BIAS: SYSTEMATICALLY FAVORING CERTAIN OUTCOMES.

VOLUNTARY RESPONSE: GIVING PEOPLE THE CHANCE TO RESPOND OR NOT - NOT SEEKING OUT YOUR SAMPLE.

CONVENIENCE SAMPLING: SELECTION OF WHICHEVER INDIVIDUALS ARE EASIEST TO REACH

EXAMPLES: CALL OR WRITE IN SURVEYS; MALL INTERVIEWS

A SAMPLE CHOSEN BY CHANCE ALLOWS NEITHER FAVORITISM BY THE SAMPLER NOR SELF-SELECTION BY RESPONDENTS.

** IT GIVES INDIVIDUALS AN EQUAL CHANCE OF BEING CHOSEN FOR THE STUDY.

EXAMPLE: PLACE NAMES IN A HAT AND DRAW OUT A HANDFUL.

** ONE OF THE MOST COMMON THREATS TO INTERNAL VALIDITY

PSEUDO-EXPERIMENT:

* VERY VULNERABLE TO INDIVIDUAL DIFFERENCES

* RESEARCH DESIGN IN WHICH SOMEONE TESTS A CLAIM ABOUT A VARIABLE BY EXPOSING PEOPLE TO THE VARIABLE OF INTEREST AND NOTING THAT THESE PEOPLE FEEL, THINK, OR BEHAVE AS EXPECTED.

USE THE EXPERIMENTAL METHOD TO REDUCE THIS TYPE OF PROBLEM.

-- THREAT TO BOTH EXTERNAL AND INTERNAL VALIDITY

-- SAMPLING TECHNIQUE FAVORS ONE TYPE OF PERSON OR GROUP à MAKES IT DIFFICULT TO DRAW CONCLUSIONS ABOUT THE GENERAL POPULATION!

SELECTION BIAS: SAMPLING PEOPLE FROM AN UNREPRESENTATIVE SAMPLE (BY USING IMPERFECT SAMPLING TECHNIQUES).

EXAMPLE: SELECTING NAMES FOR POLLS BY USING THE PHONE BOOK OR AUTOMOBILE REGISTRATION RECORDS.

NONRESPONSE BIAS: RESPONDENTS THEMSELVES ARE THE SOURCE OF BIAS. DIFFERENCE IN THOSE WHO RESPOND, LOW RESPONSE RATES

EXAMPLE: TYPE OF MAGAZINE YOU USE WILL INFLUENCE THE PEOPLE SURVEYED (I.E., TV GUIDE).

IF WE WISH TO MAKE GENERAL STATEMENTS ABOUT HUMAN NATURE, WE SHOULD TRY TO SAMPLE A WIDE VARIETY OF HUMAN BEINGS IN OUR RESEARCH.

EXAMPLE: CROSS-CULTURAL RESEARCH

** DIFFERENCES IN THE SAME PERSON ACROSS TIME AND SITUATIONS CAN SOMETIMES DO THE SAME THING AS DIFFERENCES BETWEEN PEOPLE.

** EACH REPRESENT COMMON THREATS INTERNAL VALIDITY.

HISTORY: REFERS TO GENERAL CHANGES OCCURRING IN A VERY LARGE GROUP OF PEOPLE SUCH AS A NATION OR A CULTURE. EXAMPLE: FAMINE IN A PARTICULAR CULTURE OR REGION

MATURATION: SUBJECTS MAY CHANGE BETWEEN CONDITIONS OF AN EXPERIMENT EXAMPLE: THIS IS A BIG PROBLEM FOR RESEARCH WITH CHILDREN BECAUSE THEY CHANGE MORE RAPIDLY OVER TIME THAN DO ADULTS.

** THREAT TO INTERNAL VALIDITY

** TENDENCY FOR PEOPLE WHO RECEIVE HIGH OR LOW SCORES ON A PARTICULAR MEASURE TO SCORE CLOSER TO THE MEAN ON A SUBSEQUENT TESTING.

(SIMPLE THINGS LIKE LUCK OR NOT HAVING YOUR COFFEE - CAN MAKE A DIFFERENCE).

