2. Scientific Foundations of Psychology: Research Methods

Descriptive Research Naturalistic Observation

In a naturalistic observation, researchers unobtrusively observe the behavior of subjects as it occurs in a real social setting. For example, a researcher may observe how parents interact with their children at the local mall. This method minimizes artificiality, which can be a problem in laboratory studies. However, the researcher cannot control the environment or any outside factors that may influence the outcome.

Correlation Studies Definition

In correlation studies researchers observe or measure a relationship between variables in which changes in one variable are reflected in changes in the other variable. It is important to note that in correlation studies researchers do not directly manipulate the variables. Correlations can be used to analyze the data gathered in any type of descriptive method.

Ethical Guidelines Human Research Studies

Informed consent - Informed consent is the participant's agreement to take part in a study after being told what to expect. - Researchers must obtain the participant's permission, or permission from a parent or guardian before the study begins. Voluntary participation - All participation must be voluntary. - Participants should be told that they are free to withdraw from the research at any time. Deception - The American Psychological Association (APA) recognizes the need for some deception in certain research areas. - Deception is only justified when there is no alternative and the findings justify the use of deception because of scientific, educational, or applied value. - When deception is used, subjects must be debriefed to explain the true purpose of the study and clear up any misconceptions or concerns. Confidentiality - All information about participants must remain private. - Researchers may not compromise the privacy of their participants. Alternative Activities - Many college courses include research participation as a course requirement or opportunity for extra credit. - All students must be given an option to choose an alternative activity of equal value.

Descriptive Research Case Studies

A case study is an in-depth examination of an individual, small group, or situation. Case studies enable researchers to obtain detailed knowledge about rare individuals and unusual occurrences. Case studies cannot be used to establish cause-and-effect relationships. They are susceptible to inaccurate reporting and the subject's biased views.

Correlation Studies Correlation Coefficient

A correlation coefficient is a numerical value that indicates the strength and direction of the relationship between two variables. Correlation coefficients are calculated by a formula that produces a number ranging from +1.00 to -1.00. A positive correlation - Indicates that two variables move or vary in the same direction. - For example, studies have found a positive relationship between smoking and the incidence of lung cancer. That is, as frequency of smoking increases so does the incidence of lung cancer. A negative correlation - Indicates that two variables move or vary in opposite directions. - For example, studies have found a negative correlation between level of education and anger. That is, as level of education increases expressions of anger decrease. A zero correlation - Indicates that there is no relationship between two variables. - The meta-analysis of 3806 salespeople found the correlation between extraversion and sales to be .07. Researchers concluded that the correlation between extraversion and sales is nonexistent.

The Experimental Method Testable Hypothesis

A hypothesis is a tentative statement that describes the relationship between two or more variables. A hypothesis must be testable, verifiable, and refutable. The independent variable is the factor that is manipulated or controlled by the experimenter. The dependent variable is the factor that is measured by the experimenter. It is an aspect of the participant's response that is dependent on the independent variable. Examples: - An experimenter wants to determine if playing violent games increases the frequency of aggressive behavior in children. The independent variable is the video game. The dependent variable is the aggressive behavior. - To determine the relationship between rehearsal of a list of definitions of SAT words. The independent variable is the amount of rehearsal, the dependent variable is the number of correctly recalled definitions. - An experimenter wants to determine if a new drug reduces hyperactivity in children. The independent variable in this study is the drug. The dependent variable in this study is the level of hyperactivity. - To determine the effects of cell phone use on driving, participants were randomly assigned to either drive with or without a cell phone. The independent variable is cell phones, the dependent variable is driving safety. Operational Definitions - An operational definition is a precise description of how the variable in a study will be manipulated and measured. - Precise definitions of variables, terms, and concepts facilitate future repetition of the study. - In a study measuring the relationship between rehearsal/repetition and recall of SAT vocabulary words, rehearsal might be operationally defined as the number of times the subject reads aloud a list of words.

