You are on page 1of 40

The basic steps of research...

Scientific and disciplined inquiry is an orderly process, involving: • recognition and identification of a topic to be studied (“problem”)

• description and execution of procedures to collection information (“method”)
• objective data analysis • statement of findings (“results”)

Research methods...
Quantitative… …collects and analyzes numerical data obtained from formal instruments

Quantitative methods...

descriptive research (―survey research‖) correlational research experimental research

experimental research

…the researcher selects participants and divides them into two or more groups having similar characteristics and, then, applies the treatment(s) to the groups and measures the effects upon the groups

Conducting an experimental study… select the problem select participants and instrument selection and execution of a research plan data analysis and formulation of conclusions .

comparison of an existing approach to a new approach (A and ~ A) 3. comparison of two different approaches (A versus B) 2. comparison of differing amounts of a single approach (A and a or a and A) .Types of experimental comparison… 1.

where: A – experimental (―treatment‖) group B – control (―no treatment.‖ ―nonmanipulated‖) group .

intelligence...Variable.g..  …a concept (e. height. aptitude) that can assume any one of a range of values .

. Independent… …an activity of characteristic believed to make a difference with respect to some behavior …(syn.. active variable.Research variables. cause.) experimental variable. treatment .

outcome. effect. assigned variable. posttest .Dependent… …the change or difference occurring as a result of the independent variable …(syn.) criterion variable.

posttest . such that it is difficult to determine the unique effects of each variable …(syn. effect. outcome.) criterion variable.Confounding… …the fact that the effects of the independent variable may intertwine with extraneous variables. assigned variable.

Validity of Experimental Design   Internal validity—The accuracy in concluding that the outcome of an experiment is due to the independent variable External validity—The extent to which the results of an experiment can be generalized .

INTERNAL OR EXTERNAL VALIDITY: A TRADE-OFF?    Too much control reduces ability to generalize Too little control reduces ability to make causal statements Attempt to find a good balance Internal Validity External Validity .

Factors Jeopardizing Internal Validity  History . During the sale a hurricane occurs and results of the study may be affected because of the hurricane. Example: Researcher collects gross sales data before and after a 5 day 50% off sale.The events occurring between the first and second measurements in addition to the experimental variable which might affect the measurement. not the sale. .

growing more tired.  Maturation . Example: Subjects become tired after completing a training session.The process of maturing which takes place in the individual during the duration of the experiment which is not a result of specific events but of simply growing older. and their responses on the Posttest are affected. . or similar changes.

  Pre-testing . Experimental group learns from the pretest.The effect created on the second measurement by having a measurement before the experiment. Example: Subjects take a Pretest and think about some of the items. . On the Posttest they change to answers they feel are more acceptable.

or scorers may cause changes in the measurements. 5th. Example: Interviewers are very careful with their first two or three interviews but on the 4th. 6th become fatigued and are less careful and make errors. calibration of instruments. . observers.Changes in instruments. Measuring Instruments .

. even if no training were given. those scores or measurements tend to move toward the mean with repeated measurements even without an experimental variable.Groups are chosen because of extreme scores of measurements. Example: Managers who are performing poorly are selected for training.  Statistical Regression . Their average Posttest scores will be higher than their Pretest scores because of statistical regression.

Different individuals or groups would have different previous knowledge or ability which would affect the final measurement if not taken into account. .  Differential Selection . Example: A group of subjects who have viewed a TV program is compared with a group which has not. There is no way of knowing that the groups would have been equivalent since they were not randomly assigned to view the TV program.

 Experimental Mortality . Groups to be compared need to be the same after as before the experiment. Example: Over a 6 month experiment aimed to change accounting practices.The loss of subjects from comparison groups could greatly affect the comparisons because of unique characteristics of those subjects. . 12 accountants drop out of the experimental group and none drop out of the control group. but the 12 dropouts may be very different from those who remained in the experimental group. Not only is there differential loss in the two groups.

. . Interaction of Factors. such as Selection Maturation.Combinations of these factors may interact especially in multiple group comparisons to produce erroneous measurements. etc.

Factors Jeopardizing External Validity or Generalizability  Pre-Testing -Individuals who were pretested might be less or more sensitive to the experimental variable or might have "learned" from the pre-test making them unrepresentative of the population who had not been pre-tested. Example: Prior to viewing a film on Environmental Effects of Chemical. a group of subjects is given a 60 item antichemical test. Taking the Pretest may increase the effect of the film. The film may not be effective for a nonpretested group. .

.The selection of the subjects determines how the findings can be generalized. The 12th corporation is obviously different then the others because they accepted. is turned down by 11 corporations. Example: Researcher. but the 12th corporation grant permission. Randomly chosen subjects from the entire population could be generalized to the entire population. requesting permission to conduct experiment. Thus subjects in the 12th corporation may be more accepting or sensitive to the treatment. Differential Selection . Subjects selected from a small group or one with particular characteristics would limit generalizability.

