Psychology Quiz: Non Experimental Designs
20 questions · exam conditions
0:00
Non Experimental DesignsQuestion 1 of 20

A sociologist wants to understand national attitudes towards a new environmental policy. The goal is to gather data from thousands of individuals across different states, age groups, and socioeconomic backgrounds to create a descriptive overview. Which research method is uniquely suited to achieve this scope efficiently?

Naturalistic observation, as it allows for unobtrusive data collection about environmental behaviors in real-world settings.
A series of case studies, as they provide deep, rich data on individuals' complex reasoning about the policy.
An archival correlational study, as it can determine the causes of specific attitudes towards the policy by using pre-existing data.
A survey, as it can be administered to large, representative samples over a wide geographic area relatively quickly and inexpensively.
← Back to quizzes

Psychology Quiz

Psychology Quiz: Non Experimental Designs

Practice Non Experimental Designs in Psychology with focused quiz questions that help you check what you know, review explanations, and build confidence with test-style prompts.

What this quiz covers

This quiz focuses on Non Experimental Designs, giving you a quick way to practice the rules, question types, and explanations that matter most for Psychology.

How to use this quiz

Try each quiz question before looking at the correct answer. Use the explanations to review missed ideas, then come back to similar questions until the pattern feels familiar.

All questions

Question 1

A sociologist wants to understand national attitudes towards a new environmental policy. The goal is to gather data from thousands of individuals across different states, age groups, and socioeconomic backgrounds to create a descriptive overview. Which research method is uniquely suited to achieve this scope efficiently?

  1. Naturalistic observation, as it allows for unobtrusive data collection about environmental behaviors in real-world settings.
  2. A series of case studies, as they provide deep, rich data on individuals' complex reasoning about the policy.
  3. An archival correlational study, as it can determine the causes of specific attitudes towards the policy by using pre-existing data.
  4. A survey, as it can be administered to large, representative samples over a wide geographic area relatively quickly and inexpensively. (correct answer)
Explanation: The primary strength of the survey method is its ability to gather data from large and geographically dispersed samples efficiently. For a research goal that requires data from thousands of people across a country to describe national attitudes, a survey is the most practical and effective method. Naturalistic observation (A) is not feasible on this scale for measuring attitudes. Case studies (B) are too small-scale and in-depth. A correlational study (C) describes a statistical approach, not a data collection method, and it cannot determine causes.

Question 2

A team of researchers wants to study the social dynamics of preschoolers during free play. To minimize disruption, they install unobtrusive video cameras in the corners of the classroom after informing the children and parents that the cameras are 'newly upgraded smoke detectors.' The researchers' strategy of disguising the cameras is primarily an attempt to mitigate which limitation of observational research?

  1. Observer bias, which involves the researchers' expectations influencing their interpretation of the children's behaviors.
  2. Reactivity, which is the tendency for individuals to alter their behavior when they are aware of being watched. (correct answer)
  3. Lack of experimental control, which is the inability to manipulate variables and isolate causes in a natural setting.
  4. Low inter-rater reliability, which refers to a lack of consistency in how different observers score the same behaviors.
Explanation: Reactivity (also known as the Hawthorne effect) occurs when participants change their behavior because they know they are being observed. By disguising the cameras, the researchers are attempting to make the children unaware of the observation, thereby ensuring that their behavior is natural and not a reaction to being watched. Observer bias (A), lack of control (C), and inter-rater reliability (D) are all potential issues in this type of research, but the specific strategy of disguising the cameras is designed to combat reactivity.

Question 3

A researcher wants to compare the helping behaviors of people in bustling urban environments versus quiet rural environments. The researcher has a confederate drop a pile of books in a city street and later in a small-town square, counting the number of times the confederate receives help in each location. This field study's primary limitation, when compared to a laboratory experiment on helping behavior, is:

  1. the heightened potential for reactivity from participants who notice the confederate's repeated actions.
  2. the reduced ecological validity due to the staged and artificial nature of the book-dropping event.
  3. the inability to control for numerous confounding variables, such as the specific individuals present or the weather. (correct answer)
  4. the difficulty in operationally defining and reliably measuring what constitutes 'helping behavior.'
Explanation: The key trade-off between a field study (or field experiment) and a laboratory experiment is control versus ecological validity. While this design has good ecological validity because it's in a real-world setting, its primary limitation compared to a lab study is the lack of control. The researcher cannot control who walks by, what time of day it is, the weather, ambient noise, or other factors that could influence helping behavior. These uncontrolled factors are confounding variables. Reactivity (A) is a concern, but less so than in a lab. Ecological validity (B) is actually a strength, not a weakness, of this design. Defining 'helping' (D) is a challenge in any study of the topic, not one specific to the field setting.

