Manuel B. Garcia

Manuel B. Garcia serves as the Senior Director for Educational Technology and Digital Learning at FEU Institute of Technology, Manila, Philippines. Read More

Contact Info

1607, FEU Tech Building,
P. Paredes St, Sampaloc,
Manila, Philippines
mbgarcia@feutech.edu.ph

Follow Me

The Complete Library

All Research Guides

Browse every published guide in the Researcher's Field Guide, including the complete research journey and supplemental collections, listed alphabetically for quick reference.

Complete Library

Every published guide

Showing 2,551–2,600 of 5,065 guides

5,065 guides
PART 04 · SUBPART 55 · GUIDE 633

Non-Probability Sampling and Population Prevalence

Can a Non-Probability Sample Estimate Population Prevalence?

A non-probability sample can produce an observed proportion, but estimating population prevalence requires a defensible connection between respondents and the target population. Learn when modeling and weighting may support broader estimates, what assumptions they require, and why large samples alone cannot establish representativeness.

PART 04 · SUBPART 55 · GUIDE 632

Choosing a Non-Probability Sampling Method

How Do You Choose the Most Appropriate Non-Probability Sampling Method for Your Study?

Choosing a non-probability sampling method requires matching recruitment decisions to the evidence a study needs. Compare five common methods, understand their distinct purposes, and learn how to justify a sampling strategy without overstating population representativeness.

PART 04 · SUBPART 55 · GUIDE 631

Consecutive vs. Convenience Sampling

When Is Consecutive Sampling Better Than Convenience Sampling?

Consecutive sampling recruits every eligible case encountered during a defined period or sequence, while convenience sampling primarily relies on accessibility. Learn when consecutive recruitment provides a more systematic approach, how to implement it, and why neither method automatically supports population-wide inference.

PART 04 · SUBPART 55 · GUIDE 630

When Quota Sampling Is Defensible

When Is Quota Sampling Defensible?

Quota sampling can help researchers recruit specified numbers of participants from important population categories when probability sampling is impractical. Learn when the approach is defensible, how to establish meaningful quotas, and why matching population proportions does not guarantee representativeness.

PART 04 · SUBPART 55 · GUIDE 629

When Snowball Sampling Is Defensible

When Is Snowball Sampling Defensible?

Snowball sampling can help researchers identify eligible participants who are difficult to locate through conventional recruitment channels. Learn when referral-based sampling is defensible, how to reduce network-related selection problems, and why ordinary snowball samples cannot automatically support population-level estimates.

PART 04 · SUBPART 55 · GUIDE 628

When Purposive Sampling Is Defensible

When Is Purposive Sampling Defensible?

Purposive sampling can be defensible when participants are deliberately selected for experiences, characteristics, or knowledge relevant to a research question. Learn how to establish meaningful selection criteria, choose suitable cases, and avoid unsupported claims about population representativeness.

PART 04 · SUBPART 55 · GUIDE 626

When Convenience Sampling Is Defensible

When Is Convenience Sampling Defensible?

Convenience sampling can be defensible when accessible participants provide evidence appropriate to a clearly defined research objective. Learn when it is useful for feasibility testing, exploratory research, and bounded populations, and why its limitations must shape the conclusions.

PART 04 · SUBPART 54 · GUIDE 625

Replacing Nonrespondents in Probability Sampling

Can Replacing Nonrespondents Compromise Probability Sampling?

Replacing nonrespondents may appear to be a practical way to achieve the required sample size, but informal substitution can alter selection probabilities and introduce bias. Learn when replacement is problematic, how planned reserve samples differ from convenience substitutes, and what researchers should do when participation falls short.

PART 04 · SUBPART 54 · GUIDE 623

Fixing Sampling Frame Errors

How Do You Handle Duplicates or Outdated Records in a Sampling Frame?

Duplicate and outdated records can distort selection probabilities, exclude eligible population members, or introduce ineligible units into a probability sample. Learn how to audit, clean, and document a sampling frame without compromising the integrity of the selection process.

PART 04 · SUBPART 54 · GUIDE 622

Unequal Selection Probabilities and Weights

How Do Unequal Selection Probabilities Affect Sampling Weights?

When population units have different probabilities of selection, their observations generally cannot contribute equally to population estimates. Learn how to calculate base sampling weights, interpret weighted estimates, and understand the effects of unequal probabilities on precision and statistical inference.