Descriptive Research Surveys

A research technique that uses questionnaires or interviews, or a combination of the two, to assess the behavior, attitudes, and opinions of a large number of people. The entire group that a researcher wants to study is called a population. Researchers question a sample of the population. A random sample, in which every person has an equal chance of participating, minimizes bias and ensures that the sample is representative. Survey respondents often report that they are healthier, happier, and less prejudiced than would be expected based upon the results of other types of research. This phenomenon is known as the social desirability bias.

The Experimental Method Definition

An experiment is a carefully controlled method of investigation used to establish a cause-and-effect relationship. The experimenter purposely manipulates and controls selected variables in order to determine cause and effect.

Correlation Studies Correlation And Causation

Correlation studies indicate the possibility of a cause-and-effect relationship. Correlation does not prove causation. Research studies have found a moderate correlation of +0.4 between SAT® scores and college grades. This does not tell us whether high SAT® scores cause high college grades. Other known and unknown factors such as the level of achievement motivation and the pressure or absence of tutors could be responsible for both the SAT® scores and the college grades.

The Experimental Method Disadvantages Of Experiments

Create artificial laboratory conditions that do not correspond to real-life situations. Can be compromised by confounding variables that are difficult to identify and control. Susceptible to researcher and participant biases. Raise ethical concerns when subjects are deceived.

Descriptive Statistics Measures Of Variation

Definition - A measure of variation is a single score that presents information about the spread of scores in a distribution. Range - The highest score in a distribution minus the lowest score. Standard Deviation - The most widely used measure of variation. - A standard measurement of how much the scores in a distribution deviate from the mean. Normal distribution - Normal distributions form a bell-shaped or symmetrical curve. - In a normal distribution of test scores the percentage of scores that fall at or above the mean score is 50. The percentage of test scores that fall at or below the mean score is also 50. - In a normal distribution, approximately one-third of the scores fall one standard deviation below the mean and one-third of the scores fall one standard deviation above the mean. - All score-based normal curves have the following 68-95-99.7 rule in common: - Approximately 68% of all scores fall within one standard deviation of the mean. - Approximately 95% of all scores fall within two standard deviations of the mean. - Approximately 99.7% of all scores fall within three standard deviations of the mean.

Descriptive Research Definition

Descriptive research includes methods that enable researchers to observe and describe behaviors and mental processes without manipulating variables. Descriptive methods do not enable researchers to establish cause-and-effect relationships.

The Experimental Method Advantages Of Experiments

Enable researchers to identify cause-and-effect relationships. Enable researchers to distinguish between real and placebo effects. Enable researchers to control bias by using a double-blind study. Enable researchers to manipulate the independent variable and measure the dependent variable. Enable researchers to replicate a study, thus increasing confidence that the independent variable influences the dependent variable.

Descriptive Statistics Measures Of Central Tendency

Measures of central tendency describe the average or most typical scores for a set of research data or distribution. Measures of central tendency include the mean, median, and mode. Mean - The sum of a set of scores in a distribution divided by the number of scores. The mean is the average score. - Extreme scores have a greater impact on the mean than on the mode or the median. - Any change in the highest score in any distribution must result in a change in the mean. Median - The score that divides a frequency distribution exactly in half, so that the same number of scores lie on each side of it. - The median is a better measure of central tendency when extreme scores distort the mean. Mode - The most frequently occurring score in a distribution. An Example - The nine members of a psychology class earned the following scores on a 10-question quiz: 3, 5, 5, 5, 6, 7, 8, 10, and 10. - The mean score is 6.5, the median score is 6, and the mode is 5.

Descriptive Research Meta-Analysis

Meta-analysis is a procedure for statistically combining the results of many different research studies. For example, many social scientists have investigated the relationship between extroversion and sales success. A meta-analysis of 35 separate studies enabled researchers to analyze data for 3,806 salespeople.

Inferential Statistics Key Points

Most experiments are conducted with a small sample of subjects. Psychologists want to generalize the results from their small sample to a larger population. Inferential statistics are used to determine how likely it is that a study's outcome is due to chance and whether the outcome can be legitimately generalized to the larger population from which the sample was selected.