Question 4

A survey about public policy includes the following two questions, administered to two different random samples of the population:

  • Sample 1: "Do you believe the government should forbid public speeches against democracy?"
  • Sample 2: "Do you believe the government should allow public speeches against democracy?"

Results show that a significantly higher percentage of people in Sample 1 answered "No" than the percentage of people in Sample 2 who answered "Yes."

The discrepancy in responses between the two samples most likely illustrates which of the following phenomena in survey research?

  1. Social desirability bias
  2. Non-response bias
  3. Wording effects (correct answer)
  4. Sampling error
Explanation: This scenario is a classic example of wording effects. Even though 'not forbidding' a speech is logically similar to 'allowing' it, the negative connotation of the word 'forbid' prompts more people to disagree with it. The different phrasing of the question leads to different responses, demonstrating how subtle changes in wording can significantly impact survey results. Social desirability bias (A) might play a role, but the core issue demonstrated by comparing the two phrasings is the effect of the words themselves. Non-response bias (B) and sampling error (D) are not directly illustrated by this systematic difference based on question phrasing.

Question 5

A political polling organization attempts to predict a mayoral election outcome by conducting a survey. They draw their sample from publicly available residential landline phone directories. The poll's prediction differs significantly from the actual election results. The poll's inaccuracy is most likely a consequence of which specific limitation?

  1. Wording effects, because the questions may have been phrased in a way that biased the responses of participants.
  2. Social desirability bias, because respondents may have been untruthful about their preferred candidate.
  3. The directionality problem, because it is unclear if voter preference influences polling response or vice-versa.
  4. Sampling bias, because the sample excluded voters who only use cell phones or have unlisted numbers. (correct answer)
Explanation: When evaluating research validity, you need to distinguish between different types of methodological problems. This question tests your understanding of sampling bias versus other research limitations. The correct answer is D because the polling method created a systematic exclusion of certain voter groups. By only using residential landline directories, the sample missed people who rely solely on cell phones (often younger voters) and those with unlisted numbers (who may have different demographic characteristics). This sampling bias means the sample wasn't representative of the actual voting population, leading to inaccurate predictions. Option A (wording effects) would cause systematic bias in how people respond to questions, but the question doesn't indicate problematic phrasing was involved. Option B (social desirability bias) occurs when people give socially acceptable rather than honest answers, but there's no evidence voters were lying about preferences rather than being excluded entirely. Option C (directionality problem) refers to uncertainty about cause-and-effect relationships in correlational research, which isn't relevant to a straightforward polling scenario where researchers are simply measuring existing voter preferences. The key distinction is that sampling bias affects who gets included in your study, while the other options affect how included participants respond. Since the poll's methodology systematically excluded entire groups of voters, the fundamental problem was with sample representativeness. Remember: When research results don't match reality, first ask whether the sample actually represented the target population. Sampling problems often explain why studies fail to generalize to real-world outcomes.

Question 6

A researcher measures conscientiousness and the number of job promotions in 100 young adults at age 25. The researcher then measures job promotions again for the same group at age 35. They find that conscientiousness at age 25 is positively correlated with the total number of promotions received by age 35. What is the primary advantage of this longitudinal correlational design over a cross-sectional design?

