UGC NET Questions (Paper – 1)

Cluster sampling involves dividing the population into natural groups, or clusters, such as schools, villages or classes, and then randomly selecting some of these clusters for inclusion in the sample. All or many members within chosen clusters are then studied. This method is often used when a complete list of individuals is difficult to obtain but a list of groups is available. Since the stem describes selecting intact groups like schools as sampling units, cluster sampling is the correct term.

Option A:
Simple random sampling selects individual units from the entire population so that each has an equal chance of inclusion, without grouping them into clusters. It does not specifically use intact groups as the units of selection, so it does not match the situation in the stem.

Option B:
Stratified random sampling first divides the population into homogeneous strata based on characteristics such as gender or region and then draws random samples from each stratum. The primary aim is proportional representation of strata, not sampling intact groups as units. Therefore, stratified random sampling is not the best answer here.

Option C:
Cluster sampling is particularly useful when the population is geographically dispersed, because studying selected clusters reduces travel and administrative costs. However, it may increase sampling error compared to simple random sampling. The defining feature of using intact groups matches the description in the question.

Option D:
Quota sampling is a non-probability technique in which researchers fill predetermined quotas for subgroups using convenience procedures, not random selection of clusters. It does not require intact groups such as schools to be the sampling units, so quota is not appropriate.

A double-blind design ensures that both participants and the researchers who have contact with them are unaware of which individuals are in the experimental or control group. This reduces expectancy effects, such as participants changing behaviour because they think they are receiving a special treatment, and experimenter bias, where researchers unintentionally influence outcomes. By keeping group assignment concealed from both parties, the design enhances the credibility of observed differences. Therefore, the arrangement described in the stem is correctly called double-blind.

Option A:
Single-blind designs keep group assignment hidden from participants but not from researchers, so experimenter expectations can still influence data collection or interpretation. This makes single-blind less effective than double-blind in controlling expectancy effects, so it does not fully match the stem.

Option B:
Open-label studies are those in which both participants and researchers know who receives the treatment, making them vulnerable to numerous biases. They are not designed to control expectancy effects and therefore are not an appropriate completion.

Option C:
Option C, double-blind, is widely used in clinical trials and psychological experiments to address both participant and experimenter expectations simultaneously. This dual masking corresponds exactly to the description in the question, making it the correct option.

Option D:
Matched-pairs designs pair participants based on similarity in key characteristics before assigning them to different conditions but do not inherently prevent either party from knowing group assignments. Thus, matched-pairs is not the right answer here.

The population in research is the complete set of individuals, events or objects that share certain characteristics and about which the researcher wants to draw conclusions. It forms the universe from which the sample is selected. When findings from the sample are generalised, they are said to apply to this population. Because the stem describes the entire group to which results are to be generalised, the correct term is population.

Option A:
A sample is a subset of the population selected for actual observation or measurement. While inferences are drawn from the sample, the broader group that these inferences target is the population. Since the question explicitly refers to the entire group, not the subset, sample is not the correct choice.

Option B:
An element is a single member of the population, such as one individual respondent or one school. It does not refer to the whole group to which the researcher wishes to generalise. Therefore, element cannot complete the stem properly.

Option C:
A stratum is a homogeneous subgroup of the population created when using stratified sampling. Each stratum contains members who share certain characteristics, but it is only a part of the population, not the entire group. Consequently, stratum is not the right answer.

Option D:
Population encompasses all units that meet the specified criteria, whether they are people, institutions or events. Identifying the population clearly is crucial for designing sampling strategies and interpreting generalisations. This broad target group is exactly what the stem refers to, so population is the appropriate completion.

Stratified random sampling involves dividing the population into relatively homogeneous strata based on characteristics such as gender, region or discipline and then drawing random samples from each stratum. This ensures that important subgroups are adequately represented in the final sample. It can increase the precision of estimates, especially when subgroup differences are substantial. Because the stem mentions dividing the population into homogeneous subgroups and sampling from each, it describes stratified random sampling.

Option A:
Stratified random sampling uses random selection within each stratum, preserving probabilistic principles while controlling subgroup representation. This approach leads to a sample that mirrors the composition of the population with respect to chosen stratification variables. These features align exactly with the process outlined in the stem, making stratified random the correct answer.

Option B:
Simple random sampling selects units from the population without any prior subdivision, giving each element an equal chance of being chosen, but it does not guarantee representation of specific subgroups. Since the question specifies dividing the population into subgroups first, simple random is not the best match.

Option C:
Systematic sampling selects every kth element from an ordered list after a random start, without necessarily dividing the population into strata. Although it is a probability method, it does not follow the subgroup-based approach described in the stem. Therefore, systematic is not appropriate here.