Ethical Guidelines Animal Research Studies

Must have a clear scientific purpose. Must provide humane living conditions for animal subjects. Must legally acquire animal subjects from accredited companies. Must minimize the amount of suffering. It is important to note that less than 10 percent of research is done with nonhuman animals. Ninety percent of the nonhuman animals are rats, mice, and pigeons.

Descriptive Statistics Skewed Distributions

Positively skewed distributions - A positively skewed distribution contains a preponderance of scores on the low end of the scale. - The mean will be higher than the median in a positively skewed distribution. The median is thus a better representation of central tendency than the mean in a positively skewed distribution. Negatively skewed distributions - A negatively skewed distribution contains a preponderance of scores on the high end of the scale. - The mean will be lower than the median in a negatively skewed distribution. The median is thus a better representative of central tendency than the mean in a negatively skewed distribution.

The Experimental Method Experimental Controls

Purpose - Controls are used to ensure that all groups in the experiment are treated exactly the same, except for the independent variable. Problems - Experimenter bias—occurs when a researcher's expectations or preferences about the outcome of a study influence the results in a hoped-for direction. - Sample bias—occurs when research participants are not representative of the larger population. A researcher wanted to study trick-or-treaters who appeared at her home, this isn't all children tho. Solutions - Random assignment—procedure by which participants are assigned to groups by chance. This minimizes differences between participants assigned to the groups, reducing the effects of confounding variables. - Placebo—an inactive substance or fake treatment often used as a control technique in drug research. It allows researchers to separate the effects of the drug from the expectations of the participants. - Single-blind study—a procedure in which the subjects do not know whether they are in the experiment or control group. - Double-blind study—a procedure in which neither the researcher nor the participant knows which group received the experimental treatment. This procedure reduces experimenter bias. - The single-blind technique is more appropriate than a double-blind technique when a variable such as race or gender makes blinding impossible.

Inferential Statistics Statistical Significance And The p-Value

Results are statistically significant when the probability that findings are due to chance is low. If the mean scores of two groups is statistically significant, a researcher would conclude the difference exists. If the difference is not statistically significant, a researcher would conclude that the difference occurred by chance. The p-value is the probability of concluding that a difference exists when in fact this difference does not exist. By consensus, a statistically significant difference is one that would occur only 5% of the time or less. The smaller the p-value the more significant the results. A p-value can never equal 0 because researchers can never be 100 percent certain that the results did not occur by chance.

The Experimental Method Participants: Experimental And Control Groups

The experimental group comprises the participants who are exposed to the independent variable. The control group comprises the participants who are exposed to all experimental conditions except the independent variable. This enables the experimenter to make comparisons with the experimental group. Confounding variables - In a controlled experiment, confounding variables are differences between the experimental group and the control group other than the independent variable. (gender, age, and education). - In a study measuring the impact of playing violent games on aggression in children, confounding variables could include the income level of the children's parents and the incidence of child abuse.

Descriptive Research Studies Of Development

The longitudinal method measures an individual or group over an extended period of time. A longitudinal study of intelligence would retest the same people over a period of years. Longitudinal studies provide in-depth information but can be expensive. In addition, participants who drop out during the course of the study may be different in important ways from those who did not drop out. The cross-sectional method compares individuals of various ages at one point in time. A cross-sectional study of achievement motivation would test 8th, 10th, and 12th grade students at the beginning of the year. Cross-sectional studies provide information about age differences. However, it is very difficult to make generalizations since cross-sectional studies measure behavior at only one point in time.

Correlation Studies Advantages Of Correlation Studies

They can be used to describe or clarify a relationship between two variables. They can be an efficient way to utilize pre-existing data. They can be used to dispel illusory correlations. Although believed, an illusory correlation is non-existent. It is erroneously believed that there is a correlation between date of birth and personality traits.

Correlation Studies Disadvantages Of Correlation Studies

They cannot be used to establish cause-and-effect relationships. They cannot be used to establish the direction of causal influence. They do not allow researchers to actively manipulate the variables. They make it difficult to identify the impact of confounding variables.