  1. It eliminates the possibility of a third variable, such as intelligence, explaining the relationship.
  2. It establishes the temporal precedence of conscientiousness, strengthening the case for a potential causal link. (correct answer)
  3. It is less susceptible to attrition, ensuring the sample remains representative of the general population over time.
  4. It definitively proves that higher conscientiousness is the direct cause of greater career success.
Explanation: One of the criteria for inferring causality is temporal precedence, meaning the cause must come before the effect. A cross-sectional study measures both variables at the same time, making it impossible to know which came first. This longitudinal design measures the predictor (conscientiousness) long before the final outcome (promotions at 35), establishing temporal precedence. This addresses the directionality problem and strengthens a potential causal argument, though it does not prove causation (D) or eliminate third variables (A). Longitudinal designs are notoriously susceptible to attrition (C).

Question 7

A developmental psychologist finds a significant positive correlation between the number of books in a child's home and their vocabulary size. The psychologist wishes to conclude that having more books at home causes children to develop larger vocabularies. Which of the following represents the most critical challenge to this causal inference?

  1. The correlation might be spurious because parents who buy many books may also be more educated and spend more time reading to their children. (correct answer)
  2. The directionality of the relationship is unclear, as children with larger vocabularies might actively seek out and request more books from their parents.
  3. The sample of children may not be representative of the entire population, which limits the generalizability of the reported findings.
  4. The measurement of 'vocabulary size' could be unreliable, which would introduce systematic error into the calculated correlation coefficient.
Explanation: The most critical challenge to the causal claim is the third variable problem. Option A describes this perfectly: a third variable (parental education/behavior) is likely influencing both the number of books in the home and the child's vocabulary size. While B (directionality) is a possible issue in correlational studies, the influence of parents on young children is a more prominent and likely confound in this specific scenario. C and D describe general research limitations (generalizability and reliability) but do not address the core flaw in the specific causal inference being made.

Question 8

A study finds a negative correlation between an individual's average daily screen time and their self-reported life satisfaction. The researchers also find that screen time is positively correlated with symptoms of depression, and that depression is negatively correlated with life satisfaction.

Based on these findings, what is the most plausible and methodologically sound interpretation of the relationship between screen time and life satisfaction?

  1. Increased screen time directly causes a measurable decrease in an individual's overall life satisfaction.
  2. The relationship is likely spurious, and an unmeasured third variable, such as socioeconomic status, causes both.
  3. The relationship may be mediated by depression, where screen time contributes to depression, which in turn reduces life satisfaction. (correct answer)
  4. The use of self-report measures for all variables makes the correlations unreliable and therefore meaningless.
Explanation: This question requires synthesizing multiple correlational findings. A causal claim (A) cannot be made from correlational data. While a third variable (B) is always possible, the data provided points to a specific pathway. Option C describes mediation, a concept where the relationship between two variables is explained by a third variable. The given correlations (screen time -> depression -> lower life satisfaction) fit this model perfectly. While self-report measures have limits (D), this doesn't render the findings meaningless; it's a limitation, not an interpretation of the pattern.

Question 9

Dr. Evans believes that boys are more physically aggressive than girls. He conducts a naturalistic observation on a preschool playground, recording instances of hitting and pushing. He is the sole observer. A colleague notes that Dr. Evans's results show a much larger gender difference than studies that use multiple observers who are unaware of the study's hypothesis. Dr. Evans's findings may have been compromised by which of the following?

  1. Observer bias (correct answer)
  2. The Hawthorne effect
  3. Social desirability bias
  4. Sampling bias
Explanation: When you encounter research methodology questions, focus on identifying what could systematically distort the data collection process. This question tests your understanding of different types of bias and confounding factors in psychological research. Dr. Evans's study shows classic signs of observer bias. Since he believes boys are more aggressive and is the sole observer who knows the hypothesis, he's likely unconsciously noticing, recording, or interpreting ambiguous behaviors differently for boys versus girls. The key clue is that studies using multiple observers who don't know the hypothesis show much smaller gender differences—this suggests Dr. Evans's expectations influenced his observations. Looking at the wrong answers: (B) The Hawthorne effect occurs when participants change their behavior because they know they're being observed, but there's no indication the children knew they were part of a study. (C) Social desirability bias happens when participants alter their responses to appear more favorable, which doesn't apply to naturalistic observation of young children who aren't reporting anything. (D) Sampling bias involves problems with how participants are selected for the study, but the issue here is with data collection, not participant selection. The comparison to studies with "blind" observers (who don't know the hypothesis) is the critical detail that points to observer bias rather than other methodological problems. Study tip: When you see research questions mentioning that the researcher has strong expectations and is the sole data collector, immediately consider observer bias. Multiple blind observers are a key control for this problem.

