable --> explore the relationship between two quantitative variables

Independent Variable

a variable (often denoted by x ) whose variation does not depend on that of another --> the variable manipulated by the research team

Dependent Variable

a variable (often denoted by y ) whose value depends on that of another --> the variable that is measured

What is the independent variable for our experiment?

adherence to a Mediterranean diet

Placebo Effect

an effect produced by a placebo drug or treatment, which cannot be attributed to the properties of the placebo itself, and must therefore be due to the patient's belief in that treatment --> the well-known fact that just BELIEVING the treatment is being administered can lead to a measurable result *if researchers know that they are administering a treatment, that can also lead to a placebo effect!*

Many different types of studies have shown that a Mediterranean diet is associated with cardiovascular health and longevity --> What is needed in order to show that consuming this diet helps CAUSE, or helps LEAD to cardiovascular health and longevity?

an experimental design

Randomized Block Technique

an experimental design in which the experimenter divides subjects into subgroups called blocks, such that the variability within blocks is less than the variability between blocks --> researchers evaluate where participants fall along the variables they wish to homogenize, then they randomly assign individuals from these groups so that the treatment and control group are similar along the variables of interest

Extraneous (or Confounding) Variables

any variable that you're not investigating that can potentially affect the outcomes of your research study --> variables other than the treatment that could potentially explain an experimental result

What is one of the most important aspects of experimental design?

assigning a control group

How is this a threat to external validity? --> the fact that there was a special diet, constructed by researchers, cooked by culinary professionals at a university, and monitored by scientists

can we really expect an average person trying to eat an experimental diet to match the rigor of this group?

What is the dependent variable for our experiment?

cardiovascular health --> this is the variable that the researchers will measure to see if their diet has an effect

What type of non-experimental study would this be? --> a researcher from healthy Living U met a native Sicilian in her late-90s with extraordinary health and fitness. They might want to know everything about this person's diet and lifestyle to understand how they were able to obtain such a high level of fitness

case study --> involves in-depth exploration of one individual or case

Phenomenological Studies

commonly described as the study of phenomena as they manifest in our experiences of the way we perceive and understand phenomena, and of the meaning phenomena have in our subjective experience --> interested in describing phenomena, in using the introspective method to explore research questions

Experimental design offers the only way to...

confidently establish a causal relationship between two variables

Double Blind

describes an experimental procedure in which neither the participant nor the experimenter are aware of which group (the experimental or control) each participant belongs to --> used to help counter the placebo effect

twin studies interested in the heritability of intelligence might look at correlations in IQ scores between monozygotic (identical) and fraternal (dizygotic) twins --> What would be a reasonable conclusion about this study?

differences between these two correlations are due to genetics, since both twins share an environment

What should not be done when trying to reject a null hypothesis?

do not simply observe a difference between two groups because the observed difference may simply be due to chance --> if the Healthy Living U researchers find slight differences between the experimental and control groups in cardiovascular fitness, they will not rush to conclude that the difference is SIGNIFICANT

What type of non-experimental study would this be? --> a researcher interested in the effect of the Mediterranean diet on health might go to a remote Sicilian village and study the lives of the participants, scrutinizing their everyday lives and recording everything they possibly can over the span of several years

ethnographic study

Do ethical problems tend to arise more in experimental or non-experimental designs? Why

experimental --> because researchers are directly manipulating variables, not just observing what they see in nature

What is the purpose of operationalizing the independent and dependent variables in an experiment?

good experimental design requires experiments that can be reproduced by other researchers, who may want to verify the results on their own or critique or adapt some aspect of the experiment --> precise definitions are key

For testing the hypothesis (step 7), what have scientists over the years generally agreed on?

it is better to incorrectly conclude that there is no effect than to falsely suppose a result that does not actually exist --> it is better to reason from a point of skepticism

From the first step of selecting the population for our experiment, if the researchers DO find that Mediterranean diet adherence leads to cardiovascular health, can they say that this result is also true for individuals in their early 50s or 60s?

