• Shuffle
    Toggle On
    Toggle Off
  • Alphabetize
    Toggle On
    Toggle Off
  • Front First
    Toggle On
    Toggle Off
  • Both Sides
    Toggle On
    Toggle Off
  • Read
    Toggle On
    Toggle Off
Reading...
Front

Card Range To Study

through

image

Play button

image

Play button

image

Progress

1/77

Click to flip

Use LEFT and RIGHT arrow keys to navigate between flashcards;

Use UP and DOWN arrow keys to flip the card;

H to show hint;

A reads text to speech;

77 Cards in this Set

  • Front
  • Back
How do you MAXIMIZE POWER?
1. DECREASING the susceptibility of the DV measure to MEASUREMENT random) ERROR.

2. ONE-TAILED TEST

3. MAXIMIZE DIFFERENCES between TXT groups.

HOW DO YOU MAXIMIZE POWER?
What does a split-plot (mixed) design involve?
~1 BETWEEN-GROUPS VARIABLE

~1 WITHIN-SUBJECTS VARIABLE.

What does a split-plot (mixed) design involve?
What is involved in a Randomized Block Design?
In a randomized block design, at least one of the IVs is a BLOCKING (extraneous) VARIABLE, & subjects W/I each block are randomly assigned to levels of another IV. The extraneous variable is statistically analyzed.

What is involved in a Randomized Block Design?
What is the Solomon Four-Group Design used for?
Used to measure the effects of PRETESTING on a study's Internal and External Validity.

What is the Solomon Four-Group Design used for?
What is the Latin Square Design used for?
A WITHIN SUBJECTS DESIGN.

The order of the different levels of the independent variable(s) are COUNTERBALANCED (applied to different subjects or subgroups of subjects in a different order).

What is the Latin Square Design used for?
When do you use a One-Way Anova?
-1 IV, 1 DV

-Compare 2 or more independent groups/means.

KEEP IN MIND THAT TO OBTAIN AN F-RATIO, IT INVOLVES COMPARING BETWEEN-GROUP VARIABLITY TO WITHIN GROUP VARIABILITY

When do you use a One-Way Anova?
What type of data is used when using the Chi-Square?
The chi-square (either SINGLE SAMPLE OR MULTI-SAMPLE, is used to compare NOMINAL (frequency) data.

What type of data is used when using the Chi-Square?
When do you use a T-Test for a Single Sample?
The T-Test for a Single Sample is used to COMPARE AN OBTAINED SAMPLE MEAN TO A KNOWN POPULATION MEAN.

When do you use a T-Test for a Single Sample?
Define a Quasi-Independent Variable.
Treat the ORGANISMIC VARIABLE like an IV.

Define a Quasi-Independent Variable.
What is SAMPLING ERROR due to? Results?
DUE TO RANDOM FACTORS

PRODUCES A NON-REPRESENTATIVE SAMPLE

What is SAMPLING ERROR due to? Results?
What are the STANDARD ERRORS (eg MEASUREMENT, MEAN, ESTIMATE)?
Indicates the degree w/ which these estimates can be expected to DEVIATE from TRUE VALUES.

What are the STANDARD ERRORS (eg MEASUREMENT, MEAN, ESTIMATE)?
Why would you use a SINGLE SUBJECTS DESIGNS?
When it's too difficult to WITHOLD TXT.

Why would you use a SINGLE SUBJECTS DESIGNS?

Why would you use a SINGLE SUBJECTS DESIGNS?
What is the CORRECTION FOR GUESSING FORMULA?
Corrected Score =

(R) - (W/n-1)

R = number of right answers, W = number of wrong answers, and n = the number of choices per answer.

What is the CORRECTION FOR GUESSING FORMULA?
WHAT IS A QUASI-INDEPENDENT VARIABLE?
WHEN AN ORGANISMIC VARIABLE IS TREATED LIKE AN IV.
What is REGRESSION ANALYSIS USED FOR?
PREDICT Y (CRITERION) USING an X (PREDICTOR)

What is REGRESSION ANALYSIS USED FOR?
IN MULTIPLE REGRESSION, WHAT DOES IT MEAN WHEN THERE IS AN INVERSE CORRELATION BETWEEN A PREDICTOR AND THE CRITERION?
-AS ONE VALUE ON ONE VARIABLE INCREASE, THE VALUES OF THE OTHER VARIABLE DECREASE

-LL a NEGATIVE SIGN

IN MULTIPLE REGRESSION, WHAT DOES IT MEAN WHEN THERE IS AN INVERSE CORRELATION BETWEEN A PREDICTOR AND THE CRITERION?
What is a MEDIATOR VARIABLE?
A mediating (intervening) variable EXPLAINS (is responsible for) the RELATIONSHIP between an IV and DV.