Question 10

A person believes that they always have bad luck on Friday the 13th. They vividly remember spilling coffee on their shirt and missing a bus on a past Friday the 13th, but they do not take note of the many Friday the 13ths that have passed without incident. This person's belief is most likely being maintained by:

  1. the third variable problem.
  2. a negative correlation.
  3. an illusory correlation. (correct answer)
  4. the Hawthorne effect.
Explanation: An illusory correlation is the perception of a relationship between two variables when none actually exists. This cognitive bias is often fueled by confirmation bias, where we pay special attention to and remember instances that confirm our beliefs (bad luck on Friday the 13th) while ignoring disconfirming evidence (uneventful Friday the 13ths). This perfectly describes the scenario. The third variable problem (A) and negative correlation (B) are statistical concepts not relevant here, and the Hawthorne effect (D) relates to being observed.

Question 11

A researcher surveys people on diet and wellness. One question asks for the number of vegetable servings consumed daily, and another asks for a self-rating of overall health. The researcher finds a positive correlation but is concerned that more health-conscious individuals might be more likely to both eat vegetables and report being healthy. This concern exemplifies the  . A separate concern, that people might overstate their vegetable intake to sound healthy, exemplifies the  .

  1. third variable problem; social desirability bias (correct answer)
  2. directionality problem; third variable problem
  3. social desirability bias; wording effect
  4. sampling bias; observer bias
Explanation: When evaluating correlational research, you need to distinguish between different types of validity threats that can compromise your ability to draw meaningful conclusions from the data. The first concern describes a third variable problem - when an unmeasured variable (health consciousness) might be causing both measured variables (vegetable consumption and health ratings) to correlate. Health-conscious people naturally both eat more vegetables AND rate themselves as healthier, creating a spurious correlation that doesn't reflect a direct causal relationship between vegetables and health. The second concern illustrates social desirability bias - when participants alter their responses to appear more favorable or socially acceptable. People might inflate their vegetable intake because they know it's "the right answer" for healthy living. Looking at the wrong answers: Choice B incorrectly identifies the first issue as a directionality problem, which would involve uncertainty about whether vegetables cause health or health causes vegetable consumption - not the issue here. Choice C reverses the concepts entirely. Choice D introduces sampling bias (problems with who's selected for the study) and observer bias (researcher influence on data collection), neither of which matches the described concerns. Study tip: Remember that third variable problems involve hidden causes affecting both measured variables, while social desirability bias involves participants consciously or unconsciously modifying responses to look good. In correlational studies, always ask yourself: "What else could explain this relationship?" and "Might people be answering dishonestly?"

Question 12

A primatologist spends two years living with a specific troop of chimpanzees in a remote national park, carefully documenting their social behaviors. Her findings provide an unprecedented, rich account of this troop's life. A primary limitation of this type of in-depth naturalistic observation is that:

  1. the detailed findings from this single troop may not be generalizable to other chimpanzee troops. (correct answer)
  2. the researcher's prolonged presence may have altered the chimpanzees' natural behavior over time.
  3. it is impossible for the researcher to remain objective, so observer bias is guaranteed to invalidate the data.
  4. the qualitative nature of the data is inherently less scientific than quantitative experimental data.
Explanation: When you encounter questions about research methods, focus on the fundamental trade-offs between different study designs. Naturalistic observation offers rich, authentic data but comes with inherent limitations regarding scope and application. The correct answer is A because this study exemplifies a classic limitation of single-case naturalistic observation: limited generalizability. While the researcher gathered incredibly detailed data about one specific troop, these findings may reflect unique characteristics of that particular group, their specific environment, or local conditions. Without studying multiple troops across different locations and contexts, you cannot confidently apply these behavioral patterns to chimpanzees generally. This is a sample size and representativeness issue—one case, no matter how thoroughly studied, cannot represent an entire species. Answer B incorrectly assumes researcher presence automatically alters behavior significantly. While this can happen, many naturalistic studies successfully minimize this through careful methodology, and it's not the primary limitation described here. Answer C overstates the observer bias problem—while bias is always a concern, skilled researchers use various techniques to maintain objectivity, and bias doesn't automatically "invalidate" data. Answer D reflects a misconception that qualitative data is inherently unscientific. Both qualitative and quantitative approaches have scientific value; the issue isn't the type of data but the scope of the study. Remember: on psychology research questions, distinguish between methodological concerns that can be managed (like bias or researcher effects) versus fundamental structural limitations (like generalizability from small samples). The latter are typically more significant constraints.