it might, but this conclusion now lies outside of the scope of the Healthy Living U experiment --> follow-up studies would be needed to say for sure whether the effect also applies to older adults

What is the purpose of the null hypothesis?

it places the "burden of proof" on the experimental hypothesis

Once the individuals who will participate in the study have been incentivized and rounded up (step 4), what is the next step?

its time to assign them to the experimental and control groups (step 5)

What type of non-experimental study would this be? --> want to answer the question: What effect does our disposition at birth have on the life we lead?

longitudinal study --> the researcher is interested in how an individual develops over time

Significant Difference

means that there is a measurable difference between the two groups and that, statistically, the probability of obtaining that difference by chance is very small --> a measured difference between two groups that is large enough that it is probably not due to chance

Qualitative

measured by the quality of something rather than its quantity --> descriptive

Quantitative

measured by the quantity of something rather than its quality --> numerical

Does our experimental design require validating the measurements (step 6)? What type of experiments would more likely apply to this step?

not really, because for this experiment, the dependent variable is a set of well-known physiological measurements with standardized collection procedures and error measures --> more generally, if researchers are using a survey or new instrument, they must check to make sure that their measurements are valid

What is an advantage of case studies?

offers an excellent way to thoroughly explore the potential causes that led to a phenomena

Potential flaws that may arise in experimental designs might compromise...

our ability to draw conclusions about the real world from our study

What type of experimental studies would especially need reliability?

psychological studies that might test dependent variables like mood, memory, and attitude that are hard to pin down

Operationalize

put into operation or use

Reliable

refers to the consistency of a research study or measuring test --> measures what it's supposed to and repeated measurements lead to similar results

What type of control group would be best to answer the research question for our experiment?

researchers want to show that eating a Mediterranean diet causes cardiovascular health --> to show this, they need a control group that is as similar as possible to the experimental group, except for the variable of interest: the treatment (they need homogeneity)

What kind of experimental design can be combined with Pearson correlations? What would be the benefit of this?

significance testing --> to see if the compound correlated is likely to have occurred by chance, or not

Operational Definition

specifies concrete, replicable procedures designed to represent a construct (form) --> a specification of precisely what they mean by each variable

Null Hypothesis

states that there is no relationship between the two variables being studied --> assume that there is no causal relationship between the variables and any measured effect, if there is one, due to chance

Twin Studies

studies conducted on identical or fraternal twins --> often run to test the relationship between nature and nurture

What is wrong with this experiment formed to study the association between a Mediterranean diet and cardiovascular health and longevity? (2) --> (1) a team of social scientists create a scale to measure the extent to which an individual follows the Mediterranean diet - (2) when paired with a food frequency questionnaire, they assign a score for each individual, from 1 (diet least resembles Mediterranean diet) to 12 (diet most resembles Mediterranean diet): they call this the Mediterranean Diet Index (MDI) - (3) RESULTS: they find that as individual MDI scores increase, so do measures of cardiovascular health

1) does not show that adherence to the Mediterranean diet LEADS to improved health 2) the team has found a positive correlation between the MDI and cardiovascular fitness, but the correlation is not causation

What are the most common threats to external validity? (4)

1) experiment doesn't reflect real-world --> lab setups that don't translate to the real world, lack of generalizability 2) selection criteria --> too restrictive of inclusion or exclusion of criteria for participants (ex: sample is not representative) 3) situational effects --> presence of lab. conditions change the outcome (ex: pre-test and post-test, presence of experimenter, claustrophobia in an MRI machine) 4) lack of statistical power --> sample groups have high variability OR sample size is too small

What is the correct protocol for running modern experiments? (3)

1) experiments must be cleared by an independent internal commission that considers ethics 2) they must also contain some type of DISCLOSURE 3) finally, experimental protocol should include DEBRIEFING --> in some experiments (ex: if the experiment triggered psychological vulnerability), participants may be offered access to treatment or counseling services

The potential flaws that may arise in experimental designs can be placed into two categories. What are they?

