FILD 311: Research Strategies & Validity 3rd Year Midterm Lesson

RESEARCH STRATEGIES

After you have identified a new idea for research, formed a hypothesis, decided how to define and measure your variables, and determined which individuals should participate in the study and how to treat them ethically, the next step is to select a _____ ______

Research strategy

________ _______ is a general approach to research determined by the kind of question that the research study hopes to answer.

Descriptive Research Strategy

The only strategy that focuses on individual variables

Descriptive Research Strategy

This strategy intends to answer questions about the current state of individual variables for a specific group of individuals.

Descriptive Research Strategy

The goal is to obtain a description of specific characteristics of a specific group of individuals.

Descriptive Research Strategy

the ________ ______ _______ is not concerned with relationships between variables but rather with the description of individual variables. The goal of descriptive strategy is to obtain a snapshot (a description) of specific characteristics of a specific group of individuals.

Correlational Research Strategy

One technique for examining the relationship between variables is to observe the two variables as they exist naturally for a set of individuals. That is, simply measure the two variables for each individual.

correlational strategy

the _______ ______ only attempts to describe the relationships (if one exists); it is not trying to explain the relationship.

Experimental Research Strategy

The _______ ______ _______ is intended to answer cause-and-effect questions about the relationship between two variables.

Experimental Research Strategy

To answer this question, a researcher could create two treatment conditions by changing the amount of manipulation.

experimental research strategy

the purpose of the _______ ______ _____ is to explain the relationship by determining the underlying cause.

experimental study

An ______ _____is conducted with rigorous control to help ensure an unambiguous demonstration of a cause-and-effect relationship.

Quasi-Experimental Research Strategy

Although this strategy usually attempts to answer cause-and-effect questions about the relationship between two variables, it can never produce an unambiguous explanation. However, unlike a true experiment a quasi-experiment does not rely on random assignment. Instead, subjects are assigned to groups based on non-random criteria.

quasi-experimental research strategy

The ______-______ ______ _____ uses some of the rigor and control that exist in experiments; however, quasi-experimental studies always contain a flaw that prevents the research from obtaining an absolute cause-and-effect answer.

Quasi-Experimental Research Strategy

For this example, the researcher used preexisting groups and did not control the assignment of individuals to groups. Therefore, there is no way to know whether the people in the treatment program are similar to those in the non treatment program. The two groups could be very different in terms of age, income, motivation, or a variety of other variables.

nonexperimental research strategy

The ________ ______ _____ is intended to demonstrate a relationship between variables, but it does not attempt to explain the relationship.

nonexperimental research strategy

In particular, this strategy does not try to produce cause-and-effect explanations.

Nonexperimental studies

__________ _____ do not use the rigor and control that exist in experiments and in quasi-experimental studies and do not produce cause-and-effect explanations.

Nonexperimental studies

For example, a study may demonstrate that girls have higher verbal skills than boys, but it does not explain why girls' scores are higher.

CATEGORY 1: Strategies that examine individual variables

Descriptive

Purpose: produce a description of individual variables as they exist within a specific group.

Data: a list of scores obtained by measuring each individual in the group being studied.

Descriptive

________

Purpose: produce a description of individual variables as they exist within a specific group.

Data: a list of scores obtained by measuring each individual in the group being studied.

CATEGORY 2: Strategies that examine relationships between variables by measuring two (or more) variables for each participant

Correlational

Purpose: produce a description of the relationship between two variables but do not attempt to explain the relationship.

Data: measure two variables (two scores) for each individual in the group being studied.

Correlational

________

Purpose: produce a description of the relationship between two variables but do not attempt to explain the relationship.

Data: measure two variables (two scores) for each individual in the group being studied.

CATEGORY 3: Strategies that examine relationships between variables by comparing two (or more) groups of scores

Experimental

Purpose: produce a cause-and-effect explanation for the relationship between two variables.

Data: create two treatment conditions by changing the level of one variable. Then measure a second variable for the participants in each condition.

Quasi-Experimental

Purpose: attempt to produce a cause-and-effect explanation but fall short.

Data: measure before/after scores for one group that receives treatment and for a different group that does not receive the treatment.

Nonexperimental

Purpose: produce a description of the relationship between two variables but do not attempt to explain the relationship.

Data: measure scores for two different groups of participants or for one group at two different times.

Experimental

__________

Purpose: produce a cause-and-effect explanation for the relationship between two variables.

Data: create two treatment conditions by changing the level of one variable. Then measure a second variable for the participants in each condition.

Quasi-Experimental

_______________

Purpose: attempt to produce a cause-and-effect explanation but fall short.

Data: measure before/after scores for one group that receives treatment and for a different group that does not receive the treatment.

Research Strategy

The general approach and goals of a research study.

Research Strategy

Usually determined by the kind of question you plan to address and the kind of answer you hope to obtain.