What is a MEDIATOR VARIABLE?
What is the MODERATOR VARIABLE?
* A moderator variable INFLUENCES the nature of the relationship between the IV and DV. E.G. level of depression affects the relationship between type of therapy and therapy outcome.

*"DIFFERENTIAL VALIDITY"

What is the MODERATOR VARIABLE?
When would you use a ONE-WAY ANOVA?
*1 IV

*1 DV

*2 INDEPENDENT GROUPS

When would you use a ONE-WAY ANOVA?
When would you use a FACTORIAL ANOVA?
*2 OR MORE IV (2 WAY = 2 IV's)

When would you use a FACTORIAL ANOVA?
When would you use a MANOVA?
*1 OR MORE IV & 2 OR MORE DV

When would you use a MANOVA?
What is ETA used for?
ASSESSES NON-LINEAR RELATIONSHIPS; BOTH ARE INTERVAL OR RATIO

What is ETA used for?
What occurs in an ANCOVA?
STATISTICALLY REMOVES VARIABILITY IN DV DUE TO EV

What occurs in an ANCOVA?
What are the SD and CI in a NORMAL DISTRIBUTION?
*1 SD = 68

*2 SD = 95

*3 SD = 99

What are the SD and CI in a NORMAL DISTRIBUTION?
When would you use the TUKEY?
*POST HOC

*LEAST RISK TO TYPE I

*PAIRWISE WHEN EQUAL SIZE GROUPS

When would you use the TUKEY?
When would you use the FISHER LSD?
*POST HOC

*LEAST RISK TO TYPE II

*PAIRWISE AND COMPLEX

When would you use the FISHER LSD?
What happens to CONFIDENCE when ALPHA decreases?
It INCREASES AS ALPHA DECREASES
What is the RELIABILITY COEFFICIENT RANGE?
0 TO +1


What is the RELIABILITY COEFFICIENT RANGE?
What is the VALIDITY COEFFICIENT RANGE?
-1 TO +1



What is the VALIDITY COEFFICIENT RANGE?
Describe MULTI-TRAIT, MULTI-METHOD and TRAITS.
CONVERGENT VALIDITY-ONE TRAIT TWO METHODS

DIVERGENT VALIDITY-TWO TRAITS ONE METHOD

Describe MULTI-TRAIT, MULTI-METHOD and TRAITS.
What are some examples of NOMINAL data?
-ATTITUDE (e.g. yes or no)
-GENDER
-HAIR COLOR

What are some examples of NOMINAL data?
What are some examples of ORDINAL data?
-WIN/PLACE/SHOW
-LIKERT-SCALE SCORES
-SAFE SEX PRACTICES
-RANKS (1ST, 2ND, 3RD)

What are some examples of ORDINAL data?
What are some examples of INTERVAL data?
-MOST STANDARDIZED TESTS
-IQ TESTS SCORES
-TEMPERATURE (FARENHEIT & CELSIUS, NOT KELVIN)


What are some examples of INTERVAL data?
What are some examples of RATIO data?
-REACTION TIME IN SECONDS
-# OF AGGRESSIVE ACTS


What are some examples of RATIO data?
What are some NON-PARAMETRIC TESTS? (e.g when using ORDINAL DATA)
-WILCOXON MATCHED PAIRS ( 2 CORR GROUPS)

-MANN-WHITNEY U (2 INDEP GROUPS)

-KRUSKALL-WALLIS (2 + GROUPS)



What are some NON-PARAMETRIC TESTS? (e.g when using ORDINAL DATA)
Describe the following VARIABLES:

-CONTINUOUS
-DISCRETE
-MANIPULATED & ORGANISMIC
-CONTINUOUS V = CAN BE INFINITE # OF VALUES

-DISCRETE V = LIMITED

-MANIPULATED & ORGANISMIC V = M IS CONTROLLED BY E, O IS A CHARACTERISTIC OF THE SUBJECTS

Describe the following VARIABLES:
When you have a distribution that is skewed, which Measures of Central Tendency do you use?
-Mo or MODE (the most frequent score)

-also, Mo can be used with either NOIR.