Example: Department heads realize they are being studied. Generalization to persons not in the experimental setting may be precluded.The experimental procedures and arrangements have a certain amount of effect on the subjects in the experimental settings. . try to guess what the experimenter wants and respond accordingly rather than respond to the treatment. Experimental Procedures .

Since training effects cannot be deleted. the first training will affect the second. .If the subjects are exposed to more than one treatment then the findings could only be generalized to individuals exposed to the same treatments in the same order of presentation. Multiple Treatment Interference . Example: A group of CPA’s is given training in working with managers followed by training in working with comptrollers.

The pre-test. or measurement before the experiment begins.Tools of Experimental Design Used to Control Factors Jeopardizing Validity   Pre-Test . . However. pre-tests cause problems by their effect on the second measurement and by causing generalizability problems to a population not pretested and those with no experimental arrangements. can aid control for differential selection by determining the presence or knowledge of the experimental variable before the experiment begins. It can aid control of experimental mortality because the subjects can be removed from the entire comparison by removing their pre-tests.

 Control Group -The use of a matched or similar group which is not exposed to the experimental variable can help reduce the effect of History. Maturation. The control group is exposed to all conditions of the experiment except the experimental variable. . and Interaction of Factors. Instrumentation.

 Randomization . Differential Selection. and the Interaction of Factors. It greatly increases generalizability by helping make the groups representative of the populations .Use of random selection procedures for subjects can aid in control of Statistical Regression.

They would have to be used in conjunction with other pre-tested groups or other factors jeopardizing validity would be present.The effects of Pre-tests and Experimental Procedures can be partially controlled through the use of groups which were not pre-tested or exposed to experimental arrangements. Additional Groups . .

single-variable 2.Group experimental designs… 1. factorial .

single-variable designs …involve one manipulated independent variable  pre-experimental  quasi-experimental  true experimental .

greater control of validity Quasi-Experimental Design .loose in structure.greater control and refinement.Experimental Designs    Pre-Experimental Design . could be biased True Experimental Design .not randomly selected .

Pre-Experimental Design Aim of the Research Name of the Design Notation Paradigm X» O Comments An approach that prematurely links antecedents and consequences. To attempt to One-shot explain a consequent experimental case by an antecedent study To evaluate the influence of a variable One group pretest.» O Weakness lies in no examination of preexperimental equivalence of groups. An approach that provides a measure of change but can provide no conclusive results. Conclusion is reached by comparing the performance of each group to determine the effect of a variable on one of them. .O » X » O posttest To determine the influence of a variable on one group and not on another Static group comparison Group 1: X » O Group 2: . The least reliable of all experimental approaches.

True Experimental Design Aim of the Research To study the effect of an influence on a carefully controlled sample Name of the Design Pretest-posttest control group Notation Paradigm R--[O»X»O [O»-»O Comments This design has been called "the old workhorse of traditional experimentation. . this design controls for eight threats of internal validity." If effectively carried out. Data are analyzed by analysis of covariance.

» X » O [-»-»O Comments This is an extension of the pretest-posttest control group design and probably the most powerful experimental approach. Data are analyzed by analysis of variance on posttest scores .Experimental design (cont) Aim of the Research To minimize the effect of pretesting Name of the Notation Design Paradigm Solomon four-group design R--[O»X»O [O»-»O [.

.Experimental design (cont) Aim of the Research To evaluate a situation that cannot be pretested Name of the Notation Design Paradigm Posttest only control group R--[ X»O [-»O Comments An adaptation of the last two groups in the Solomon four-group design. Probably. Randomness is critical. the simplest and best test for significance in this design is the t-test.

Quasi-Experimental Design Aim of the Research To investigate a situation in which random selection and assignment are not possible Name of the Notation Design Paradigm Nonrandomized control group pretestposttest O»X»O O»-»O Comments One of the strongest and most widely used quasi-experimental designs. . Differs from experimental designs because test and control groups are not equivalent. Comparing pretest results will indicate degree of equivalency between experimental and control groups.

Quasi-Experimental Design (cont) Aim of the Research Name of the Notation Design Paradigm Comments To determine the influence of a variable introduced only after a series of initial observations and only where one group is available Time series experiment O»O»X»O»O If substantial change follows introduction of the variable. repeat the experiment in different places under different conditions. then the variable can be suspect as to the cause of the change. . To increase external validity.

.Quasi-Experimental Design (cont) Aim of the Research To bolster the validity of the above design with the addition of a control group Name of the Design Control group time series Notation Paradigm O»O»X»O»O O»O»-»O»O Comments A variant of the above design by accompanying it with a parallel set of observations without the introduction of the experimental variable.

sometimes absent. off-again design in which the experimental variable is sometimes present.Quasi-Experimental Design (cont) Aim of the Research To control history in time designs with a variant of the above design Name of the Design Equivalent timesamples Notation Paradigm [X1 » O1] »[X0 » O2] » [x1 » O3] Comments An on-again. .