TRUE SCORE: AN UNDERLYING ABILITY OR TRAIT THAT THE OBSERVED SCORE PRESUMABLY REFLECTS.

** TRUE SCORES ARE MUCH MORE STABLE THAN OBSERVED SCORES.

PERFORMANCE/OBSERVED SCORES ARE ALSO INFLUENCED BY ERROR (CHANCE FACTORS THAT INFLUENCE PERFORMANCE). EXAMPLE: BEING TIRED, ROOM TEMPERATURE ETC

** DECREASE THIS PROBLEM BY USING A REAL EXPERIMENT: THE KINDS OF STUDIES THAT ARE MOST LIKELY TO BE INFLUENCED BY REGRESSION TOWARD THE MEAN ARE PRETEST-POSTTEST STUDIES THAT DO NOT INVOLVE A CONTROL GROUP.

HAWTHORNE EFFECT: THE ACT OF STUDYING PEOPLE CAN DRAMATICALLY CHANGE THE WAY THAT PEOPLE BEHAVE

** THREAT TO INTERNAL VALIDITY

** BEING IN AN EXPERIMENT OR BEING TESTED WILL INFLUENCE PEOPLE’S PERFORMANCE IN A LATER EXPERIMENT OR ADMINISTRATION OF THE TEST.

ATTITUDE POLARIZATION: THINKING ABOUT ATTITUDES à MAY STRENGTHEN THOSE ATTITUDES

1. CONDUCT A TRUE

2. DON’T GIVE A PRETEST

3. WAIT AS LONG AS POSSIBLE TO ADMINISTER YOUR POSTTEST OR USE ALTERNATE VERSION OF THE TEST.

PARTICIPANTS THAT DO NOT COMPLETE THE STUDY

** CAN REPRESENT A THREAT TO INTERNAL VALIDITY, EXTERNAL VALIDITY OR BOTH.

** PEOPLE MAY BECOME BORED, MIGHT MOVE AWAY ETC.

HOMOGENEOUS ATTRITION: AN EQUAL LEVEL OF ATTRITION ACROSS ALL OF THE EXPERIMENTAL CONDITIONS (PROPORTION OF THE PEOPLE WHO DROPPED OUT OF THE STUDY (ATTRITION) IS EXACTLY THE SAME IN TWO DIFFERENT CONDITIONS).

HETEROGENEOUS ATTRITION: THE ATTRITION RATES IN TWO OR MORE CONDITIONS OF AN EXPERIMENT ARE NOTICEABLY DIFFERENT. AFTER HETEROGENEOUS ATTRITION, THE PEOPLE IN ONE CONDITION OF THE STUDY ARE SYSTEMATICALLY DIFFERENT FROM THE PEOPLE IN SOME OTHER CONDITION OF THE STUDY.

1) KEEP PEOPLE FROM DROPPING OUT OF THE STUDY:

* COMMUNICATING THE PERSONAL OR SCIENTIFIC IMPORTANCE OF THE STUDY TO PARTICIPANTS AND PRESENTING IT TO PEOPLE WITH AUTHORITY AND ENTHUSIASM

* WARN PEOPLE THAT THE STUDY MAY NOT BE ALL THAT EXCITING

* SCHEDULE BREAKS OR REST POINTS FOR PARTICIPANTS

* OFFER PEOPLE SIGNIFICANT ACADEMIC OR FINANCIAL AWARDS FOR COMPLETING THE STUDY.

* EQUALIZE THE ATTRITION IN THE TWO CONDITIONS OF YOUR EXPERIMENT BY EXPOSING THE CONTROL GROUP TO AVERSIVE PART OF EXPERIMENT AFTER THEY HAVE DONE EVERYTHING ELSE.

• OCCURS ALMOST ANYTIME THAT PEOPLE REALIZE THAT THEY ARE BEING STUDIED.

