Inhoudsopgave:

• Hoofdstuk 1 Introduction to research
• Hoofdstuk 2 Developing the research hypothesis
• Hoofdstuk 3 Ethics in research
• Hoofdstuk 4 Measures
• Hoofdstuk 5 Reliability and validity
• Hoofdstuk 6 Surveys and sampling
• Hoofdstuk 7 Naturalistic methods
• Hoofdstuk 8 Hypothesis testing and inferential statistics
• Hoofdstuk 9 Correlational research designs
• Hoofdstuk 10 Experimental research: one-way designs
• Hoofdstuk 11 Experimental research: factorial design
• Hoofdstuk 12 Experimental control and internal validity
• Hoofdstuk 13  External validity 
• Hoofdstuk 14 Quasi- experimental research designs
• Appendix A

Hoofdstuk 1 Introduction to research

The hindsight bias is the tendency to think that we could have predicted something that we probably could not have predicted. 

Basic research provides underlying principles that can be used to solve specific problems and applied research gives ideas for the kinds of topics that basic research can study. 

Research designs:

• Descriptive research (survey, interview and observation)

There is qualitative and quantitative research in this design.

• Correlational research (pearson product-moment correlation coefficient)

• Experimental research

Converging operations is using more than one design to study the same thing, with the hope that all of the approaches will produce similar findings. 

Hoofdstuk 2 Developing the research hypothesis

The inductive method is getting ideas about the relationships among variables by observing specific facts. Your own curiosity becomes the source of your ideas. 

There are primary and secondary sources. Primary are complete descriptions of the collected data and the data analyses. Secondary means only a summary or interpretation of the research report.

Principles that are so general as to apply to all situations are known as laws. A theory is an integrated set of principles that explains and predicts many, but not all, observed relationships within a given domain of inquiry. The deductive method is the process of using a theory to generate specific ideas that can be tested through research.Good theories are general, parsimonious(summarize many different outcomes), provide for future research and are falsifiable. Theories in which the variables cannot be measured or in which the variables are vague enough that they cannot provide information to falsify the theory are called tautological. 

Experimental research: Independent variable ⇒ Dependent variable

Correlational research: predictor variable ⇔ Outcome variable

Hoofdstuk 3 Ethics in research

Conducting ethical research with human participants involves avoiding psychological and physical harm to research participants, providing freedom of choice, treating participants with respect and honestly describing the nature and use of the research. The most important tool for providing freedom of choice and reducing psychological stress from participation in behavioral science research is the use of informed consent. “Geïnformeerde toestemming is een procedure waarin iemand de mogelijke voor- en nadelen van een medische behandeling te horen krijgt alvorens degene besluit om de behandeling al dan niet te ondergaan.”

In most cases the institutional review board(IRB) at the institution where the research is being conducted will help the scientist determine whether his or her research is ethical. 

Hoofdstuk 4 Measures

A conceptual variable is the abstract basis of the research hypothesis. The measured variables are the numbers that represent the conceptual variable. Operational definition means the precise statement of how a conceptual variable is turned into a measured variable. Before any research can be tested, the conceptual variables must be turned into measured variables through the use of operational definition. This process is known as measurement.

A nominal variable is used to name or identify a particular characteristic. A quantitative variable uses numbers to indicate the extent to which a person possesses a characteristic of interest. 

An interval scale has equal distances between scores on a measure and are known to correspond to equal changes in the conceptual variable. A ratio scale is an interval scale with a true zero point. An ordinal scale has numbers that indicate the exact interval between the individuals on the conceptual variable. 

Fixed-format self-report measures have a set of questions presented to the individual and the responses that can be given are more structured than in free-format measures. Such as Likert, semantic differential and Guttman scales. “Een semantisch differentiaal is een psychometrische schaal met op de twee uitersten tegenovergestelde begrippen.” A problem that occurs here is the acquiescent responding, which describes the general tendency of a person to provide affirmative answers to items of a questionnaire, regardless of the content of the items. 

Hoofdstuk 5 Reliability and validity

Reliability is about the consistency of a measure, and validity is about the accuracy of a measure

Whereas random errors tend to cancel out over time, systematic errors systematically increase or decrease the scores on the measured variable.
The reliability of a measure refers to the extent to which it is free from random error. One direct way to determine reliability of a measured variable is to measure it more than once. In an equivalent forms reliability there are two different but equivalent versions of the same measure given at different times and the correlation between the scores on the two versions is assessed. Interrater reliability refers to the reliability of a set of judges or coders.

Internal consistency refers to the extent to which the scores on the items correlate with each other and thus are all measuring the true score rather than random error. 

Validities:

• construct= the extent to which a measured variable actually measures the conceptual variable that it is designed to measure.

1. face= the extent to which the measured variable appears to be an adequate measure of the conceptual variable.

2. content= the extent to which the measured variable appears to have adequately covered the full domain of the conceptual variable.

3. convergent= the extent to which a measured variable is found to be related to other measured variables designed to measure the same conceptual variable.