1) external validity 2) internal validity

What are the potential flaws that can form from our experimental design of random sampling from the population? How can they compromise the experiment? (2)

1) for the Healthy Living U study, any healthy young adult in their early 20s should have an equal chance of participating --> however, since the study is done at a specific university, only students at that school can be used 2) ATTRITION: if the participants are dropping out for non-random reasons, this could introduce an extraneous variable --> ex: if the participants who drop out do so because they tend to not follow through with things they sign up for, this personality characteristic may confound any conclusions about their health and cardiovascular fitness

What are the potential flaws that can form from our experimental design of operationalization of the dependent and independent variables? How can they compromise the experiment? (2)

1) for the independent variable, what if the Mediterranean diet really starts to be effective after many years? perhaps our bodies have an adjustment period to any new dietary protocol and we only start to see benefits over time spans longer than 6 months --> if this were the case, the present experiment would not pick up a result, and might wrongly conclude that the diet is ineffective 2) the operationalization of the dependent variable is quantitative and rigorous, however, it only indirectly measures what we are really interested in : lowered risk of heart attack, increased longevity, and high life satisfaction --> the variable the researchers selected can only INDIRECTLY suggest that the quality of life variables we really care about are improving

What sorts of extraneous variables can affect our experiment? (3)

1) gender, age, and socioeconomic status 2) racial differences in responsiveness to the dietary regiment 3) exercise, BMI, and stress levels

Under what conditions is internal validity high? (2)

1) if confounding variables have been considered and minimized 2) if the causal relationship between the independent and dependent variables can be established by the way the experiment was set up

What are examples of experiments that confound the results and threaten internal validity? (3)

1) if researchers forget to control for gender 2) if the diet they selected did not actually represent a Mediterranean diet 3) if they had participants in their control group eat unhealthy foods

What are the conventional values for significant differences? (3)

1) if the probability of an observed difference is found to be 5% (or 0.05) or less --> this is a significant difference 2) if (and only if) p < 0.05 --> scientists reject the null hypothesis 3) other p values such as 0.01 or 0.001 are also frequently used as the threshold for significance in some cases

What are the potential flaws that can form from our experimental design of carefully selecting the control and experimental groups? How can they compromise the experiment? (2)

1) if the study is not double-blind --> the placebo effect can occur and produce incorrect results 2) if the control group is given pizza, burgers, and fries as their diet, rather than a healthy diet similar to the Mediterranean diet --> this would not be a good point of reference, since any healthy diet would probably produce a relative benefit

How does the Pearson correlation work? (3)

1) if the value is negative --> the two variables are negatively correlated: this means that if one increases, the other will decrease, and vice versa 2) a positive Pearson correlation --> represents a positive correlation, which means as one variable increases, the other also increases, and if one variable decreases, the other will also decrease 3) a value of zero --> indicates no correlation, there is no relationship between the two variables

What are the most common threats to internal validity? (4)

1) impression management --> participants adapt their responses based on social norms or perceived researcher expectations OR self-fulfilling prophecy OR methodology is not double blind, Hawthorne effect 2) confounding variables --> extraneous variables not accounted for in the study OR another variable offers an alternate explanation for results OR lack of a useful control 3) sampling bias --> selection criteria is not random, population used for sample does not meet conditions for statistical test (ex: population is not normally distributed) 4) attrition effects --> participant fatigue OR participant drops out of study

Explain the characteristics of ethnographic studies... (2)

1) they tend to be lengthy and thorough and involve as little interference or intervention by the researcher as possible 2) the culture studied is often unique or remote in someway, or offers a special insight into the scientific question

Explain the optimal experimental design for operationalization of the independent variable for our experiment... (5)

1) independent variable --> adherence to a Mediterranean diet 2) the researchers decide that they will work with the cafeteria on campus to serve a special diet to participants --> they create a 6-month, 21-meal weekly diet plan that participants will be required to follow 3) participants can also consume a pre-selected set of snacks and beverages for their dorm rooms, but these are provided, and outside food is not allowed 4) the diet the team constructs is such that it would score a perfect 12 on the MDI scale 5) NOW --> the independent variables are strictly operationalized or specified