Question 13

A school psychologist wants to determine if a new anti-bullying program causes a reduction in aggressive incidents. Which of the following non-experimental designs represents the most significant compromise in trying to establish this causal link?

  1. A pre-post study where incidents are counted for one month before and one month after the program is introduced in one school.
  2. A naturalistic observation comparing playground behavior at a school with the program to a similar school without it.
  3. A series of in-depth case studies on students identified as bullies, tracking their behavior after they participate in the program.
  4. A correlational study using national data to find the relationship between school funding for such programs and rates of bullying. (correct answer)
Explanation: When evaluating research designs for establishing causation, you need to consider how well each design controls for confounding variables and allows for valid causal inferences. The key question here is which design creates the most significant compromise in establishing that the anti-bullying program actually causes reduced aggression. Option D represents the most significant compromise because correlational studies using broad national data cannot establish causation at all—they can only show relationships. This design suffers from numerous confounding variables (school size, demographics, other programs, reporting differences) and lacks the specificity needed to isolate the program's effects. The correlation between funding and bullying rates could be explained by countless other factors. Option A, while lacking a control group, at least measures the same population before and after the intervention, providing some basis for causal inference. Option B compares similar schools with and without the program, offering a quasi-experimental control condition that's stronger than pure correlation. Option C uses detailed case studies that can track individual changes over time, providing rich qualitative evidence of program effects. Each of these designs (A, B, C) has limitations compared to a true randomized controlled trial, but they maintain some ability to suggest causal relationships. Option D abandons this entirely by using correlational data that's too removed from the actual intervention to support causal claims. Remember: correlational designs are the weakest for establishing causation, especially when using broad aggregate data rather than studying specific interventions directly.

Question 14

Dr. Evans believes that boys are more physically aggressive than girls. He conducts a naturalistic observation on a preschool playground, recording instances of hitting and pushing. He is the sole observer. A colleague notes that Dr. Evans's results show a much larger gender difference than studies that use multiple observers who are unaware of the study's hypothesis. Dr. Evans's findings may have been compromised by which of the following?

  1. Observer bias (correct answer)
  2. The Hawthorne effect
  3. Social desirability bias
  4. Sampling bias
Explanation: When you encounter research methodology questions, focus on identifying what could systematically distort the data collection process. This question tests your understanding of different types of bias and confounding factors in psychological research. Dr. Evans's study shows classic signs of observer bias. Since he believes boys are more aggressive and is the sole observer who knows the hypothesis, he's likely unconsciously noticing, recording, or interpreting ambiguous behaviors differently for boys versus girls. The key clue is that studies using multiple observers who don't know the hypothesis show much smaller gender differences—this suggests Dr. Evans's expectations influenced his observations. Looking at the wrong answers: (B) The Hawthorne effect occurs when participants change their behavior because they know they're being observed, but there's no indication the children knew they were part of a study. (C) Social desirability bias happens when participants alter their responses to appear more favorable, which doesn't apply to naturalistic observation of young children who aren't reporting anything. (D) Sampling bias involves problems with how participants are selected for the study, but the issue here is with data collection, not participant selection. The comparison to studies with "blind" observers (who don't know the hypothesis) is the critical detail that points to observer bias rather than other methodological problems. Study tip: When you see research questions mentioning that the researcher has strong expectations and is the sole data collector, immediately consider observer bias. Multiple blind observers are a key control for this problem.

Question 15

A developmental psychologist finds a significant positive correlation between the number of books in a child's home and their vocabulary size. The psychologist wishes to conclude that having more books at home causes children to develop larger vocabularies. Which of the following represents the most critical challenge to this causal inference?

