Psychological Assessment

Intelligence, Developmental, Aptitude, Achievement Tests (Table)

Source: Cohen & Swerdlik (2018), Kaplan & Saccuzzo (2018), Gravetter & Wallnau (2013)
Terms to Remember:
o Descriptive Statistics – used to summarize, organize, and simplify data
o Inferential Statistics – measurement of the extent to which pairs of related values on 2 variables tend to change together; drawing conclusions or inferences
about population based on samples
 Allows to study samples and make generalizations to about the population selected
o Parametric Tests – assumed normal distributions; requires numerical scores for each participants
o Nonparametric Tests – little to no information about the population; participants are just classified into categories
o Independent Groups – sample values selected from one population are not related in any way to sample values selected from the other populations
o Dependent Groups – provide information about subjects in other groups
o ANOVA – used to evaluate mean differences between two or more treatments (populations)
o T-Test - used to test hypotheses about an unknown population mean and variance
o Chi-Square – measures the relationship between categorical/non-numerical data

Differences/Correlation Level of Data No. of Description

Groups
Correlation
Pearson R Correlation Interval/Ratio + 2 o Quantifies a linear relation between two scale variables
Interval/Ratio o Single number is used to describe the direction and
(Continuous) strength of the relation between two variables
Spearman Rho’s Correlation Ordinal + 2 o Measure of the agreement between two rankings
Ordinal o More sensitive to error and discrepancies
(Ranking) o Larger values
o Calculations based on deviations
o Measures consistencyꟷwhen two variables are
consistently related, their ranks are linearly related
Kendall’s Coefficient of Correlation Ordinal + 3 or more o Measure of the agreement between two or more rankings
Concordance W Ordinal + o Has smaller gross error sensitivity and smaller
Ordinal asymptotic variance
(Ranking) o Usually smaller values
o Calculations based on concordant and discordant pairs
o An index of interrater reliability of ordinal data
Point-Biserial Coefficient Correlation Nominal 2
(Dichotomous)
+ Interval/Ratio
 Psychological Assessment
Intelligence, Developmental, Aptitude, Achievement Tests (Table)
Source: Cohen & Swerdlik (2018), Kaplan & Saccuzzo (2018), Gravetter & Wallnau (2013)
(Continuous)
Phi or Fourfold Coefficient Correlation Nominal + 2
Nominal
Rank Biserial Correlation Nominal 2
(Dichotomous)
+ Ordinal
(Ranking)
Tetrachoric R Correlation Artificial 2
Dichotomous +
Artificial
Dichotomous

(supposed to be
interval/ratio
but labelled as
nominal)
Inferential Statistics
Z-Scores Differences Interval 1-2 o Describe the exact location of any specific sample mean
within distributions of sample means
T-test
1. Independent Samples Difference DV: 2 or more 2 o Also known as Independent T-Test, Independent
(Subjects) Measure T-Test, Independent Two-Sample T-Test,
Nominal Unpaired T-Test
o Between-Subjects design
IV: 2 o Compares the means of two independent groups in order
(Treatments) to determine whether there is a statistical evidence that
Interval/Ratio the associated population means significantly differently
o Must have equal variances, independent, and normally
Experimental + distributed
Control o Parametric Test
2. Dependent Samples Difference DV: 1 1 o Also known as Paired T-Test or Paired-Samples T-Test
(Subjects) o Within Subjects
Nominal o Compares means of two related groups to determine
whether there is a statistically difference between these
IV: 2 means
(Treatment) o Same participants are present in both groups
Interval/Ratio
 Psychological Assessment
Intelligence, Developmental, Aptitude, Achievement Tests (Table)
Source: Cohen & Swerdlik (2018), Kaplan & Saccuzzo (2018), Gravetter & Wallnau (2013)
o Fewer subjects
Before + After o Suited for studying learning, development, or other
changes that takes place over time
o Reduces or eliminates problems caused by individual
differences
o Allow factors other than the treatment effect to cause a
participant’s score to change from one treatment to next
o E.g., pre-test-post-test
3. Proportions/Percentages
4. Variances
5. 2 Correlation Differences 2 o Used to assess the significance of the difference between
Coefficients two correlation coefficients found in two independent
samples
6. One Sample T-Test Differences Interval/Ratio 1 o Whether the mean of a population is statistically
different from a known or hypothesized value
o Test variable’s mean is compared against a “test value”
which is a known or hypothesized value of the mean in
the population
Regression Equation
Linear Regression of Y on Prediction Interval 2 o Y = a + bX
X o A and B are unknown constants know as intercept
Y – DV and slope of the equation
X - IV o Used to predict the unknown value of variable Y
when value of variable X is known
o Y’s coefficient will change if there would be an
increase in X
Linear Regression of X on Prediction Interval 2 o X = c + dY
Y o Used to predict the unknown value of variable X
Y – IV using the known variable Y
X - DV
Coefficient of Determination
ANOVA
1.1 One-Way Within- Differences DV: 1 1 o Compares means of 1-2 independent groups in order to
Groups ANOVA determine whether there is statistical evidence that the
e.g., female associated population means are significantly different
o Analyze data from field studies, experiments, quasi
 Psychological Assessment
Intelligence, Developmental, Aptitude, Achievement Tests (Table)
Source: Cohen & Swerdlik (2018), Kaplan & Saccuzzo (2018), Gravetter & Wallnau (2013)
IV: 1 but more experiments
than 2 levels o If the grouping variable has two groups, then the
(Categorical) results of one-way ANOVA and independent samples
T-Test will be EQUIVALENT
e.g., 3pm (High o Denoted as F
Blood Pressure o Within-Subjects, Repeated Measures
or Low Blood o Determine whether the differences that are found
Pressure), 5pm between treatment conditions are significantly greater
(High Blood that would be expected if there is not treatment effect
Pressure or
Low Blood
Pressure), 6pm
(High Blood
Pressure or
Low Blood
Pressure)
1.2 One-Way Between- Differences DV: 2 or more 2 or more o Independent Groups, Between-Subjects
Groups ANOVA
E.g., Boys &
Girls