Option D:
Cluster sampling divides the population into clusters, often based on natural groupings such as schools or villages, and then selects some clusters, usually sampling all or many elements within chosen clusters. Clusters are not necessarily homogeneous, and the method focuses on groups rather than ensuring representation from all subgroups. Thus, cluster sampling does not fit the description given.

A sampling frame is a practical list or representation of all units in the population that can potentially be selected for the sample, such as a roster of students or a registry of schools. It operationalises the population for sampling purposes. The quality of the sampling frame strongly affects the representativeness of the sample. Because the stem describes a complete list of sampling units from which the sample is drawn, sampling frame is the correct term.

Option A:
Population denotes the entire set of individuals or units to which the researcher wishes to generalise findings, but it may exist conceptually without a concrete list. A sampling frame is a specific listing used to select sample elements. Therefore, population does not precisely match the stem’s description.

Option B:
A sample is the subset of units actually selected from the sampling frame for study, not the list from which they are chosen. The stem focuses on the list itself, so sample is not the right completion.

Option C:
Sampling frames are crucial for probability sampling, as they determine whether every population element has a known chance of selection. Incomplete or biased frames can lead to coverage error. This role corresponds exactly to the description in the question, confirming sampling frame as the appropriate answer.

Option D:
Cluster refers to naturally occurring groupings within the population, such as schools or villages, which may be sampled in cluster sampling designs. It is not the same as the comprehensive list of units used in selection. Hence, cluster is not the correct term here.

Randomisation is the process of assigning participants to experimental and control groups using random mechanisms, such as random number tables or computer-generated sequences. This practice helps ensure that groups are equivalent on both known and unknown variables at the start of the experiment. By reducing systematic differences between groups, randomisation strengthens internal validity and makes it more likely that observed effects are due to the treatment. Hence, the procedure described in the stem is correctly called randomisation.

Option A:
Stratification involves dividing a population into homogeneous subgroups and can be used before sampling or randomisation, but it does not by itself eliminate selection bias in group assignment. It is more related to sampling than to within-experiment group allocation, so it is not the best answer.

Option B:
Matching pairs participants on certain characteristics such as age or ability before assigning them to groups, which can improve equivalence on those specific variables, but it is not purely random. It cannot control for all unmeasured variables, so it differs from the chance-based process emphasised in the stem.

Option C:
Option C, randomisation, uses chance to distribute both measured and unmeasured characteristics across groups, reducing the risk that pre-existing differences, rather than the treatment, explain outcomes. This aligns exactly with the purpose stated in the question.

Option D:
Standardisation refers to keeping procedures, instructions and conditions uniform across participants to reduce procedural variation. While important for internal validity, it does not address selection bias in the same way randomisation does.

Primary data are original information gathered first-hand by the researcher through methods such as surveys, experiments, observations or interviews. They are collected specifically to address the objectives of the current study, rather than being reused from previous investigations. Because they originate at the source in direct contact with respondents or phenomena, they are called primary. The stem clearly describes such directly collected data, so primary is the correct term.

Option A:
Secondary data are information that already exist, having been collected earlier by other researchers, institutions or agencies for different purposes. Examples include census reports, published statistics and previous research datasets. Since the stem emphasises data collected directly by the researcher for a specific current study, secondary data do not fit.

Option B:
Derived data might refer to values computed from existing data, such as indices or ratios, rather than raw observations collected in the field. Although derived data can be based on primary data, the stem focuses on original collection rather than on computations, so derived is not accurate here.

Option C:
Primary data are tailored to the research questions and allow control over how variables are defined and measured. They can be more time-consuming and costly to collect but often provide better alignment with the study’s objectives. For these reasons, the type of data described in the stem is correctly labelled primary.

Option D:
Standardised data could suggest information measured using uniform procedures or scales, regardless of whether they are primary or secondary. It is not a standard term for classifying data sources according to whether they are directly collected. Thus, standardised data is not the correct completion.

Longitudinal design involves collecting data from the same participants at two or more points in time, sometimes spanning years, in order to track developmental trends or changes in behaviours and attitudes. This design is particularly valuable for understanding trajectories and causal processes that unfold over time. It can be prospective, following participants into the future, or retrospective, using historical records. Because the stem refers to repeatedly studying the same individuals or groups over an extended period to observe changes, longitudinal design is the correct term.

Option A:
Cross-sectional design gathers data from different individuals at a single point in time, comparing groups such as age cohorts, but it cannot directly reveal within-person change over time. Therefore, cross-sectional design does not fit the longitudinal focus described in the stem.

