Help needed

BeautyGrad11

See attachments 

  • 5 months ago
  • 10
files (2)

Instructions1.docx

Please respond to this topic using the attached PowerPoint for notes. This is a discussion post, not a formal paper. 100% NO PLAGIARISM or AI!!!!! This should only be maybe 1 or 2 paragraphs at the most.

List the primary strengths of the experimental research design. In particular, what makes it the best method for revealing cause and effect relationships? Lastly, if it is the best method, why isn’t it used more frequently in the social sciences? In other words, what are some issues that may prevent us from using this design when conducting research?

PPnotes.pptx

The Practice of Social Research

Chapter 8 – Experiments

Chapter Outline

Topics Appropriate to Experiments

The Classical Experiment

Selecting Subjects

Variations on Experimental Design

An Illustration of Experimentation

Alternative Experimental Settings

Strengths and Weaknesses of the Experimental Method

Ethics and Experiments

Quick Quiz

LEGEND: common notation

IV – independent variable

DV – dependent variable

E – experimenter

S - subject

EG – experimental group

CG – control group

ES – experimental stimulus

P – placebo

T1: Time 1

T2: Time 2

T3: Time 3

Experiments

Experiments involve:

Taking action

Observing consequences of that action

Topics Appropriate to Experiments

In particular, best suited for

Explanatory research

E.g., Hypothesis testing

Evaluation research

Particularly, well-positioned for projects involving limited & well-defined concepts & propositions.

The Classical Experiment

Central Features

Variables, time order, measures, and groups

Major Components

IV & DV

Pre-testing & Post-testing

Experimental & Control Groups

The Classical Experiment

Independent & Dependent Variables

Independent – takes form of dichotomous stimulus (it is either present or absent), cause

i.e., it “varies”

Dependent – effect

Outcome measure of presence or absence of DV.

Examples: physical conditions, social behavior, attitudes, feelings, or beliefs

The Classical Experiment

Pre-testing – the measurement of a DV along subjects

prior to testing.

Time 2: implementation of IV

For experimental group only.

Post-testing – measurement of a DV among subjects after exposure to IV.

Differences btw measurements on DV at T1 and T3 can be attributed to influence of IV.

The Classical Experiment

Experimental Group – a group of subjects to whom an experimental stimulus is administered.

Control Group – a group of subjects to whom no experimental stimulus is administered.

Should resemble experimental group.

If we do detect a difference, we want to ensure it is due to the IV, and not a difference btw the two groups!

10

11

12

Hawthorne Effect

Pointed to necessity of control groups

IV: improved working conditions (better lighting)

DV: improvement in worker morale/productivity

Results: workers were responding to attention of researchers, not the improved working conditions.

Placebo

Because of Hawthorne effect, we don’t want subjects to know if they are receiving ES (i.e., IV)

Control groups are exposed to “dummy” IV just so it appears as if everyone is treated the same

Medical research uses this: S doesn’t know what they are taking

Ensures that changes in DV actually result from IV and are not psychologically based.

The Classical Experiment

E may be more likely to “observe” improvements among those who receive the drug (IV)

The Double-Blind Experiment – an experimental design in which neither S nor E know which is the EG and which is CG.

Ostensibly eliminates the possibility of interviewer bias.

i.e. witnessing a change that isn’t there

Selecting Subjects

Must decide the target population – group in which results are extrapolated

Next, decide how to select S from the target pop.

Cardinal rule – EG and CG must be as similar as possible!!!

Randomization purposes towards this goal.

Role of college students

Generalizability?

Selecting Subjects

Probability Sampling

You need at least 100, and this is hard to attain

Randomization – technique for assigning experimental subjects to EG and CG.

Matching –procedure whereby pairs of subjects are matched on basis of their similarities on one or more variables, and one member of the pair is assigned to EG, and the other to the CG – similar to quota sampling

Ideally, produces EG & CG that are statistically =.

Selecting subjects (cont’d)

David Farrington: “randomization insures that the average unit in the EG is approx. equivalent to the avg. unit in the CG before treatment is applied.

“All other things are equal”

19

Variations on Experimental Design

Quasi-Experimental Research Designs

One-shot case study – a single group of subjects is measured on DV following an ES.

One-group pre-test post-test design – a pre-test is added for the EG but lacks a CG.

Static-group comparison – includes EG and CG, but no pre-test.

21

Variations on Experimental Design

Validity Issues in Experimental Research

Internal Validity – possibility that conclusions drawn from experimental results may not accurately reflect what happened in the experiment itself.

Sources: history, maturation, testing, instrumentation, statistical regression, selection bias, experimental mortality, causal time order, diffusion or imitation of treatments, compensation, compensatory rivalry, demoralization

External Validity – the possibility that conclusions drawn from experimental results may not be generalizable to the “real” world

Internal validity threats

History – external events may occur during experiment that influences R.

Maturation – people are constantly evolving.

Testing – R may be learning how to test rather than the material – e.g., comprehensive exams/assessments.

Instrumentation – changes in measurement process.

Statistical regression – extreme scores regress to mean.

Selection biases – way in which subjects are chosen (random assignment).

Experimental mortality – S may drop out of experiment.

