Home > Flashcards > Print Preview
The flashcards below were created by user
flash581
on FreezingBlue Flashcards. What would you like to do?

Statistics
 an objective way of interpreting a collection of observations.
 Types of statistics – Descriptive techniques – Correlational techniques – Differences among groups

Inference
generalization of results to some larger extent/group

Sample
 a group of participants, treatments, or situations selected from a larger group
 a selection of people or items from the population
 easier/quicker to use

Population
 refers to all people or items with a particular characteristic of interest
 the larger group from which a sample is taken

Systematic sampling
 i.e picking every 100th name in phone book
 select a sample for telephone interviewing by selecting every 20th name in the student directory

Stratified random sampling
 Method of stratifying a population on some characteristic before random selection of the sample
 i.e picking 20 males from 1000 random 20 females from 1000 random

Random assignment
i.e assign id numbers to clients pick clients at random

Post Hoc
Justification that the sample repressents some groups at large

Central tendancy
 a single score that best represents all the scores
 Indication of the typical score in a data set
 – Mean – Median – Mode

Variability
 the degree of difference between each individual score and the central tendency score
 measures of how scores vary
 – Range – Interquartile range – Standard deviation

Standard Deviation
 an estimate of the variability of the scores of a group around the mean (Rmpa)
 measure of how much the score varies around the mean
 *spread of scores about the mean
 gives us the average amount by which the scores deviate from the mean

Variance
the square of the standard deviation

Mean
 Most frequently used measure of central tendency
 add all numbers divide by sum of participants
 influenced by extremes

Median
middle of all scores in order

Mode
most frequent score occuring

Range
 Highest lowest
 variability score

Confidence Interval
 Present an interval estimate of the population mean
 Indicates the interval within which we are confident the population mean will fall
 Centered around the sample mean
 Provies an expected upper and lower limit for a statistic at a specified probability level
 Can be represented in error bar charts

Normal Curve
 Distribution of data in which the mean, median and mode are at the same point.
 and in which is from the mean includes
 Skewness – Kurtosis
 68% of the scores 1+ from the means
 95% 2+ from score and 99% is 1+

Parametric statistics
 Normal distribution Equal variances – Independent observations
 Test based on data assumptions of normal distribution equal variances and independent observations

Non Parametric Statistics
 Distribution is not normal
 any of a number of statistical techniques used when the data do not meet the assumptions required to perform parametric

Statistical power
 the probability of rejecting a false null hypothesis
 The probability of making a correct decision!
 Directly related to the probability of making a type II error

Skewness
 description of the dirction of the hump of the curve of the data distribution and the nature of the tails of the curve
 *term that describes the position of the hump in the curve of a distribution is
 side to side
 Left positive skewness
 Right negative skewness

Kurtosis
 Description of the vertical characteristics of the curve
 Whether the curve is more peaked or or flatter

Statistical Significance
 A criterion for significance is set
 This is usually a probability set at .05
 if our calculated pvalue is less than the criterion for significance
 This is classed as ‘statistically significant’

Meaningfulness
The importance or practical significnat of an effect or relationship

Probability
Odds that a certain event will occer

Pvalue
 The probability that your results are due to chance or sampling error
 chance your results are due to chance or sampling error

Null hypothesis
 a statement of no difference or no relationship.
 statistical hypothesis that assumes that there is no difference among the effects of treatments
 i.e There is no difference between the vocabulary scores of average and highability students.

alpha a/ level of significance
level of probability set by the experimenter before the study

type 1 error
 rejecting the null hypothesis when its true
 probability of making a Type I error is denoted by the alpha (α)
 researcher claims that there is a difference between treatments (i.e., rejects the null hypothesis) when there really is no difference

Type 2 error
 accepting the null hypothesis when its true
 a Type II error is denoted by the beta (β) level

Beta
Magnitude of a type 2 error

Sample size
the number of participants in the study being evaluated or planned

Effect size/ delta
 the outcome of a study typically expressed in standard deviation units
 standardized value that is the difference between the means divided by the standard deviation
 Meaningfulness The size of the difference (Cohen’s d)
 the strength of the relationship (r2)

standard error
variability of the sampling distribution

Descriptive statistics
statistical techniques which helps us describe data

Inferential statistics
statistical techniques devised to allow us to generate from our data to populations

Quartiles
values which divides data set into exactly 4 equal parts

variance
the average of the squared deviates from the mean

cluster sampling
sampling where the population is divided into smaller identifiable clusters and one or more of these cluster are then randomly selected. Participation are then randomly selected from smaller cluster to take part in a study

Opportunity sampling
sampling from those people who are available at a particular time and place

snowball sampling
a sampling technique where individuals who have taken a part in a study provide detail of people they know who might also be willing to participate

Volunteer sampling
sampling which relies on participants coming forward to volunteer to take part in a study usually in response to an advertising

sampling error
bias in the estimation of population paremeters that arise from using samples

parameters
statistical descriptions of populations

statistics
description applied to samples

chance
same as probality odds of something happening

normal distribtution
a distribution of a scores which is symmetrical peaked in the middle, is bell shaped and equal on both sides of the peak

Bidirectional/ twotailed hypothesis
 Suggests a difference or relationship but not the specific direction of these
 *researcher predicts that there will be a difference between 2 groups but is unable to predict which group will score higher than the other
 There will be a difference between hearing aid and control groups in social anxiety scores
 a hypothesis where we have not specified the direction of the predicted difference or relations

Directional, uni/onetailed hypothesis
 States the direction of the difference or relationship
 ie. the hearing aid group will have lower social anxiety than the control group
 specified direction of the hypothesis.

a priori
Information needed in planning research • Alpha • Effect size • Power • Sample size