What are the disadvantages of case studies? (2)

1) involves the limitation of no isolation of variables and control over the conditions 2) difficult to determine how the different variables involved in a phenomena interact

What are the possible explanations for the positive correlation between MDI scores and cardiovascular health found from the initial experiment? (2)

1) it is possible that people with a genetic predisposition towards cardiovascular health produce a profile of digestive enzymes that leads to a natural preference for a Mediterranean diet OR 2) perhaps there is some third factor such as exercise or social support that leads to both greater cardiovascular health AND preference for Mediterranean foods

Explain the optimal experimental design for randomly assigning individuals to groups (step 5) for our experiment... (3)

1) it should be equally likely that they are assigned to either group 2) assignments are usually not perfectly random, but if scientists alternate assignments or use another randomization technique, they can come close 3) in this study, there are many extraneous variables, so the researchers might use a RANDOMIZED BLOCK TECHNIQUE

What do good experimental designs often involve? (2)

1) making compromises to meet conditions OR 2) make conducting a study realistic

Explain the optimal experimental design for testing the hypothesis (step 7) for our experiment... (2)

1) must select the significance threshold in advance, or you might be tempted to change the number so that the data reaches a significance 2) a lower p-value suggests a stronger relationship

Explain the optimal experimental design for carefully selecting the control and experimental groups for our experiment... (5)

1) researchers agreed on a list of potential extraneous variables --> they carefully select groups that are homogenous in age, gender, race, status, serum cortisol levels, and BMI 2) to control for the extraneous variable exercise, they create a regulated regiment for both groups to follow 3) the study is DOUBLE-BLIND to help counter the placebo effect 4) the control group needs their own special diet, with physiologists taking their readings, and special chefs cooking their meals in the cafeteria 5) to appropriately isolate the variable being tested (the Mediterranean diet), researchers need to give a healthy alternative diet to the control group (s dier that scores about a 6 on the MDI, rather than 12) --> then, later, if a difference were measured, researchers could be sure that this result was due to the Mediterranean diet specifically, and not just the effect of eating a healthy diet

What are the disadvantages of our experimental design of carefully selecting the control and experimental groups? (2)

1) researchers can never account for EVERY potential extraneous variable --> ANY variable could be a potential confound, so researchers must focus on the most likely candidates 2) it may not be possible to control for a variable even if the researchers would like to --> ex: there is one variable that Healthy Living U can't do - education level: they cannot include people without high school diplomas without severely complicating the procedure

Explain the optimal experimental design for random sampling from the population for our experiment... (4)

1) researchers start recruiting participants for the study --> this sampling should be random 2) usually, participants are incentivized (encouraged) in some way --> could range from monetary compensation to new treatments and medications 3) population --> students at the university 4) Healthy Living U may use grades or tuition rebates as an incentive for students to participate

What are the steps involved for a good experimental design? (7)

1) select the population 2) operationalize the independent and dependent variables 3) carefully select control and experimental groups 4) randomly sample from the population 5) randomly assign individuals to groups 6) measure the results 7) test the hypothesis

Explain the optimal experimental design for the step of selecting the population... (4)

1) since many experiments in the social sciences are done by scholars at a university, suppose our team of researchers were all tenured at a university --> call this Healthy Living U 2) then, the easiest way for the researchers to get a large group of participants at low cost is to use students at Healthy Living U as participants in the experiment 3) our researchers would ideally like their findings to apply to everyone, but this would be very taxing in terms of resources and logistics 4) the researchers decide that their population of interest will be healthy young adults in their early 20s

What are the two main categories of non-experimental studies?

