Research Chapter 10 Test 2

Front 1

Group

Back 1

= treatment of data, rather than how the treatment is administered.
o Treatment (IV) may be administered to one participant at a time, but data from those individuals are “grouped” for analysis
o First, the randomized controlled trial is presented.
o Then, several of different single and multiple factor research designs are outlined.

Front 2

Underlying assumption

Back 2

: the statistically significant differences will NOT represent true difference between or among groups. (just probabilities)

Front 3

Samples of population

Back 3

can’t be truly random

Front 4

Results of a valid experiment

Back 4

cannot be generalized to the population as a whole

Front 5

RCT are prospective and experimental

Back 5

o Independent (treatment) variable is subject to the controlled manipulation of the investigator
• At least 2 levels (includes a treatment group and control group)
o Dependent ( measurement or outcome) variables are collected under controlled conditions

Front 6

Phase 1 pharmacological agents research

Back 6

o Phase I: usually conducted on a single group of healthy volunteers- establishing safety a different doses

Front 7

Phase 2 pharmacological agents research

Back 7

o Phase II: small group of pts- evaluate effectiveness
• Phase II is either non randomized or randomized

Front 8

Phase 3 pharmacological agents research

Back 8

: new drug compaired to placebo or the accepted standard treatment

Front 9

Caution about RCTs

Back 9

o It is practically impossible to obtain a true random sample of a population
o Two roadblocks
• ID all members of a clinical population
• Researchers can only use volunteers

Front 10

Single Factor Experimental designs

Back 10

o Have one independent variable
o Pretest- posttest control group design
o Calls for at least 2 groups randomly selected from the population of interest and randomly assigned to one group or another.
o Performance on the dependent variable(s) is measured and equivalence on the dependent variable(s) is determined statistically.
o When there are 2 groups, one will receive treatment (independent variable) and the other group will not.
o At the end of the treatment period, performance on the dependent variable(s) is measured again.

Front 11

Between groups design (parallel group design)

Back 11

R O X O
R O O R= participants assigned randomly to the two groups
O= observation, or measurement
X= an intervention, manipulation
Blank= control group
Intervention and control are the two levels of the independent variable

Front 12

o In clinical research, the pretest-posttest control group is altered slightly:

Back 12

R O X1 O
R O X2 O
• This alteration is made when the researcher does not believe it is ethical to withhold treatment altogether when two treatments are known to be effective and the researcher wishes to compare their effectiveness.
• One group receives typical treatment. The other receives experimental treatment. A control group receiving a standard treatment can be referred to as an active control group.

Front 13

Single group pretest- posttest design (Within- group design)

Back 13

O X O
o Neither an RCT nor a between group design
• Since there is only one group, no opportunity for random allocation of participants into groups or is there any between group comparison to be made.
• Comparisons are made within the single experimental group

Front 14

Nonequivalent Control group Design (between group design)

Back 14

o Used when a nonrandom control group is available for comparison
O X O
-----------------
O O
• The dotted line indicates that participants were not randomly assigned to groups (Not a RCT), not control for extraneous subject factors that might explain the differences in results between groups

Front 15

Repeated Measures or Repeated Treatment Designs

Back 15

• Same participants are measured under all the levels of the independent variable.
• Any pretest=posttest designs can be considered a repeated measures design because each participant is measured at both levels (before and after treatment) of a possible independent variable.
• Each participant gets more than one actual treatment
• RCT with cross over design: order in which participants receive intervention is randomized

Front 16

Order effects:

Back 16

the order in which the treatments are presented may influence an outcome.

Front 17

Carryover effects:

Back 17

it is possible that a treatment has a specific effect on the treatment that follows it, either enhancing or diminishing performance.
• Two strategies to select treatment orders in a repeated measures design:
o Randomly select an order and then rotate the starting position
o Use a latin square technique: ensures no only that each condition appears at each position equally often, but also that each condition precedes and follows every other condition equally often.
• Greater randomization than random start with rotation

Front 18

Multiple Factor Experimental Designs

Back 18

• Questions that Lead to a multiple factor design:
o Used because researchers are interested not only in the independent effects of the multiple factors on the dependent variable, but also in the effects on the interaction between the multiple factors (IV) on the dependent variable
Factorial vs. nested designs
Type of treatment x therapist design from above is a factorial design; factors are crossed looking for interactions

Front 19

Multiple factor experimental designs-Between Groups, Within group, and Mixed Designs:

Back 19

o Between groups: different groups get different levels of researcher- manipulable treatments.
o Within group: all participants receive all experimental conditions (All levels of the IV)
o Mixed Design: at least one between subjects factor and one within subjects factor
• Eliminate the time variable as an IV
o Usually one of the IV is manipulable (within factor), one is not ( assigned or attribute= between factor)