When you have a distribution that is skewed, which Measures of Central Tendency do you use?
THREATS TO INTERNAL VALIDITY
-MATURATION
-HISTORY
-TESTING
-INSTRUMENTATION
-STATISTICAL REGRESSION
-SELECTION
-ATTRITION
-INTERACTION WITH SELECTION


THREATS TO INTERNAL VALIDITY
What are some THREATS TO EXTERNAL VALIDITY?
-PRE-TESTING
-SELECTION-TXT INTERACTION
-REACTIVITY
-PRACTICE, ORDER OR CARRYOVER EFFECTS


What are some THREATS TO EXTERNAL VALIDITY?
Is IPSATIVE Relative or Absolute?
RELATIVE



Is IPSATIVE Relative or Absolute?
Is NORMATIVE absolute or relative?
ABSOLUTE



Is NORMATIVE absolute or relative?
What are the assmumptions of PARAMETRIC TEST?
-NORMALLY DISTRIBUTED

-HOMOSCEDASTICITY

-DATA IS MEAS ON I or R

(IF THERE ARE ANY VIOLATIONS USE NONPARAMETRIC TESTS)

What are the assmumptions of PARAMETRIC TEST?
What is TYPE I ERROR?
-TRUE NULL HO REJECTED

(SAYING YOUR STUDY WAS SIGNIFICANT WHEN IT WASN'T)



What is TYPE I ERROR?
What is TYPE II ERROR?
-FALSE NULL HO RETAINED

(SAYING YOUR STUDY WAS INSIGNIFICANT WHEN IN FACT IT WAS)

(REALLY BAD: TELLING A SICK PT HE/SHE DOESN'T HAVE CANCER, AND YOU DON'T GIVE THEM TXT, WHEN IN FACT HE/SHE DOES HAVE IT AND NEEDS CHEMO)




What is TYPE II ERROR?
What does it meant to have POWER?
ABILITY TO REJECT A FALSE NULL OR SAY YOUR STUDY FOUND SIGNIFICANCE.

What does it meant to have POWER?
What are the MULTIVARIATE TECHNIQUES?
P-L

-PATH ANALYSIS (OBSERVED VARIABLES ONLY)

and

-LISREL (OBSERVED & LATENT VARIABLES)

What are the MULTIVARIATE TECHNIQUES?
What is the difference between QUANTITATIVE VS. QUALITATIVE VARIABLES?
QUANTITATIVE = YOU CAN COMPARE PPL IN TERMS OF ORDERING (E.G. HEIGHT)

QUALITATIVE = PLACES PPL IN UNORDERED CATEGORIES (E.G. GENDER)

What is the difference between QUANTITATIVE VS. QUALITATIVE VARIABLES?
True or False: A SMALLER SAMPLE SIZE = LARGER STANDARD ERROR OF THE MEAN
TRUE.
How do you reduce the VARIABILITY of a group of sample means?
INCREASE THE NUMBER OF SCORES IN EACH SAMPLE.

How do you reduce the VARIABILITY of a group of sample means?
What are LONGITUDINAL studies?
Investigate the ppl of the same age over LONG PERIODS OF TIME. Overcome cohort effects but have drawbacks of time and cost.

What are LONGITUDINAL studies?
What are CROSS-SECTIONAL STUDIES?
Studies that EVALUATE changes OVER TIME by comparing groups of people of DIFFERENT AGES at the same time. (Cohort Effects)

What are CROSS-SECTIONAL STUDIES?
What are CROSS-SEQUENTIAL studies?
(cohort sequential) – COMBINES Cross Sectional & Longitudinal Data by studying the effects of an IV by assessing two different groups at two different times. Provides data for detecting and evaluating cohort effects.

What are CROSS-SEQUENTIAL studies?
What is Interval Recording?
-Observing behavior divide into equal time intervals.

-For behaviors having no clear beginning and end.

What is Interval Recording?
What is Event Sampling?
-Observe behaviors each time it occurs. Good

-Good for infrequent behaviors
having a long duration

-Leaving a permanent record (could be something like quiz grades)

What is Event Sampling?
What is Situational Sampling?
-Observing a behavior in a number of different settings.

