data analysis - tools

quanalitive nymbers , measure time reactions

qualitive analysis not dealing with m=numbers more complex data like interview ened survey resposes

quanative methods measure anxiety levels bth the what and the why

super number heavy quanative research the way you word a survey can be bias on how the research may go

correlation vs causation

assume that one causes the other

example ppl ho eat alot choclate are creative mabe? or it could be people who are creative are more attracted to chocolate

carefully design experiment so there is no bias

measure of central tendency -mean,median ,mode

graphs - visua representation of data such as histograms, scatterplots and bar graphs can be used to understad the distribuation of data

types of statistical analysis 😀 t-test use ti compare the means of two groups

analysis of variance- compare the means of three or more groups

correlation - used to examine the relationship between two carables

liner regression- used to predict the value of one variable from another

chi- square - used to analyze catergorical data

statisitical analysis to determmine if the observed effects are due to chance

inferferences about populaton variables- psch research to draw a conclusion about a larger population

statisitcs enable researchers to generalize finsings from asample to a broader group

statisitcal. technique like correlation. and regression help quantify analyze these relationships

data visualtion and commuication psychologist use. statisitcs to. summarize,, visualize and communicate theri. research fidings effectively

descriptive statiscitcs - a set of techniques for summarizing and displaying the data from your sample

distribuation- the way scores are distributed across the levels of that variable

frequency table- (way to display the distribution of a variable & the number of participants with that value

histogram - a graphical display of a frequency distribution

symmetrical - a histogram left and right halves are mirror images of each other

skewed- when a histogram peak is either shfted toward the upper end if its range & has a relatively long negative tail ( neg. skewed) or the peak is shifted toward the lower end of its range & has a relatively long postive tail ( postive skewed)

outlier-an extreme score that is much higher or lower than the rest of the scores in the distribution

central tendency -is its middle - the point around which the scores in the distrubution tend to cluster “average”

mean- average of a distrubution of scores ( symbolized M) where the sum of the scores are divided by the number of scores

median - midpoint of a distrubtion of scores in the sense that half the scores in the distribution are less than it and half are greater than it

mode- most frewuent occuring score in distribution

variability- of a distribution is the extent to which the scores vary around their central tendency

range- a measure of dispersion that measures the distance between the highest and lowest scores in distrbution

standard deviation- is the average between the scores and the mean in a distribution

variance - a measurement of the average distance of scores from the mean

percentile rank - for any given score the percentage of scores in the distribution that are lower that score

z score- is the difference between that individual score and the mean of the distribution, divided by the standard deviation of the distribution . it represents the number of standard deviations the score is from the mean

pie chart and bar charts can both be effective methods of potraying qualitative data , bar chart are BETTER when there are more than just a few categories and for comparing two or more distributions

qualitative variables are display using pie charts and bar charts.

QUANTITIVE variables are displayed as box plots , histogram , etc,

BAR charts the bar do not touch , in histogram the bars do touch , bar charts are appropriate for qualitative variables , whereas histograms are better for quantitative variables

types of variables : varaibles such as # of children in a household are called discrete variables since the possible score are discrete points on the scale

other varibales such as “time to respond to a question “ are CONTINUOUS variables since scale is continous & not made up of discrete steps

levels of measurement: Nominal scales- examples are gender , favoirte color etc one simply name or catergory nominal scales embody the lowest level of measurement

ORDINAL scales - research wishing to measure consumers satisfaction with microwave ask specify their feelings as either very dissatisfied , somwhat dissatisfied etc. unlke NOMINAL SCALE , ORIDIANL SCALE allow comparison of the degree to which 2 subjects posses the dependent variable , ORIDNAIL SCALE FAIL to capture important info,.

INTERVAL SCALE - numerical scale in which intervals have the same interpretation throughput

example 80-90 dregree vs 30 -40 (10 degree intervals ) same

RATIO scales - MOST INFORMATIVE scale , like a NOMInal scale it provides name , category for each object (nymbers serve as label) Like an ORDIANL scale he obj are orderes ( in terms of the ordering of the numbers) like an INTERVAL same DIFFERENCE at two places on the scale has the meaning , same ratio at two places on the scale also carries the same meaning

POpulation & samples - small subset of a larger set of data - to draw inferneces about the larger set the larger set is known as the population which the sample is drawn

simple random sampling - each memebr has an equal chance of being selcted into the sample , in addtion the selection of one member must be independent of the selection of every other member msut be independent of the selection of every other member

sample size matters

more complex sampling - not having everyone phone # is evaluating all of tx polpulation

stratified sampling - use if the poultion has number of distunct “strata” or groups identify members of your sample who belong to each group

convenience sampling- well design research projects with proper sampling , ,

types of research designs - experimental design , quasi- experimental design, non-experimental designs

descriptive statisctics - are # that re used to summarize and describe date

Inferential statistics -qhT VARIABLES ARE REALTED AS WELL AS HOW DID THE DATA BEHAVE