  1. The correlation might be spurious because parents who buy many books may also be more educated and spend more time reading to their children. (correct answer)
  2. The directionality of the relationship is unclear, as children with larger vocabularies might actively seek out and request more books from their parents.
  3. The sample of children may not be representative of the entire population, which limits the generalizability of the reported findings.
  4. The measurement of 'vocabulary size' could be unreliable, which would introduce systematic error into the calculated correlation coefficient.
Explanation: The most critical challenge to the causal claim is the third variable problem. Option A describes this perfectly: a third variable (parental education/behavior) is likely influencing both the number of books in the home and the child's vocabulary size. While B (directionality) is a possible issue in correlational studies, the influence of parents on young children is a more prominent and likely confound in this specific scenario. C and D describe general research limitations (generalizability and reliability) but do not address the core flaw in the specific causal inference being made.

Question 16

A public health researcher is interested in the relationship between lifelong smoking habits and the incidence of a rare form of lung cancer. An experimental design where participants are randomly assigned to 'smoking' and 'non-smoking' groups is not ethically feasible. Which non-experimental design would be most appropriate for this research question, and what is its primary strength in this context?

  1. Naturalistic observation, because it provides high ecological validity by observing smokers in their own environment.
  2. A survey, because it can quickly gather self-report data on smoking habits from a very large, representative sample.
  3. A correlational study, because it allows for the examination of relationships between variables that cannot be ethically manipulated. (correct answer)
  4. A case study, because it would provide in-depth, rich information about a single individual suffering from the rare cancer.
Explanation: The most appropriate design is a correlational study (often a retrospective or prospective cohort study in epidemiology). Its key strength in this context is that it allows researchers to investigate relationships between variables, like smoking and cancer, when it would be unethical or impossible to manipulate the independent variable (smoking). While a survey (B) might be used to collect data for the correlational study, the core design is correlational, and its ethical feasibility is the key strength. Naturalistic observation (A) would not be effective for linking behavior to a long-term health outcome, and a case study (D) could not establish a relationship across a population.

Question 17

A person believes that they always have bad luck on Friday the 13th. They vividly remember spilling coffee on their shirt and missing a bus on a past Friday the 13th, but they do not take note of the many Friday the 13ths that have passed without incident. This person's belief is most likely being maintained by:

  1. the third variable problem.
  2. a negative correlation.
  3. an illusory correlation. (correct answer)
  4. the Hawthorne effect.
Explanation: An illusory correlation is the perception of a relationship between two variables when none actually exists. This cognitive bias is often fueled by confirmation bias, where we pay special attention to and remember instances that confirm our beliefs (bad luck on Friday the 13th) while ignoring disconfirming evidence (uneventful Friday the 13ths). This perfectly describes the scenario. The third variable problem (A) and negative correlation (B) are statistical concepts not relevant here, and the Hawthorne effect (D) relates to being observed.

Question 18

A researcher surveys people on diet and wellness. One question asks for the number of vegetable servings consumed daily, and another asks for a self-rating of overall health. The researcher finds a positive correlation but is concerned that more health-conscious individuals might be more likely to both eat vegetables and report being healthy. This concern exemplifies the  . A separate concern, that people might overstate their vegetable intake to sound healthy, exemplifies the  .

  1. third variable problem; social desirability bias (correct answer)
  2. directionality problem; third variable problem
  3. social desirability bias; wording effect
  4. sampling bias; observer bias
Explanation: When evaluating correlational research, you need to distinguish between different types of validity threats that can compromise your ability to draw meaningful conclusions from the data. The first concern describes a third variable problem - when an unmeasured variable (health consciousness) might be causing both measured variables (vegetable consumption and health ratings) to correlate. Health-conscious people naturally both eat more vegetables AND rate themselves as healthier, creating a spurious correlation that doesn't reflect a direct causal relationship between vegetables and health. The second concern illustrates social desirability bias - when participants alter their responses to appear more favorable or socially acceptable. People might inflate their vegetable intake because they know it's "the right answer" for healthy living. Looking at the wrong answers: Choice B incorrectly identifies the first issue as a directionality problem, which would involve uncertainty about whether vegetables cause health or health causes vegetable consumption - not the issue here. Choice C reverses the concepts entirely. Choice D introduces sampling bias (problems with who's selected for the study) and observer bias (researcher influence on data collection), neither of which matches the described concerns. Study tip: Remember that third variable problems involve hidden causes affecting both measured variables, while social desirability bias involves participants consciously or unconsciously modifying responses to look good. In correlational studies, always ask yourself: "What else could explain this relationship?" and "Might people be answering dishonestly?"