PART 04 · SUBPART 54 · GUIDE 621

When to Oversample Rare Population Groups

When Should Rare Population Groups Be Oversampled?

Rare population groups may contribute too few observations under proportional sampling to support meaningful estimates or comparisons. Learn when deliberate oversampling is justified, how to implement it within a probability design, and what trade-offs researchers must consider.

PART 04 · SUBPART 54 · GUIDE 620

Proportional vs. Disproportionate Allocation

Should Stratified Sampling Use Proportional or Disproportionate Allocation?

Proportional allocation preserves population shares in a stratified sample, while disproportionate allocation can support small-group comparisons or improve precision under particular conditions. Learn how to calculate both approaches, evaluate their trade-offs, and account for unequal selection probabilities.

PART 04 · SUBPART 54 · GUIDE 619

Choosing Strata for Sampling

How Do You Choose Strata That Improve Sample Representativeness or Precision?

Choosing strata requires more than dividing a population into convenient demographic categories. Learn how to identify stratification variables that support subgroup estimates, potentially reduce sampling variance, and remain practical to implement using reliable population information.

PART 04 · SUBPART 54 · GUIDE 618

Choosing a Probability Sampling Method

How Do You Choose the Most Appropriate Probability Sampling Method for Your Study?

Choosing a probability sampling method requires more than deciding which technique is easiest to implement. Learn how to compare simple random, systematic, stratified, cluster, and multistage sampling according to your research objectives, population structure, sampling frame, statistical precision, and practical constraints.

PART 04 · SUBPART 54 · GUIDE 617

When to Use Multistage Sampling

When Is Multistage Sampling Necessary?

Multistage sampling can make large-scale research feasible when researchers cannot efficiently select individuals directly from the entire population. Learn when successive sampling stages are justified, how to preserve known selection probabilities, and what the design means for statistical inference.

PART 04 · SUBPART 54 · GUIDE 616

When to Use Cluster Sampling

When Is Cluster Sampling Appropriate?

Cluster sampling can make research feasible when population members are distributed across many schools, communities, institutions, or geographical areas. Learn when selecting groups rather than scattered individuals is appropriate, how the design affects statistical precision, and what researchers must consider before using it.

PART 04 · SUBPART 54 · GUIDE 615

When to Use Stratified Sampling

When Is Stratified Sampling Appropriate?

Stratified sampling is useful when population subgroups require deliberate representation or when dividing the population into meaningful strata can improve statistical precision. Understand the conditions, decisions, and practical limitations that determine whether this probability sampling method fits your research.

PART 04 · SUBPART 54 · GUIDE 614

When to Use Systematic Sampling

When Is Systematic Sampling Appropriate?

Systematic sampling selects units at regular intervals after a random starting point. Understand when this probability sampling method is appropriate, how the ordering of the sampling frame affects results, and when another design may provide more defensible estimates.

PART 04 · SUBPART 54 · GUIDE 613

When to Use Simple Random Sampling

When Is Simple Random Sampling Appropriate?

Simple random sampling gives every eligible population unit an equal probability of selection under a defined random design. Learn when this method is suitable, how to implement it using a reliable sampling frame, and when stratified, systematic, or cluster sampling may be more efficient.

PART 04 · SUBPART 53 · GUIDE 612

When to Use a Census Instead of Sampling

When Is Sampling the Entire Population Feasible and Preferable?

Studying every member of a population can be preferable when the population is small, identifiable, and accessible. Learn how to decide whether complete enumeration is feasible, what it achieves statistically, and why a census does not automatically eliminate nonresponse, measurement error, or limitations on generalizability.

PART 04 · SUBPART 53 · GUIDE 611

Sampling Small Population Subgroups

How Do You Choose a Sampling Strategy When Important Subgroups Are Very Small?

Important population subgroups may be too small to appear adequately in ordinary samples, making meaningful comparisons or precise estimates difficult. Learn when to use oversampling, disproportionate stratification, complete enumeration, or specialized estimation methods, and how to avoid confusing subgroup representation with statistical precision.

PART 04 · SUBPART 53 · GUIDE 610

Sampling Hidden and Hard-to-Reach Populations

How Do You Choose a Sampling Strategy for Hidden or Hard-to-Reach Populations?

Hidden and hard-to-reach populations present sampling challenges because their members may be difficult to identify, contact, or recruit through conventional frames. Learn how to select an appropriate strategy, assess network and coverage biases, protect participants, and determine which population claims the resulting evidence can support.