IV: 1 but more

than 2 levels
each

e.g., low,
medium, high
usage
2. Two-Way ANOVA Differences DV: 1 or more 1-2 o Hypothesis test that includes two nominal IV, regardless
(Factorial ANOVA) of their numbers of levels and a scale dependent variable
e.g., Age group o Mixed ANOVA
(Adolescence, o Two-factor
Young
Adulthood,
Middle
Adulthood)
 Psychological Assessment
Intelligence, Developmental, Aptitude, Achievement Tests (Table)
Source: Cohen & Swerdlik (2018), Kaplan & Saccuzzo (2018), Gravetter & Wallnau (2013)
IV: 1-2
regardless of
the no. levels

E.g., Therapy
Techniques &
Monthly report
of improvement
Multivariate Analysis of Differences o More than one dependent variable
Variance o Provides regression analysis and ANOVA for multiple
dependent variables by one or more factor variables or
covariates
Analysis of Covariance Differences o A covariate is included so that statistical findings reflect
effects after a scale variable has been statistically
removed
o Analyzes the differences between three or more groups
while controlling the effects of at least one continuous
covariate
Chi-Square
Goodness of Fit Differences Categorical o Measure of how well a statistical model fits a set of
observations
o High = values expected based on the model are close
to the observed values
o Allows to draw conclusions about the distribution of a
population based on a sample
o Used when you want to test a hypothesis about
distribution one 1 categorical variable
o Data Binning – converting categorical variable to
continuous by separating variables into intervals
Independence Differences Categorical 2 o non-parametric
o used to determine whether your data are significantly
different from what you expected
o aka Chi-Square test of independence
o based on observed frequencies
Non-Parametric Tests
Median Test Differences Ordinal o used to test whether two (or more) independent groups
 Psychological Assessment
Intelligence, Developmental, Aptitude, Achievement Tests (Table)
Source: Cohen & Swerdlik (2018), Kaplan & Saccuzzo (2018), Gravetter & Wallnau (2013)
differ in central tendency (mean, median, mode)
Fischer’s Sign Test Differences Ordinal o alternative to paired t-test, chi-square
o knowing whether the proportions for one variable are
different among values of other variable
Wilcoxon Rank Sum Test Differences Ordinal o when the requirements for t-test for two independent
samples are not satisfied
o Paired T-test
Mann-Whitney (U) Test Differences Ordinal 2 o evaluates the difference between two groups of scores
(Independent T-Test) from an independent-measures design
o Unpaired T-test, Independent T-test
Wilcoxon Signed Ranks Differences Ordinal 2 o evaluates the differences between two groups of scores
Tests (T) (Paired from a repeated-measures design
T-Test/Dependent T-Test)
Kruskal-Wallis H Test Differences Ordinal 3 or more o evaluates differences between three or more groups from
(One-Way Between Groups an independent-measures design
ANOVA)
Friedman Rank (Repeated Differences Ordinal 3 or more o evaluates differences among three or more groups from a
Measures ANOVA) repeated-measures design
Spearman Rho (Pearson R) Ordinal