Option B:
Case study design examines a bounded case such as an individual, institution or programme in depth, often at one or a few time points. While some case studies can be longitudinal, the term case study alone does not specifically denote repeated measurements over an extended period, so it is not the best answer.

Option C:
Longitudinal designs can be demanding in terms of time, cost and participant retention, but they provide powerful insights into stability, change and developmental sequences that are not accessible through one-time measurements. This central feature of observing change over time aligns exactly with the question.

Option D:
Experimental design is characterised by manipulation of independent variables and control over extraneous variables to test causal hypotheses, and may be either cross-sectional or longitudinal. The stem, however, highlights repeated observations over time rather than manipulation, so experimental design is not the correct completion.

Probability sampling is defined by the use of random selection mechanisms that give each member of the population a known, non-zero chance of inclusion. This property allows researchers to estimate sampling error and to generalise findings from the sample to the population with quantifiable confidence. Techniques such as simple random, stratified and cluster sampling fall under this category. Because the stem explicitly mentions a known non-zero chance of selection for every element, it is describing probability sampling.

Option A:
Quota sampling is a non-probability method where the researcher fills pre-specified quotas for certain subgroups, often using convenience within each quota. Individual elements do not have known chances of selection, and probability theory cannot be applied to estimate sampling error. Thus, quota sampling does not satisfy the conditions stated in the stem.

Option B:
Purposive sampling involves selecting cases that are judged to be information-rich or particularly relevant to the research question, based on the researcher’s judgement. It does not assign known probabilities of selection to all population members, so it is not probability sampling. Therefore, purposive sampling cannot be the correct option.

Option C:
Convenience sampling selects units that are easiest to access, such as volunteers or people who are readily available. This method ignores the requirement that every member of the population have a known non-zero chance of selection, and it often yields biased samples. Consequently, convenience sampling does not meet the criteria in the question.

Option D:
Probability sampling uses objective randomisation procedures, such as random number tables or computer-generated random lists, to ensure fairness in selection. Because each element’s chance of being chosen is known, researchers can make statistically grounded inferences to the population. This matches exactly what the stem describes, making probability sampling the correct answer.

Documentary research relies heavily on existing documents and records rather than collecting primary data directly from respondents. It includes the systematic analysis of sources like government statistics, institutional reports and archival materials. The researcher interprets these documents to answer research questions. Since the stem refers to studies based on existing records such as census data, documentary research is the correct term.

Option A:
Field research involves going directly into natural settings such as schools, communities or organisations to collect primary data through observation, interviews or surveys. It is not primarily based on analysing existing official documents. Therefore, field research does not match the situation described in the question.

Option B:
Documentary research systematically selects, evaluates and interprets written or recorded materials as data. It is especially useful when historical trends or large-scale patterns must be understood without new field data collection. Because the stem focuses on using census data and institutional reports, documentary is the best completion.

Option C:
Experimental research manipulates one or more independent variables under controlled conditions to observe their effect on dependent variables. It typically requires planning interventions and collecting new data rather than relying solely on existing documents. Hence, experimental research is not the appropriate answer.

Option D:
Action research is practitioner-oriented and seeks to solve immediate problems in a local context through cycles of planning, acting, observing and reflecting. Although it may consult documents, it is not defined by primary reliance on official records. Thus, action research does not fit the description in the stem.

A sample is a smaller group of units selected from a larger population so that information collected from it can be used to infer characteristics of the whole. Sampling makes research feasible when studying every member of the population is impractical or impossible. The quality of the sample strongly affects the accuracy of conclusions drawn from the study. Since the stem speaks of a subset drawn from the target population for making inferences, the correct term is sample.

Option A:
Population refers to the entire group of individuals, objects or events that share specified characteristics and about which the researcher wants to draw conclusions. It is not a subset but the full set of interest. Because the stem clearly mentions a subset drawn from the population, population cannot complete the statement.

Option B:
A sample is selected using some sampling design so that it reflects the key characteristics of the population as closely as possible. Data are collected from the sample, and statistical techniques are then used to estimate population parameters. This use of a subset for inference corresponds exactly to the description in the question, confirming sample as the correct option.

Option C:
Parameter is a numerical characteristic of a population, such as the true mean or proportion. It is not itself a group of units but a value that describes the population. The stem is looking for the name of the subset of units, so parameter is not appropriate.

Option D:
Universe is another term sometimes used interchangeably with population to refer to the total collection of elements under study. It does not denote a subset selected for research. Hence, universe cannot be the right completion of the stem.