PART 04 · SUBPART 53 · GUIDE 609

Sampling Without a Complete Sampling Frame

How Do You Choose a Sampling Strategy When No Complete Sampling Frame Exists?

A missing or incomplete population list does not automatically make rigorous sampling impossible. Learn how to evaluate frame coverage, construct alternative selection mechanisms, distinguish probability from nonprobability approaches, and make defensible population claims when no complete sampling frame exists.

PART 04 · SUBPART 53 · GUIDE 607

Research Validity With Nonrepresentative Samples

Can a Nonrepresentative Sample Still Answer the Research Question Well?

A nonrepresentative sample does not automatically make research invalid. Its usefulness depends on the research question, selection mechanism, study design, and intended conclusions. Learn when focused or nonprobability samples can provide strong evidence, when they cannot support population estimates, and how to defend their methodological adequacy without overstating generalizability.

PART 04 · SUBPART 53 · GUIDE 606

Does Every Study Need a Representative Sample?

Does Every Research Study Need a Representative Sample?

A representative sample is valuable when researchers need to estimate characteristics of a defined population, but not every study has that objective. Learn why representativeness is not a universal requirement, how sampling expectations differ across research designs, and when a nonrepresentative sample can still support scientifically defensible conclusions.

PART 04 · SUBPART 53 · GUIDE 605

Should Sampling Prioritize Representativeness?

Should Representativeness Be the Main Goal of Your Sampling Strategy?

Representativeness is important for some research questions, particularly those involving population estimates, but it is not the universal objective of sampling. Learn when population representativeness should be prioritized and when causal identification, predictive performance, subgroup precision, or conceptual depth provides a more appropriate basis for selecting participants.

PART 04 · SUBPART 53 · GUIDE 604

Can a Large Sample Still Be Biased?

Can a Sample Be Large but Still Seriously Biased?

A large sample can reduce random uncertainty while leaving systematic bias almost untouched. Learn why thousands or even millions of observations can produce extremely precise answers to the wrong population question.

PART 04 · SUBPART 53 · GUIDE 603

Representative Samples

What Is a Representative Sample, and Does Your Study Actually Need One?

A representative sample is meaningful only in relation to a specified population. Learn what representativeness actually requires, how researchers assess it, and why not every worthwhile study needs a statistically representative sample.

PART 04 · SUBPART 53 · GUIDE 602

Does a Bigger Sample Make Research Better?

Does a Bigger Sample Automatically Make a Study Better?

More participants can improve statistical precision and power, but sample size is only one part of research quality. A large sample cannot automatically repair biased recruitment, poor measurement, confounding, or a weak design.

PART 04 · SUBPART 53 · GUIDE 598

What Defines Probability and Non-Probability Sampling?

What Makes a Sampling Method Probability-Based or Non-Probability-Based?

The difference between probability and non-probability sampling is not whether participants are diverse, whether the sample is large, or whether researchers use statistical analysis. It concerns how units are selected and whether their inclusion probabilities are known. Learn how to classify sampling methods correctly, recognize misleading claims of random selection, and understand the implications for statistical inference.

PART 04 · SUBPART 53 · GUIDE 597

Choosing the Right Research Sampling Method

How to Choose a Sampling Method That Actually Fits Your Study

The appropriate sampling method depends on what your study is trying to learn, not simply which technique is easiest or most familiar. Learn how to select a sampling strategy that matches population estimation, causal inference, prediction, or qualitative inquiry while accounting for population coverage, selection bias, feasibility, and generalizability.

PART 04 · SUBPART 52 · GUIDE 596

Preventing Unnecessary Exclusion of Underrepresented Groups

How Do You Prevent Exclusion Criteria from Unnecessarily Excluding Underrepresented Groups?

Exclusion criteria may appear scientifically neutral while disproportionately preventing certain populations from participating in research. Learn how to identify unnecessary restrictions, distinguish eligibility from accessibility barriers, evaluate the consequences for validity and equity, and develop more inclusive recruitment procedures without compromising participant safety.

PART 04 · SUBPART 52 · GUIDE 595

Eligibility Changes and the Target Population

When Does Changing Eligibility Criteria Change the Target Population?

Changing eligibility criteria may correct an operational problem, expand participation, or fundamentally redefine the population a study investigates. Learn how to distinguish these consequences, assess changes to the estimand, and preserve valid inference when eligibility rules are revised.