1. PEOPLE MAY TRY TO DO WHAT THEY THINK THE RESEARCHER EXPECTS

2. PEOPLE MAY TRY TO DO THE OPPOSITE OF WHAT THEY THINK THE RESEARCHER EXPECTS

3. PEOPLE MAY TRY TO DO WHATEVER WILL MAKE THEM LOOK GOOD

DEMAND CHARACTERISTICS: CHARACTERISTICS OF AN EXPERIMENT ITSELF THAT SUBTLY SUGGEST HOW PEOPLE ARE EXPECTED TO BEHAVE. EXAMPLE, GUN SITTING ON TABLE

PARTICIPANT REACTANCE: THE TENDENCY OF PARTICIPANTS TO TRY TO DISCONFIRM AN EXPERIMENTER’S HYPOTHESIS

EVALUATION APPREHENSION: REFERS TO PEOPLE’S CONCERNS ABOUT BEING JUDGED FAVORABLY OR UNFAVORABLY BY ANOTHER PERSON.

** TAKE STEPS TO GUARANTEE THE ANONYMITY OR PRIVACY OF THEIR RESEARCH PARTICIPANTS.

* USE OF DECEPTION.

* KEEP PARTICIPANTS IN THE DARK/BLIND TO THE EXPERIMENTAL CONDITIONS TO WHICH THEY HAVE BEEN ASSIGNED. THE RESEARCH PARTICIPANTS DO NOT REALIZE THAT THEY ARE BEING STUDIED AT ALL/OBSERVATION

* INDIRECT MEASURES OF PEOPLE’S ATTITUDES AND OPINIONS - ASKING PARTICIPANTS TO MAKE SOME JUDGMENTS ABOUT ANOTHER PARTICIPANT’S BEHAVIOR. TRUE ATTITUDES WILL BE REVEALED IN HOW THEY EVALUATE OTHERS.

* MEASURING IMPLICIT ATTITUDES ETC. SELF-ESTEEM EXAMPLE = FLASH "I" SEE IF ASSOCIATION IS GOOD OR BAD. IDENTIFY THE WORD FLASHED ON SCREEN - BAD OR GOOD.

** THINGS THAT RESEARCHERS UNINTENTIONALLY ALLOW TO VARY ALONG WITH THEIR INDEPENDENT VARIABLES

1) EXPERIMENTER BIAS: EXPERIMENTER’S EXPECTATIONS ABOUT THEIR STUDIES BIAS THEIR EXPERIMENTAL OBSERVATIONS.

A) RESEARCHERS MAKE BIASED OBSERVATIONS IN AN EXPERIMENT

B) EVEN A PERFECTLY OBJECTIVE OBSERVER MIGHT OBSERVE DIFFERENCES IN THE BEHAVIOR OF PEOPLE IN DIFFERENT EXPERIMENTAL CONDITIONS

"I’LL SEE IT WHEN I BELIEVE IT": PARTICIPANTS MAY GET UNWITTINGLY CAUGHT UP IN EXPERIMENTER’S SELF-FULFILLING PROPHECIES.

** EXPERIMENTERS SHOULD KEEP THEMSELVES BLIND TO THEIR PARTICIPANT’S TREATMENT CONDITIONS:

* HAVE ONE RESEARCHER INTERACT WITH PARTICIPANTS WHILE A SEPARATE RESEARCHER KEEPS TRACK OF PARTICIPANTS’ EXPERIMENTAL CONDITIONS

* STANDARDIZE MOST ASPECTS OF THE INSTRUCTIONS THAT PARTICIPANTS RECEIVE (I.E., RECORDING AND PRESENTING IN AUDIOTAPED FORM).

* DOUBLE-BLIND PROCEDURE - BOTH THE EXPERIMENTER AND THE RESEARCH PARTICIPANTS ARE KEPT UNAWARE OF THE PARTICIPANTS’ TREATMENT CONDITIONS.

*** REPRESENTS A SERIOUS THREAT TO INTERNAL VALIDITY.

CONFOUND IS A BROAD TERM FOR ANY DESIGN PROBLEM IN WHICH SOME ADDITIONAL VARIABLE VARIES SYSTEMATICALLY ALONG WITH THE INDEPENDENT VARIABLE ("THIRD VARIABLE PROBLEM").

* TRY TO CONDUCT TRUE EXPERIMENTS - LESS LIKELY TO CONTAIN CONFOUNDS

MEASURE ANY VARIABLES THAT ARE SAID TO BE CONFOUNDED WITH YOUR RESEARCH.