Part Three Modes of Observation. Chapter 8 Experiments.

Part Three

Modes of Observation

Chapter 8

Experiments

Chapter Outline Introduction Topics Appropriate to Experiments The Classical Experiment Selecting Subjects

Introduction 實驗？ 生活中其實充滿了實驗性 交女朋？上課？翹課？煮飯？買手機……

Chapter Outline Topics Appropriate fo Experiments The Classical Experiment Selecting Subjects Variations on Experimental Designs An Illustration of Experimentation Alternate Experimental Settings Strengths and Weaknesses of the

Experimental Method

甚麼課題適合使用實驗法？ Projects with limited and well-defined

concepts. 概念範圍小而且明確：中文教材、英文教材學生成績

Projects that are exploratory rather than descriptive. 解釋性 ( 因果關係 ) 而非描述性

Studies of small group interaction.( 小團體研究 ) ：賦予不同的工作、給予不同的獎勵團體的動態會有何不同？

The Classical Experiment

Three Pairs Independent and dependent variables Pretesting and posttesting Experimental and control groups

1 、自變項與依變項 假設種族偏見源自於缺乏知識，因此 接觸他族的資訊 ( 自變項 ) 愈豐富偏見

( 依變項 ) 會愈低 自變項如何操作？依變項如何測量？ 特定而標準化的測量和觀察。

Question In the simplest experimental design,

subjects are measured in terms of a _________ variable exposed to an _________ variable.

A. pretested; posttestedB. fluid; staticC. independent; dependentD. dependent; independent

2 最簡單的實驗法：前測與後測 前測：接收資料之前，測量個體的種族偏

見程度 ( 依變項 ) 閱讀資料、觀看影片…… ( 增多資訊之接

受 ) 後測，再測量種族偏見的程度 ( 依變項 ) 後測 – 前測：源自於自變項之改變

Answer: D In the simplest experimental design,

subjects are measured in terms of a dependent variable exposed to an independent variable.

效度？ 如果受試者”感受”到：實驗是在檢視她 /

他的種族偏見程度，因此……。 後測 - 前測：真是因為”接收了資訊”嗎？ 實驗過程的本身，而不是自變項的改變，

可能就會造成受試者的改變

兩個例子 霍桑效果 工廠的燈光亮度工人的工作效果 新葯有沒有效？ 新葯有沒有效？ 如果有兩組人，一組給新葯；另一組給糖

漿，是否也都使病情改善？

3 、 Experimental and Control Groups 實驗組之外，另增控制組 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 and who resemble the experimental group in all other respects.

僅實驗組接受實驗，即自變項的改變

但，如果兩組人本來就不一樣？ 這兩組的成員 Must be as similar as

possible. 控制組代表：如果實驗組沒有接受實驗，

依變項會如何？ Control group represents what the experimental group would have been like had it not been exposed to the stimulus.

Question _____________ groups are groups of

subjects to whom an experimental stimulus is administered.

A. control

B. experimental

C. purposive

D. triad

Answer: B• Experimental groups are groups of

subjects to whom an experimental stimulus is administered.

Diagram of Basic Experimental Design

如果再有其他事件發生 種族偏見實驗的前、後測之間，發生了種

族之間的激烈衝突事件…… 上述的圖表所列，可不可以排除這個事件

的影響？

Double-blind Experiment 在新葯的例子，施測者本身可能也會預期

葯效，而誤判效果真的發生，因此… An experimental design in which neither

the subjects nor the experimenters know which is the experimental group and which is the control.

如果”測量”是很確定的，如標準化問卷，則施測者主觀預期就無法影響。

Selecting Subjects 以大學生為對象的實驗結果之

generalizability ？代表性與因果關係 可比性 (comparability) 最重要 1 Probability sampling( 實驗法中難以使用 ) 2 Randomization( 代表性？可比性？ ) 3 Matching ，可配合配額抽樣的觀念，必

要時，前測之後，再配對 要之，使兩者在重要變項上的分佈一致

Open Matrix Illustration

Randomization and Matching 支持隨機化法： May not know which variables will be

relevant for matching process. Most statistics used to analyze results

assume randomization. 支持配對法： Randomization only makes sense if you

have a large pool of subjects.

Question ______________ is a technique for

assigning experimental subjects to experimental and control groups randomly.

A. nonprobability analysesB. matchingC. randomizationD. none of these choices

Answer: C Randomization is a technique for

assigning experimental subjects to experimental and control groups randomly.

Preexperimental Research Designs 不夠專業的設計，或者，不知不覺中會這樣看事

情 One-shot case study - single group of subjects

is measured on a variable following experimental stimulus.

One-group pretest-posttest design - adds a pre-test for the group, but lacks a control group.

Static-group comparison - includes experimental and control group, but no pre-test.

One-Shot Case Study

A man who exercises is observed to be in trim shape.

One-Group Pretest-Posttest Design

An overweight man who exercises is later observed to be in trim shape

Static-Group Comparison

A man who exercises is observed to be in trim shape while one who doesn’t is observed to be overweight.