Threats to Internal Validity

8. Causal time order: Ambiguity about order of stimulus and Dependent Variable – which caused which?

9. Diffusion/Imitation of treatments: Experimental group may pass on elements to Control group when communicating

10. Compensatory treatment: Cgroup is deprived of something considered to be of value

24

24

Internal Validity Threats

11. Compensatory Rivalry: Control group deprived of the stimulus may try to compensate by working harder

12. Demoralization: Feelings of deprivation among control group result in subjects giving up

25

25

Alternative Experimental Settings

Web-Based Experiments

“Natural” Experiments

Strengths of Experimental Method

Isolation of experimental variable’s impact over time.

Replication

Experimental design ensures:

Cause precedes effect via taking posttest

Empirical correlation exists via comparing pretest to posttest.

No spurious 3rd variable influencing correlation via posttest comparison between EG & CG, via randomization.

Weaknesses of Experimental Method

ETHICS!!!

Artificiality of laboratory settings

Aforementioned issues of internal & external validity.

Generalizability and threats to validity

Potential threats to internal validity are only some of the complications faced by experimenters; they also have the problem of generalizing from experimental findings to the real world

Two dimensions of generalizability:

Construct Validity

External Validity

29

29

Threats to Construct Validity

Concerned with generalizing from experiment to actual causal processes in the real world

Link construct and measures to theory

Clearly indicate what constructs are represented by what measures

Decide how much treatment is required to produce change in Dependent Variable

30

30

Threats to External Validity

Significant for experiments conducted under carefully controlled conditions rather than more natural conditions

Reduces internal validity threats

John Eck (2002): "diabolical dilemma."

Suggestion:

explanatory studies  internal validity

applied studies  external validity

31

31

Threats to Statistical Conclusion Validity

Becomes an issue when findings are based on small samples

More cases allows you to reliably detect small differences; less cases result in detection of only large differences

Finding cause-and-effect relationships through experiments depends on two related factors:

Number of Subjects

Magnitude of posttest differences between the experimental and control groups

32

32

Quasi-Experimental Designs

When randomization isn’t possible for legal or ethical reasons

Renders them subject to Internal Validity threats

Quasi = “to a certain degree”

Two categories:

nonequivalent-groups designs

time series designs

33

33

Nonequivalent-Groups Designs

When we cannot randomize, we cannot assume equivalency; hence the name

We take steps to make groups as comparable as possible

Match subjects in Experimental and Control groups using important variables likely related to Dependent Variable under study

Aggregate matching – comparable average characteristics

34

34

Cohort Designs

Cohort – Group of subjects who enter or leave an institution at the same time

Ex: A class of police officers who graduate from a training academy at the same time, All persons who were sentenced to probation in May

Necessary to ensure that two cohorts being examined against one another are actually comparable

35

35

Time-Series Designs

Longitudinal Studies

Examine a series of observations over time

Interrupted – Observations compared before and after some intervention (used in cause-and-effect studies)

Instrumentation threat to internal validity is likely because changes in measurements may occur over a long period of time

Often use measures produced by CJ organizations

36

36

Variable-Oriented Research and scientific realism

A large number of variables are studied for a small number of cases or subjects

Case-oriented research: Many cases are examined to understand a small number of variables (Boston Gun Project)

Variable-oriented research: A large number of variables are studied for a small number of cases or subjects

Case Study Design: Centered on an in-depth examination of one or a few cases on many dimensions

37

37

Experimental Illustration in CJ: Program Evaluation

Evaluation of two prison programs run at Limestone Correctional Facility.

“IF” Project -- https://vimeo.com/162596857

Inside/Out Prison Exchange Program

IF Project Program Evaluation

Program Evaluation included Experimental design

Survey items tapping into static and dynamic risk factors for recidivism.

STATIC

adverse childhood experiences -- 10-item scale tapping into divorce, child abuse, etc.

DYNAMIC

Hopefulness -- 2-item scale

Loneliness --20-item scale

Anxiety 20-item scale

Emotional expression 9-item scale

Pre and post-test levels where examined among E group.

Inside/Out Program Evaluation

Experimental design for program evaluation

Compared inside (inmate) students with outside (college) students on academic self-efficacy

Hypotheses:

outside students will exhibit higher PRE-TEST levels of academic efficacy

Inside students will exhibit statistically significant INCREASE in self-efficacy from PRE-TEST to POST-TEST.

POST-TEST levels of academic efficacy btw Inside and Outside students will be insignificant.

Results:

It Appears that the program has no discernible impact on OUTSIDE students.

While there was positive movement on both the academic efficacy scale and the last item (conflict resolution with peer) from pre-test to post-test, these items were both (a) relatively modest, and (b) insignificant.

The results, while still failing to attain statistical significance, are a little more mixed for the INSIDE students.

While mean academic efficacy did technically drop from pre to post-test, this decline was both modest and failed to attain statistical significance.

Conversely, the mean improvement on conflict resolution with peers did improve noticeably from pre (4.00) to post-test (4.36).

Results (cont’d)

While OUTSIDE students exhibited statistically significant higher mean levels on both the academic efficacy scale and the conflict resolution item……

The statistically significant higher mean levels for OUTSIDE students on the conflict resolution item were reduced to insignificance in the post-test.

image4.jpeg

image5.jpeg

image6.jpeg

image7.jpeg

image8.jpeg

image9.emf

image10.emf

image11.emf

image12.emf

image13.emf

image14.emf

image15.emf

image3.jpeg