What is Situational Samling?
What is Situational Analysis?
Coding behavioral sequences rather than isolated behavioral events

-Used to study COMPLEX SOCIAL BEHAVIORS

What is Situational Analysis?
TRUE or FALSE: The more difficult it is to make a Type I error, the easier it becomes to make a type II error.
TRUE

TRUE or FALSE: The more difficult it is to make a Type I error, the easier it becomes to make a type II error.
What does Counterbalancing do?
Helps control for CARRYOVER effect by presenting different levels of IV in different orders

What does Counterbalancing do?
Describe SINGLE SUBJECTS DESIGNS
-Subjects serve as their own control

-Multiple baseline

-Reversal-Removes a treatment (Not Ethical for patients)

Describe SINGLE SUBJECTS DESIGNS
HOW DO YOU CALCULATE THE DF FOR CORRELATED SAMPLES?
The degrees of freedom for the correlated samples is total number of PAIRS of scores -1

HOW DO YOU CALCULATE THE DF FOR CORRELATED SAMPLES?
What does the BONFERRONI TEST help with?
The Bonferroni test helps control the experiment wise error rate by REDUCING the alpha for each test.

What does the BONFERRONI TEST help with?
How do you calculate the DF for ANOVAs?
Degrees of freedom = (C-1) (N-C)

C= Number of levels of the IV N= number of Subjects

CALCULATING THE DF FOR ANOVAS
What is the Scheffe S test used for?
The Scheffe HOLDS the EXPERIMENTWISE ERROR RATE CONSTANT. Use involves a critical value ensuring that the probability of making a Type I error does not exceed that of the overall ANOVA.

What is the Scheffe S test used for?
Describe CHI-SQUARE TESTS
-Observed frequency in NOMINAL data.

-Simple Chi-square requires independence of data - uncorrelated samples.

-Expected frequencies = Total Observations/Number of categories (levels)

-Degrees of freedom = (ROWs-1)*(COLUMNS-1)

Describe CHI-SQUARE TESTS
What is Eigenvectors?
-A type of factor analysis.

-No. of initially identified components are uncorrelated (orthogonal) is equal to the number of variables. The components are uncorrelated and are extracted so that the first component explains the greatest amount of variance and the second variable the second greatest variance…etc.

What is Eigenvectors?
What is Communality?
– A measure of "common variance" –

What is Communality?
What is Multicolinearity?
Multicolinearity – high correlations between predictors in a multiple regression equation - undesirable.

What is Multicolinearity?
What is an "Effect Size"?
"Effect Size"
is a type of standard score indicating the difference between the experimental group mean and the control group in terms of standard deviation units. An effect size of 1.0 means the experimental group mean is one standard deviation above the mean.

What is an "Effect Size"?
Describe TETRACHORIC design
BOTH ARE ARTIFICIAL DICHOTOMIES


Describe TETRACHORIC design
Describe BISERIAL variables
ONE IS ARTIFICAL DICHOTOMY AND ONE IS INTERVAL OR RATIO (CONTINOUS)variables

Describe BISERIAL variables
Describe POINT BISERIAL variables
ONE IS TRUE DICHOTOMY AND ONE IS INTERVAL OR RATIO (CONTINOUS)variables.

Describe POINT BISERIAL variables
Describe CONTINGENCY variables
BOTH ARE NOMINAL variables

Describe CONTINGENCY variables
Describe SPEARMAN RANK ORDER variables
BOTH VARIABLES ARE RANK ORDERED

Describe SPEARMAN RANK ORDER variables
What are the CENTRAL LIMIT THEOREM PREDICTIONS?
1. The SAMPLING DISTRIBUTION of MEANS INCREASLING APPROACHES NORMAL as the SAMPLE SIZE INCREASES regardless of the shape of the population distribution

2. The MEAN of the SAMPLING DISTRIBUTION of MEANS EQUALS the POPULATION MEAN.

3. The STANDARD DEVIATION of the SAMPLING DISTRIBUTION of MEANS (STANDARD ERROR OF MEANS) EQUALS the POPULATION STANDARD DEVIATION divided by the SQUARE ROOT of the SAMPLE SIZE.


What are the CENTRAL LIMIT THEOREM PREDICTIONS?
Describe ETA variables
-A type of Correlation Coefficient

-Assess the relationship between 2 CONTINOUS variables, when the variables relationship is NONLINEAR

Describe ETA variables
Describe SPEARMAN RHO variables
2 RANK-ORDERED variables

Describe SPEARMAN RHO variables
Describe PEARSON R variables
2 CONTINOUS variables

Describe PEARSON R variables