Question In a one-group pretest-posttest design,

what is lacking?

A. EPSEM

B. an experimental group

C. a control group

D. none of these choices

Answer: C In a one-group pretest-posttest design, a

control group is lacking.

Sources of Internal Invalidity 實驗所”發現”的結果其實不是來自實驗 1 Historical events may occur during the

course of the experiment. 2 Maturation of the subjects. 實驗時間拉

長的，會出現的問題 3 Testing and retesting can influence

behavior. 4 Instrumentation ，測驗不夠標準化時

Sources of Internal Invalidity 5 Statistical regression of subjects

starting out in extreme positions. 受試者一開始就是極端例外

6 Selection biases.選派兩組一開始就不可比

7 Experimental mortality - subjects drop out of the study before it's completed.

8 因果不明 ( ？ )

Limiting External Invalidity Solomon four-group design Posttest-only control group design

9 實驗污染： diffusion or imitation of treatment 實驗組與控制組有機會交通

10 compensation ：予控制組額外補償，造成實驗之外的額外刺激

11 compensatory rivalry: 控制組的敵對補償性

12 Demoralized control group subjects ：控制組士氣低沉

The Classical Experiment

內在效度問題？ 在降低偏見的實驗：實： 2 < 1 ；而 控 >

實 2 以上可能造成內在效度的項目，有那些被

解決？ 假設隨機分派過，則 History? Maturation? Testing?? Instrument? Statistical regression? Selection bias? Experimental mortality?

Causal time order?.......

外在效度 實驗結果可否概化至實際生活世界當中？ 測驗的情境與實驗刺激的互動 偏見降低，因為受測引起接受實驗刺激的

效果。在實際生活中，只有刺激而沒有受測

Solomon Four-group Design

Four groups of subjects, assigned randomly:

Groups 1 and 2 are the control and experimental group.

Group 3 does not have the pre-test. Group 4 is only posttested.

Solomon Four-group Design

Solomon Four-group Design Expected Findings

In Group 1, posttest prejudice should be less than pretest prejudice. ( 後低於前 )

In Group 2, prejudice should be the same in the pretest and the posttest.( 前後相等 )

The Group 1 posttest should show less prejudice than the Group 2 posttest does.(1後 低於 2 後 )

The Group 3 posttest should show less prejudice than the Group 4 posttest does. ( 後 3 低於後 4)

Question What is the basic difference between the

classical design and the Solomon four-group design?

A. There is no difference.B. The Solomon four-group design repeats the

classical design but adds groups that are not pretested.

C. The Solomon four-group design repeats the classical design but adds groups that are not posttested.

Answer: B The basic difference between the

classical design and the Solomon four-group design is that the Solomon four-group design repeats the classical design but adds groups that are not pretested.

Posttest-only Control Group Design Includes Groups 3 and 4 of the Solomon

design. With proper randomization, only these

groups are needed to control problems of internal invalidity and the interaction between testing and stimulus.

嘿！奇怪的玩意兒！

一個有趣的實驗

"Natural" Experiments Important social scientific experiments

occur outside controlled settings and in the course of normal social events.

Raise validity issues because researcher must take things as they occur.

Web-based Experiments Increasingly, researchers are using the

World Wide Web to conduct experiments. Because representative samples are not

essential in most experiments, researchers use volunteers who respond to invitations online.

Experimental Method

Strengths: Isolation of the experimental variable over

time. Experiments can be replicated several

times using different groups of subjects.

Experimental Method

Weaknesses: Artificiality of laboratory setting. Social processes that occur in a lab might

not occur in a more natural social setting.

Quick Quiz

1. Experiments are especially well suited for research projects involving:

A. limited concepts

B. well-defined concepts

C. hypothesis testing

D. all of these choices

Answer: D Experiments are especially well suited

for research projects involving limited concepts, well-defined concepts and hypothesis testing.

2. A ____________experiment eliminates the possibility of a researcher prejudging results.

A. snowball

B. double-blind

C. purposive

D. regressive

Answer: B A double-blind experiment eliminates

the possibility of a researcher prejudging results.

3. ______________refers to the possibility that the conclusion drawn from experimental results may not accurately reflect what has gone on in the experiment itself.

A. exclusionB. internal validityC. external validityD. representativenessE. none of these choices

Answer: B Internal validity refers to the possibility

that the conclusion drawn from experimental results may not accurately reflect what has gone on in the experiment itself.

4. Natural experiments are most likely to resemble which one of the following designs?

A. static-group comparison

B. classical

C. Solomon four-group

D. one-group pretest-posttest

E. posttest-only control group design

Answer: A• Natural experiments are most likely to

resemble static-group comparison designs.

5. Which of the following is the chief advantage of a controlled experiment?

A. they require little time

B. they require little money

C. they are artificial

D. the isolation of the experimental variable’s impact over time

E. none of these choices

Answer: D The isolation of the experimental

variable’s impact over time is the chief advantage of a controlled experiment.