4. discriminant= the extent to which a measured variable is found to be unrelated to other measured variables designed to measure the same conceptual variable.

• criterion= the extent to which a self-report measure correlates with behavioural measured variables. 

1. predictive= the extent to which a self-report measure correlates with (predicts) a future behaviour.

2. concurrent= the extent to which a self-report measure correlates with a behaviour measured at the same time. 

Creating valid measures:

• conduct a pilot test.

• use multiple measures.

• ensure variability within your measures.

• write good items.

• attempt to get your respondents to take your questions seriously. 

• attempt to make your items nonreactive.

• be certain to consider face and content validity by choosing items that seem reasonable and that represent a broad range of questions concerning the topic of interest.

• when possible, use existing measures rather than creating your own.

Hoofdstuk 6 Surveys and sampling

Surveys are self-report descriptive research designs that attempt to capture the current opinions, attitudes or behaviours of a group of people. 

In probability sampling procedures are used to ensure that each person in the population has a known chance of being selected to be a part of the sample:

• Simple random sampling means that everyone in the population has an equal chance of being selected to be in the sample. 

• Systematic random sampling is a method to select samples at a particular preset interval (the number of elements in the population divided by the number of elements needed for the sample.) Choose a random starting point between 1 and the sampling interval.

• Stratified sampling is drawing separate samples form each of the subgroups rather than to sample from the population as a whole. 

• Cluster sampling means that the population is broken into a set of smaller groups and then randomly choose some of the clusters for inclusion in the sample. 

When nonprobability sampling techniques are used, either because they are convenient or because probability methods are not feasible, they are subject to sampling bias. Convenience samples happen when the researcher has sampled whatever individuals were readily available without any attempt to make the sample representative of a population. 

Larger samples will produce a more accurate picture and thus have a lower margin of error.

Hoofdstuk 7 Naturalistic methods

Naturalistic research is designed to describe and measure the behaviour of people of animals as it occurs in their everyday lives.It has ecological validity, which refers to the extent to which the researcher is conducted in situations that are similar to everyday life experiences of participants. However, although the data can be rich and colorful, naturalistic research often does not provide much information about why behaviour occurs or what would have happened to the same people in different situations. 

Case studies are descriptive records of one or more individuals’ experiences and behaviour, in which unusual, unexpected or unexplained behaviours become the focus of the research. 

Systematic observation involves specifying ahead of time exactly which observations are to be made on which people and in which times and places.

Three sampling strategies:

• event sampling= focusing on specific behaviours that were theoretically related to social comparison.

• individual sampling= choosing one individual to focus on.

• time sampling= choosing one individual to focus on for a period of time and then move on to the next for a period of time. 

Archival research is based on analysis of any type of existing records of public behaviour. For example newspaper articles, television broadcasts or existing surveys. 

Hoofdstuk 8 Hypothesis testing and inferential statistics

Hypothesis testing flow-chart: Develop research hypothesis→ Set alpha(0,05)→ calculate power to determine the sample size that is needed→ collect data→ calculate statistic and p-value→ compare p-value to alpha(0,05) → reject/don’t reject null hypothesis

These procedures, based on inferential statistics, are specified by the scientific method and are set in place before the scientist begins to collect data.

Types of error:

The effect-size statistic is often used as a measure of the magnitude of a relationship between variables because it is not influenced by the sample size in the research design. The strength of the relationship may also be considered in terms of the proportion variance in the dependent measure that is explained by the independent variable. The effect size of many relationships in scientific research is small, which makes them difficult to discover.

Hoofdstuk 9 Correlational research designs

Correlational methods range from analysis of correlations between a predictor and an outcome variable to multiple-regression and path analyses assessing the patterns of relationships among many measured variables.

Relationships that change in direction and thus are not described by a single straight line are called curvilinear relationships. 

The chi-square statistic is used to assess the relationship between two nominal variables. To calculate this, the researcher first constructs a contingency table. This displays the number of individuals in each of the combinations of the two nominal variables.

When there are many correlations to be reported at the same time, they can be presented in a correlation matrix.

A spurious-relationship is one in which the common-causal variable produces and explains away the relationship between the predictor and outcome variable. 

Variables other than the predictor variable that cause the outcome variable but that do not cause the predictor variable are called extraneous variables.

Hoofdstuk 10 Experimental research: one-way designs

An one-way experimental design has one independent variable. The levels of the independent variable are frequently called the experimental conditions. There can be a between-participants design or a repeated-measures design. If the between-groups variance is significantly greater than the within-groups variance, then we conclude that the manipulation across the levels is greater than the random fluctuation among individuals within the levels. 

ANOVA summary table:

A Latin square design is a method of counterbalancing the order of conditions so that each condition appears in each order but also follows equally often after each of the other conditions. So this design is used when there are many conditions to be counterbalanced. 

Hoofdstuk 11 Experimental research: factorial design

Factorial experimental designs have more than one independent variable. It increases the amount of information than can be gained from the experimental design. The independent variables are usually crossed with each other such that each level of each varible occurs with each level of each other independent variable.