1) studies that involve researchers studying another individual or group of individuals --> correlational, ethnographic, twin, longitudinal, and case studies 2) studies that involve researchers studying themselves or researchers recording individuals as they reported their own personal experience --> phenomenological studies

What are the most important aspects of measurement for an experiment? (2)

1) the dependent variable is quantitative, therefore measurable 2) the instruments used are RELIABLE

Explain how the second step of operationalization of the dependent and independent variables we created for our experiment involves good experimental design... (3)

1) the operational definitions are strong 2) both the independent and dependent variable definitions are specific and replicable 3) the dependent variable is sufficiently quantitative to allow for statistical analyses

What are the general steps scientists use to test the hypothesis? (2)

1) they generally start with the NULL HYPOTHESIS 2) then, they see if evidence from the experiment suggests that the null hypothesis is true or false

The dependent variable in our experiment only indirectly measures what we are interested in. Why would measuring what we are actually interested in compromise the experiment? In other words, why would verifying experimentally that the Mediterranean diet decreases the risk of heart attack and leads to increased longevity potentially compromise the experiment? (3)

1) verifying this would be very difficult in practice 2) the Healthy Living U experiment we are developing is already shaping up to be VERY restrictive on participants, even though we have created an optimal scenario 3) to verify this statement, we would have to extend the dietary regiment for a life time, then measure average life expectancy and morbidity due to cardiovascular disease over the course of decades --> this would be nearly impossible to accomplish

To optimize study design, the two groups (experimental and control) being tested must be...

AS SIMILAR AS POSSIBLE

What are the potential flaws of selecting the population?

if the researcher decided their population of interest would be "all humans" --> it may seem obvious that they would be interested in "all humans", however, for many reasons this is not the best group to select

What is a disadvantage of our experimental design of operationalization of the dependent and independent variables?

in order to conduct this experiment realistically, researchers must compromise by narrowing the scope of their study and selecting measurable dependent variables like heart rate and blood pressure that IMPLY cardiovascular health, rather than try to measure cardiovascular morbidity and life expectancy directly

What is the purpose of the second step for a good experimental design for our experiment on the Mediterranean diet --> operationalize the independent and dependent variables

in this follow-up experimental study, the CAUSAL relationship that the researchers want to test experimentally is whether eating a Mediterranean diet LEADS TO greater cardiovascular health --> the researchers must specify exactly what they mean by this: they must operationalize the independent and dependent variables

When conducting an experiment, what is the first thing that researchers must agree on?

the population of interest (Who do they want to study?)

P-Value

the probability of obtaining test results at least as extreme as the results actually observed, under the assumption that the null hypothesis is correct --> a number from 0 to 1 that represents the probability that a difference observed in an experiment is due to chance

Experimental Power

the probability that a test of significance will pick up an effect that is present

Experimental Hypothesis

the proposition that variations in the independent variable cause changes in the dependent variables

It is up to _____________ to determine when the significance is big enough to reject the null hypothesis

the researcher

What can finally be done after carefully selecting the control and experimental groups?

the researchers can start recruiting participants for the study

What is an ideal of random sampling from the population that is almost never accomplished in practice?

the sampling should be random --> it should be equally likely for any member of the population to be a participant in the study

Control Group

the standard to which comparisons are made in an experiment --> acts as a point of reference and comparison

What must happen in order to rule out the possible explanations for the positive correlation between MDI scores and cardiovascular health found from the initial experiment?

the team must conduct a follow-up study with an experimental design

External Validity

the validity of applying the conclusions of a scientific study outside the context of that study

an intelligence study might look at the difference in correlations between IQ scores of identical twins reared together vs. reared apart --> What would be a reasonable conclusion about this study?

these differences would likely be due to the environment, since both sets of twins would share the same percentage of genes, namely 100

Scientists evaluating data from experiments have the same problem. What is it? How do they try to avoid this problem?

they can never be certain that a difference measured in an experiment actually reflects a fundamental difference between the groups and is not just due to chance --> they must arbitrarily (randomly) pick a cutoff point at which it is reasonable to conclude "beyond reasonable doubt" that there was a difference

How is this experiment unethical? --> suppose the Healthy Living U team wanted to conduct a separate experiment to show that high-fat, high-sugar diets are more likely to cause heart disease

they would be intentionally administering a treatment that they believe is harmful to participants