Research Design

It specifies whether the study will involve groups or individual participants will make comparisons within a group or between groups, and how many variables will be included in the study.

Research Procedures

An exact step-by-step description of a specific research study, including a precise determination of:

I. Exactly how the variables will be manipulated, regulated and measured.

II. Exactly how many individuals will be involved,

III. Exactly how the individual participants or subjects will proceed through the course of the study.

PARAMETRIC TESTS

______ ____assume that the data follows a specific distribution, typically a normal distribution. They are used when certain parameters (like mean and variance) of the population are known or can be estimated.

- Assumptions: requires assumptions about the population distribution (e.g., normality) and homogeneity of variance.

- Central Tendency: measures central tendency using the mean.

- Data Type: suitable for continuous data and interval scales.

- Sensitivity to Outliers: more sensitive to outliers, which can significantly affect results.

NON-PARAMETRIC TESTS

____________ ____ do not assume a specific distribution for the data. They are often referred to as "distribution-free" tests and are useful when the assumptions of parametric tests cannot be met.

- Assumptions: make no assumptions about population distributions; suitable for ordinal or nominal data..

- Central Tendency: measures central tendency using the median.

- Data Type: can handle various data types, including ordinal and nominal scales.

- Robustness to Outliers: generally more robust against outliers compared to parametric tests.

parametric tests

If data is normally distributed and meets other assumptions, ______ _____ are preferred due to their higher statistical power.

Parametric tests

Non-parametric tests

________ ____ require larger sample sizes for reliable results. __________ _____ can be more appropriate for smaller samples or when data is skewed.

Non-parametric tests

For ordinal or nominal data, _________ ____ are more suitable as they do not rely on strict distributional assumptions.

EXTERNAL VALIDITY

The extent to which we can generalize the results of a research study to people, settings, times, measures and characteristics other than those used in the study.

1. Generalization from a sample to the general population

2. Generalization from one research study to another

3. Generalization from a research study to a real-world situation

3 Threats to External Validity:

Generalization from a sample to the general population

Most research questions concern a large group of individuals known as a population.

Generalization from one research study to another

As we noted earlier, each research study is a unique event, conducted at a specific time and place using specific procedures with a specific group of individuals.

Generalization from a research study to a real-world situation

Most research is conducted under relatively controlled conditions with individuals who know that they are participating in a research study.

Selection Bias

the sampling procedure favors the selection of some individuals over others.

College Students

evidence is accumulating to suggest that many of the characteristics of ____ _____ limit the ability to generalize the results to other adults.

Volunteer Bias

______ are not perfectly representative of the general population.

Participant Characteristics

when a study uses participants who share similar characteristics. Demographic characteristics such as gender, age, race, ethnic identity, and socioeconomic status can limit the ability to generalize the results.

Cross-species Generalizations

external validity is also in question when research is conducted with nonhumans and presumed to be readily applicable to humans.

Novelty Effect

participating in a research study is a novel, often exciting or anxiety-provoking experience for most individuals. In this novel situation, individuals may perceive and respond differently than they would in the normal, real world.

Multiple Treatment Interference

when individuals are tested in a series of treatment conditions, participation in one condition may have an effect on the participants that carries over into the next treatment and influences their performance or behavior. (ex. fatigue and practice)

Experimenter Characteristics

the results of a study are demonstrated with a specific experimenter conducting the study.

Sensitization

the process of measurement, often called the assessment procedure, can alter participants so that they react differently to treatment.

Generality across response measures

the results of the study may be limited to that specific measurement that the researchers selects and may not generalize to other definitions or other measures.

Time of Measurement

in a research study, the scores for individuals are measured at a specific time after (or during) the treatment. The actual effect of the treatment may decrease or increase with time.

INTERNAL VALIDITY

A research study has ______ _____ if it produces a single, unambiguous explanation for the relationship between two variables.

internal validity

A threat to ______ _____ is any factor that allows for an alternative explanation.

Extraneous Variables

Any variable in a research study other than the specific variables being studied.

Can introduce variability into research findings.

Confounding Variables

An extraneous variable (usually unmonitored) that changes systematically along with the two variables being studied. It provides an alternative explanation for the observed relationship between the two variables and, therefore, is a threat to internal validity.

Confounding Variables

Can obscure true causal relationships, complicating the interpretation of results in psychological studies.

Environmental Variables

General threats to internal validity for all studies

Participant Variables

Threats to internal validity for studies comparing different groups

1. Participant Variable: personal characteristics that can differ from one individual to another.

2. Individual Differences: the differences from one participant to another. The individuals in a research study differ on a variety of participant variables such as age, height, weight, IQ, and personality.

Participant Variable

personal characteristics that can differ from one individual to another.

Individual Differences

the differences from one participant to another. The individuals in a research study differ on a variety of participant variables such as age, height, weight, IQ, and personality.

Time-Related Variables

Threats to internal validity for studies comparing one group over time.