Marginal means are the means for the factors averaged for all levels of the other factors.

The effect of one factor within a level of another factor is known as a simple effect of the first factor. When the lines are not parallel, there is an interaction. 

Two-way interactions are interactions than involve the relationship between two variables, controlling for the third variable. 

Designs in which some factors are between participants and some are repeated measures, are known as mixed factorial designs. 

The most common type of means comparison is a pairwise comparison in which any one condition mean is compared with any other condition mean. One problem is that there can be a lot of them. 

The experimentwise alpha is the probability of the experimenter having made a Type I error in at least one of the comparisons. There are three ways to reduce this alpha in means comparisons tests:

• planned comparisons/priori comparisons= compare only means in which specific differences were predicted by the research hypothesis.

• post hoc comparisons= many comparisons are being made and these comparisons were not planned ahead of time.

• complex comparisons= two means are compared at the same time. These are usually conducted with contrast tests. 

Hoofdstuk 12 Experimental control and internal validity

Four threats to the validity of research:

• threats to construct validity.

• threats to statistical conclusion validity= conclusions regarding the research may be incorrect because a Type I or Type II error was made.

• threats to internal validity= the dependent variable may have actually been caused by a confounding variable.

• threats to external validity= the observed effects may actually only be found under limited conditions or for specific groups of people.

Extraneous variables are variables other than the independent variable that cause changes in the dependent variable. Confounding variables are variables other than the independent variable on which the participants in one experimental condition differ systematically/on average from those in other conditions. 

Researchers attempt to reduce extraneous variables within the experimental conditions through the use of such techniques as limited-population, before-after, or matched-group designs. As well as through standardization of conditions.

A matched-group design is where participants are measured on the variable of interest before the experiment begins and then are assigned to conditions on the basis of their scores on that variable. (see figure 12.2, p.239)

The extent to which the experimental manipulation involves the participants in the research is known as experimental realism. 

Demand characteristics are the aspects of the research that allow participants to guess the research hypothesis. In some cases the cover story involves the use of the unrelated-experiments technique. In this technique participants are told that they will be participating in two separate experiments conducted by two seperate experimenters. In reality the experimental manipulation is presented in the first experiment, and the dependent measure is collected in the second experiment.

To avoid internal invalidity, researchers use appropriate control groups, cover stories and blocked random assignment to conditions. 

Block randomization works by randomizing participants within blocks such that an equal number are assigned to each treatment. For example, given a block size of 4, there are 6 possible ways to equally assign participants to a block. It is used to avoid artifacts when assigning participants to conditions in an experiment. 

Hoofdstuk 13  External validity 

External validity refers to the extent to which the results of a research design can be generalized beyond the specific way the original experiment was conducted. The major issue underlying external validity is that of generalization. 

Four types of replication:

• exact replication= repeat a previous research design as exactly as possible, keeping almost everything about the experiment the same as it was the first time around.

• conceptual replication= the same conceptual variables are studied but by using different operational definitions of the independent variable/the measured dependent variable.

• constructive replication= the researcher tests the same hypothesis as the original experiment but also adds new conditions to the original experiment to assess the specific variables that might change the previously observed relationship.

• participant replication= the experiment should be designed as a constructive replication in which both the original population and the new one are used.

A meta-analysis provides a relatively objective method of reviewing research findings because it specifies inclusion criteria that indicate exactly which studies will or will not be included in the analysis, systematically searches for all studies that meet the inclusion criteria and uses the effect size statistic to provide an objective measure of the strength of observed relationships. 

Hoofdstuk 14 Quasi- experimental research designs

Quasi-experimental research designs are designs in which the independent variables are measured, rather than manipulated. These are correlational and not experimental. These are used when it is not possible to randomly assign individuals to groups. 

Single group designs are designs that use a single group of participants who are measured after they have had the experience of interest. However there is no control group involved.

A comparison group is a group that is expected to be similar but not equivalent to the experimental group. 

Threats to internal validity that occur because individuals select themselves into groups, rather than being randomly assigned to groups, are called selection threats.

A before-after approach has its own set of potential threats to internal validity:

• retesting threats= the participants may be able to guess the research hypothesis. 

• attrition/mortality threats= some people might drop out.

• maturation and history threats= potential changes in the participants over time but that are unrelated to the independent variable. 

Time-series designs are designs in which the dependent measure is assessed for one or more groups more than twice, both before and after the experience of interest occurs. 

Participant-variable designs are designs where the grouping variable involves pre existing characteristics of the participants. 

Single-participant research designs are able to track the behaviour of individuals over time that makes it possible in some cases to draw conclusions about the changes in behaviour of a single person.

Damage to the hippocampus abolishes the cortisol response to psychosocial stress in humans.

Appendix A

The goals for writing the research report include being organized, precise, concise, compulsive, interesting and fair. 

There are five major sections within the APA format:

• abstract

• introduction

• methods

• results

• discussion

Creating a research report that is both technically informative and easy to read takes a substantial amount of work and will generally require much rewriting.