Question 19

A primatologist spends two years living with a specific troop of chimpanzees in a remote national park, carefully documenting their social behaviors. Her findings provide an unprecedented, rich account of this troop's life. A primary limitation of this type of in-depth naturalistic observation is that:

  1. the detailed findings from this single troop may not be generalizable to other chimpanzee troops. (correct answer)
  2. the researcher's prolonged presence may have altered the chimpanzees' natural behavior over time.
  3. it is impossible for the researcher to remain objective, so observer bias is guaranteed to invalidate the data.
  4. the qualitative nature of the data is inherently less scientific than quantitative experimental data.
Explanation: When you encounter questions about research methods, focus on the fundamental trade-offs between different study designs. Naturalistic observation offers rich, authentic data but comes with inherent limitations regarding scope and application. The correct answer is A because this study exemplifies a classic limitation of single-case naturalistic observation: limited generalizability. While the researcher gathered incredibly detailed data about one specific troop, these findings may reflect unique characteristics of that particular group, their specific environment, or local conditions. Without studying multiple troops across different locations and contexts, you cannot confidently apply these behavioral patterns to chimpanzees generally. This is a sample size and representativeness issue—one case, no matter how thoroughly studied, cannot represent an entire species. Answer B incorrectly assumes researcher presence automatically alters behavior significantly. While this can happen, many naturalistic studies successfully minimize this through careful methodology, and it's not the primary limitation described here. Answer C overstates the observer bias problem—while bias is always a concern, skilled researchers use various techniques to maintain objectivity, and bias doesn't automatically "invalidate" data. Answer D reflects a misconception that qualitative data is inherently unscientific. Both qualitative and quantitative approaches have scientific value; the issue isn't the type of data but the scope of the study. Remember: on psychology research questions, distinguish between methodological concerns that can be managed (like bias or researcher effects) versus fundamental structural limitations (like generalizability from small samples). The latter are typically more significant constraints.

Question 20

A political polling organization attempts to predict a mayoral election outcome by conducting a survey. They draw their sample from publicly available residential landline phone directories. The poll's prediction differs significantly from the actual election results. The poll's inaccuracy is most likely a consequence of which specific limitation?

  1. Wording effects, because the questions may have been phrased in a way that biased the responses of participants.
  2. Social desirability bias, because respondents may have been untruthful about their preferred candidate.
  3. The directionality problem, because it is unclear if voter preference influences polling response or vice-versa.
  4. Sampling bias, because the sample excluded voters who only use cell phones or have unlisted numbers. (correct answer)
Explanation: When evaluating research validity, you need to distinguish between different types of methodological problems. This question tests your understanding of sampling bias versus other research limitations. The correct answer is D because the polling method created a systematic exclusion of certain voter groups. By only using residential landline directories, the sample missed people who rely solely on cell phones (often younger voters) and those with unlisted numbers (who may have different demographic characteristics). This sampling bias means the sample wasn't representative of the actual voting population, leading to inaccurate predictions. Option A (wording effects) would cause systematic bias in how people respond to questions, but the question doesn't indicate problematic phrasing was involved. Option B (social desirability bias) occurs when people give socially acceptable rather than honest answers, but there's no evidence voters were lying about preferences rather than being excluded entirely. Option C (directionality problem) refers to uncertainty about cause-and-effect relationships in correlational research, which isn't relevant to a straightforward polling scenario where researchers are simply measuring existing voter preferences. The key distinction is that sampling bias affects who gets included in your study, while the other options affect how included participants respond. Since the poll's methodology systematically excluded entire groups of voters, the fundamental problem was with sample representativeness. Remember: When research results don't match reality, first ask whether the sample actually represented the target population. Sampling problems often explain why studies fail to generalize to real-world outcomes.