Unit 0 Vocab Set B

Correlations & Experiments

Convenience Sample

- Sometimes researchers recruit participants/subjects for their studies based on convenience rather than at random. Convenience samples are existing groups that researchers have access to.

- Random sampling is superior because every member of the population has an equal chance of being selected for the study, which helps ensure that the sample is representative of the whole population.

- A convenience sample may not represent the population, which may introduce confounding variables in the study (selection bias).

Sample Bias/Selection Bias

- Also called selection bias.

- When researchers choose subjects/participants for their study, the best method is random sampling, because that process can ensure that the participant group represents the population well (representative sampling tries to accomplish this goal too)

- If a group of participants doesn't represent the population well, that study has a sample bias/selection bias. If the participants aren't similar enough to the population, researchers have to be careful about generalizing their results to the real world (the population)

Correlation

- A statistical measure of a relationship between two variables.

-Correlation does not imply causation: Just because two variables are correlated does not mean that one variable causes the other.

-Can be either positive or negative. A positive correlation between two variables means that the presence of one variable predicts the presence of the other. A negative correlation means that the presence of one variable predicts the absence of the other.

Scatterplot

-A graph of correlated data.

-Graphs pairs of values,one on the y-axis and one on the x-axis

-For instance, the number of hours a group of people study per week could be plotted on the x-axis, while their GPAs could be plotted on the y-axis.  The result would be a series of points called a scatterplot.

-The closer the points come to falling on a straight line, the stronger the correlation.

-A line that slopes upward, from left to right, indicates a positive correlation.  A downward slope indicates a negative correlation.

Directionality Problem/Third Variable Problem

A correlational study establishes a relationship between 2 variables.  What happens to one variable when the other variable changes?

A correlational study cannot establish cause for the following reasons:

We don’t know if the change in one variable CAUSES the change in the other variable. We need to do an experiment to establish cause.

The directionality problem: Variable 2 might change when variable 1 changes, but we don’t know if variable 2 causes the change in variable 1 or vice versa.

The third variable problem: there might be a third variable that causes the relationship between variables 1 and 2

Experiment

- The only research method that can show a casual relationship.

- Allows the researcher to manipulate the independent variable and control for confounding variables.

- A confounding variable is any difference between the experimental and control conditions (such as time of day), except for the independent variable, that might affect the dependent variable.

- Experiments compare at least two groups: an experimental group and a control group that differ based on the independent variable.

Confounding Variable

Any difference between the experimental and control conditions (such as time of day) except for the independent variable, that might affect the dependent variable.

An experiment allows research to manipulate the inapparent variable and control the compounding variables.

Double Blind Procedure

-Method followed such that neither the participants nor the researchers are aware of who is the in the experimental group or control group while the experiment is going on.

-Double-blind procedures control for both experimental bias, (researchers treating members of the experimental and control groups differently), and participant bias (the tendency for subjects to behave in certain ways based on their perception of an experiment).

Experimental Bias

- The unconscious tendency for researchers to treat members of the experimental and control groups differently to increase the chance of confirming their hypothesis.

- Experimental bias is not a conscious act. If researchers purposely distort their data, it is called fraud, not experimenter bias.

- Using a double-blind procedure can eliminate experimental bias. A double blind occurs when neither the participants nor the researchers are able to affect the outcome of the research.

Participant/Response Bias

- Tendency for subjects to behave in certain ways based on their perception of an experiment.

- Can be controlled for using a single-blind procedure (when participants do not know whether they are assigned to an experimental group or a control group) or a double-blind procedure (when neither the participants nor the researchers are aware of who is in the experimental group or control group while the experiment is going on).

Placebo

-In an experiment, it's important that the experimental and control groups are treated exactly the same except for the presence of the independent variable.

-This means that sometimes researchers have to give the real independent variable to the experimental group, and a fake independent variable that they know doesn't have any impact (a placebo) to the control group

-Example: Researchers want to figure out if a new antidepressant medicine reduces depression rates. They give the real antidepressant medicine (the IV) to the experimental group and a medicine without any real effects (like a sugar pill) as a placebo to the control group

Random Assignment

-The process by which participants are put into either an experimental group or a control group

-Random assignment means that each participant has an equal chance of being placed into any group. It limits the effects of confounding variables based on differences between people.

-Using random assignment diminishes the chance that participants in the two groups differ in any meaningful way.

Longitudinal Research

Development of research that takes place over a long period of time.

Instead of sampling from various age groups as in cross sectional research, a longitudinal study examines one group of participants over time.

For example, a developmental researcher might study how a group of mentally challenged children progress in their ability to learn skills. The researcher would gather the participants and test them at various intervals of their lives (every three years).

Longitudinal studies have the advantage of precisely measuring the effects of development on a specific group. However, they are obviously time consuming, and the results can take years or decades to develop.

Cross-Sectional Research

- Developmental research that uses participants of different ages to compare how certain variables may change over the life span.

- For example, a developmental researcher might be interested in how our ability to recall nonsense words changes as we age. The researcher might choose participants from different age groups, say 5-9, 10-19, 20-29, 30-39, and test the recall of a list of nonsense words in each group.

- Can produce quick results, but researchers must be careful to avoid the effects of historical events.

Meta-Analysis

-A research technique researchers use to create an overall summary of what research studies say about a specific topic

-Researchers use selection criteria to find all the relevant research studies about a specific topic, like the effectiveness of a specific therapy technique. Then they examine the outcomes of all these relevant studies and combine the results to come up with the overall answer about whether that therapy technique is effective.

-Researchers usually compute or use the effect sizes of each of the relevant studies and combine all the effect sizes to come up with the overall answer.

Quantitative & Qualitative Research

- Most research studies involve measuring psychological variables in terms of numbers or scores this is quantitative research (because it involves quantities).

- Some research studies gathered data in the form of quotations/words from participants rather than trying to ¨quantify their variables. This is called qualitative research.

- Quantitative researchers use descriptive and inferential statistics to analyze their data

- Qualitative researchers use other techniques, like thematic analysis, to analyze their data