PART 04 · SUBPART 52 · GUIDE 594

Changing Eligibility Criteria During Slow Recruitment

Should Eligibility Criteria Be Changed if Recruitment Is Slower Than Expected?

Slow recruitment may reveal problems with study feasibility, overly restrictive eligibility criteria, or recruitment procedures. However, changing eligibility rules can alter the study population and intended inference. Learn when modifications are defensible, which alternatives to consider first, and how to implement and report changes without compromising research integrity.

PART 04 · SUBPART 52 · GUIDE 593

Handling Borderline Research Eligibility

How Do You Handle Borderline Eligibility in Research Participant Selection?

Borderline eligibility arises when prospective participants fall near screening thresholds, have conflicting records, or cannot be classified confidently under the study's criteria. Learn how to establish consistent decision rules, manage uncertainty, prevent selective recruitment, and document defensible eligibility decisions.

PART 04 · SUBPART 52 · GUIDE 592

Choosing Research Eligibility Assessment Methods

Should Research Eligibility Be Based on Self-Report, Records, Testing, or Clinician Judgment?

Researchers can determine participant eligibility through self-report, administrative or clinical records, objective testing, and professional judgment. Each method has different strengths, limitations, and implications for bias. Learn how to select and combine eligibility assessment methods that match your research question, population, and ethical requirements.

PART 04 · SUBPART 52 · GUIDE 591

Insufficient Eligibility Criteria and Sample Heterogeneity

Can Too Few Eligibility Criteria Make a Research Sample Too Heterogeneous?

Broad eligibility can improve population coverage, but insufficiently defined criteria may combine participants whose experiences, exposures, or outcomes are not meaningfully comparable. Learn when heterogeneity threatens interpretation, how to distinguish useful diversity from problematic variation, and how to define eligibility without unnecessarily narrowing the population.

PART 04 · SUBPART 52 · GUIDE 590

Excessive Exclusion Criteria and Sample Representativeness

Can Too Many Exclusion Criteria Make a Research Sample Unrealistic?

Exclusion criteria can protect participants and strengthen research design, but accumulating too many restrictions may produce a sample unlike the population researchers intend to understand. Learn how to recognize excessive exclusions, evaluate their cumulative consequences, and preserve meaningful population coverage without compromising scientific or ethical requirements.

PART 04 · SUBPART 52 · GUIDE 589

Confounders and Exclusion Criteria

Should Every Potential Confounder Become an Exclusion Criterion?

Excluding everyone with a potential confounding characteristic may seem like a straightforward way to improve research validity, but excessive restriction can change the population, reduce generalizability, and sometimes introduce new biases. Learn when restriction is justified and when measurement, randomization, stratification, or statistical adjustment provides a better approach.

PART 04 · SUBPART 52 · GUIDE 588

Safety Concerns and Exclusion Criteria

Should Every Safety Concern Become an Exclusion Criterion?

Safety concerns require careful evaluation, but not every risk justifies excluding participants. Learn how to distinguish genuine contraindications from manageable risks, assess alternatives to exclusion, and protect participants without unnecessarily narrowing the research population.

PART 04 · SUBPART 52 · GUIDE 587

Factors Determining Research Exclusion Criteria

What Factors Should Determine Exclusion Criteria in Research?

Exclusion criteria should protect participants and preserve meaningful research inference without unnecessarily removing relevant population groups. Learn which scientific, ethical, and methodological factors justify exclusion, when alternative safeguards are preferable, and how to assess the consequences of restrictive eligibility.

PART 04 · SUBPART 52 · GUIDE 586

Factors Determining Research Inclusion Criteria

What Factors Should Determine Inclusion Criteria in Research?

Inclusion criteria should be determined by more than the characteristics of participants who are easiest to recruit. Learn how the research question, target population, study design, intervention requirements, measurement validity, ethics, and generalizability should inform eligibility decisions.

PART 04 · SUBPART 52 · GUIDE 585

Writing Research-Aligned Inclusion Criteria

How Do You Write Inclusion Criteria That Actually Match the Research Question?

Inclusion criteria should identify the participants or other units necessary to answer your research question, not merely describe who is easiest to recruit. Learn how to translate a target population into clear, operational eligibility rules, avoid unnecessary restrictions, and ensure that participant selection supports the intended inference.