The Delphi technique gathers judgments from experts in multiple rounds where responses are summarised and fed back anonymously after each round. Experts can revise their views in light of the group feedback, gradually moving toward consensus. It is especially useful for forecasting and policy planning in complex areas. Hence, this structured, multi-round expert consultation is called the Delphi technique.

Option A:
A focus group is a face-to-face group discussion led by a moderator, relying on interaction and immediate conversation. It does not involve anonymous multi-round questionnaires. So it is not the correct term here.

Option B:
A case study is an in-depth analysis of a single case or small set of cases using multiple data sources. It does not primarily aim to obtain consensus among many experts. Therefore, it does not fit the stem.

Option C:
Ethnographic research immerses the researcher in a cultural or social setting to observe behaviours and meanings, not to collect iterative forecasts from experts. Hence, it is not the method described.

Option D:
Option D, the Delphi technique, intentionally avoids group pressure by maintaining anonymity and uses feedback summaries to refine expert judgments. This matches exactly the description in the question, so it is correct.

The pretest–posttest control group design involves randomly assigning participants to at least two groups, administering a pretest to both, applying the treatment only to the experimental group and then giving a post-test to both groups. This structure allows the researcher to compare changes over time while controlling for initial differences between groups. Random assignment enhances internal validity by balancing extraneous variables across groups. Thus, the design described in the stem is known as the pretest–posttest control group design.

Option A:
One-shot case study design exposes a single group to a treatment and then administers a post-test without any pretest or control group. Because it lacks both random assignment and a comparison group, it provides very weak evidence about treatment effects. This design is quite different from the one in the stem, which explicitly mentions both pretests and control groups.

Option B:
Static group comparison design includes an experimental group that receives treatment and a non-equivalent control group that does not, with only post-test observations and no random assignment. Without pretests and randomisation, this design cannot control for initial group differences. Therefore, static group comparison does not match the detailed description in the question.

Option C:
Pretest–posttest control group design combines random assignment, pretesting and post-testing for both experimental and control groups. This arrangement helps isolate the effect of the treatment by comparing changes in the two groups. Since the stem outlines all these components, this option correctly names the design.

Option D:
Single-subject design focuses on repeated measures of a single participant or a small number of participants over time, often using AB or ABA patterns. It does not usually involve random assignment to separate experimental and control groups with group-based pretests and post-tests. Hence, single-subject design is not the appropriate label here.

Interaction of selection and treatment occurs when the characteristics of those selected for the study, such as being volunteers or highly motivated individuals, interact with the treatment in such a way that results may not hold for a broader population. This threatens external validity because the findings may not generalise beyond the specific type of participants used. Recognising and minimising such biases is important when designing experiments. Therefore, the threat described in the stem is the interaction of selection and treatment.

Option A:
Selection refers to how participants enter the study and the ways in which they may differ systematically from the target population. When these differences influence how they respond to treatment, generalisation becomes problematic, capturing the idea in the stem and making this option correct.

Option B:
Testing as a threat to validity involves effects of taking a pretest on later performance, not differences between volunteers and non-volunteers. It is more about sensitisation than about participant characteristics.

Option C:
History refers to external events occurring between measurements that affect outcomes for all participants, which is different from the differential response of specific selection groups.

Option D:
Instrumentation concerns changes in measurement tools or observers over time, affecting scores independently of the treatment and is unrelated to how volunteers might differ from non-volunteers in responsiveness.

The dependent variable is the outcome or response that researchers observe and measure to determine whether it has changed as a result of the treatment or manipulation. Its values are assumed to depend on the levels of the independent variable. By comparing the dependent variable across experimental conditions, researchers infer whether the treatment has had an effect. Since the stem mentions the variable measured to assess the effect of the treatment, it is defining the dependent variable.

Option A:
A control variable is one that the researcher holds constant or monitors to prevent it from influencing the results. It is not the primary outcome being measured for treatment effects. While control variables are important for internal validity, they are different from the variable described in the stem.

Option B:
The independent variable is the one that the researcher manipulates or varies deliberately to study its impact on another variable. It represents the presumed cause rather than the observed effect. Because the stem refers to the variable that is measured as an outcome, independent variable is not the correct answer.

Option C:
Dependent variable represents the effect or response side of the cause–effect relationship studied in experiments. Examples include test scores, reaction times or attitude ratings after exposure to different treatments. The stem’s focus on measuring the variable to assess treatment effect corresponds exactly to this concept, making dependent variable the right completion.

Option D:
An intervening variable is a hypothetical factor that helps explain how or why an independent variable affects a dependent variable, such as motivation or anxiety. It is not usually the primary variable measured to determine treatment effectiveness. Therefore, intervening variable does not fit the stem.