STATS: prelims

stats

○       key words are summarise numerical information about a sample

○       Anything that would  describe

what is descriptive statistic

what are the Measures of central tendency

○       Mean

○       Median

○       Mode

Measures of variability

○       Range

○       Standard deviation

○       Variance

○       Interquartile range

Branches of statistics

1.  Descriptive statistics

2.  Inferential Statistics

what is in descriptive statistics

●       Distribution

●       Measures of central tendency

●       Measures of variability

what is Inferential Statistics

○       draw conclusions about the broader population based on numerical information from a sample

●       Hypothesis testing

• Regression Analysis

what is in hypothesis testing

○       Z test

○       F test

○       T test

○       ANOVA test

○       Wilcoxon signed rank test

○       mann -whitney U test

what is in regression analysis

-        Aims to really predict

■       Linear Regression

■       Nominal Regression

■       Logistical Regression

■       Ordinal Regression

Types of variables

1. categorical

2. numeric

Types of categorical variables

1. nominal -    Describes a name, label or category without natural order 

2. ordinal - values are defined by an order of realtion (somewhat agree, agree, disagree, somewhat disagree)

Types of numeric

1. continuous/interval - infinite number ( 1.6321748 or 1.63)

2. discrete/ ratio - finite (number of people in a household)

• Nominal

type of categorical that describes a name, label or category without order

• Ordinal:

• the data can be categorized and ranked.

• Interval: ( continuous)

○ Infinite number of real values within a given interval

• Ratio: (discrete)

• finite

• has a natural zero

what are the four levels of measurement

nominal

ordinal

interval

ratio

Hypothesis- tesing

Generating theories and testing them:

Theory

➢    Not a fact

➢    system of ideas intended to explain something

❖     Hypothesis

➢    proposed explanation made on the basis of limited evidence as a starting point for further investigation

How to know if it’s a USEFUL THEORY:

1. generates research

2. falsiable

3. organizes

4. guide action

5. internally consistent

6. parsimonious

generates research

○       ability to stimulate and guide further research - Descriptive and Hypothesis Testing

Falsifiable

○       Its ability to be confirmed or disconfirmed

Oragnizes

able to shape able to shape into a meaningful arrangement.

Guide Action

Guide the practitioner over the rough course of day-today problems

Internally Consistent

○       Use concepts and terms that have been clearly and operationally defined.\

○ operational definition

Parsimonious

finding the simplest accurate explanation.

types of research design

1. between groups

2. within groups

what is between groups

• they are unrelated groups

• participants experience one, and only one, level of the independent variable

• participants are divided in 2 groups and each group only has One treatment condition

• treatment A - placebo

• treatment B - new medication

what is within groups

• related groups

• all participant experience 2 treatments

Control group

participants who do not receive the experimental treatment.

experimental group

receives the treatment whose effect the researcher is interested in.

example of between groups

anova - one and two way anova

independent t- test - difference between two groups

example of within groups

1. repeated measures anova - compares means across one or more variables that are based on repeated observations

2. Dependent T-test - Compares the means of two related groups to determine whether there is a statistically significant difference

what is frequency distribution?

it is pattern of a set of numbers

1. raw score

2. frequency table

what is group frequency tables

population, uniform interval

ex: 3,6,9,12

only use when data cover has a huge range and data can go to many decimal places

what is the meaning of central tendency

refers to the descriptive statistic that best represents the center of a data set

mean

• average

  • sample- statistics

  • population-parameters

• numerical and normally distributed

median

●       Middle score

• categorical numerical and skewed

●       Arranged in ascending order

Eg: 5,2,1,3  —> 1,2,3,4,5

Mode

●       most common score

• nominal - name or label

types of mode

1.     Unimodal

●       One mode

2.     Bimodal

●       Two modes

3.     Multimodal

●       More than two modes

what is the BEST CENTRAL TENDENCY TO USE?

●       Mean because it is  normally distributed and best frequency distribution

range

●       range=  x(highest) minus X (lowest)

INTERQUARTILE (IQR)

●       Gives more description sa range

• Q1,Q2,Q3

VARIANCE

• mean or average but squareD (squared deviation)

• is a measure of how data points vary from the mean, whereas standard deviation is the measure of the distribution of statistical data.

STANDARD DEVIATION

the square root of the average of the squared deviations

types of sample and probability

1. random sample

2. convenience sample

probability sampling is

Random sample

non probability sample is

convenience sample

what is random sample ?

every member of the population has an equal chance of being selected into the study

4 types of probability sampling

1. simple random - fishbowls, spin the wheel

2. systematic - every 5th person , odd or even

3. Stratified - male and female strata

4. cluster - using simple and systematic select a representative strata - LGBTQ

what is Convenience sample

uses participants who are readily available. Volunteer sample

4) NON-PROBABILITY SAMPLING

1. Convenience

●       Individuals happen to be easily accessible

●       Nagtambay participants

2. Purposive

●       Seeking out specific samples

●       Ex: Gathering survivors

3. Snowball

●       Recruiting participants from other participants

●       Ex: A survivor may know other survivors

4. Quota

●        Setting a quota for each strata

●        Ex: Only recruiting 20 Apple users and 20 Android users

Types of selection bias:

1. sampling bias

2. survivorship bias

3. attrition bias

4. non-response bias

5. volunteer bias

6. undercoverage bias

7. confirmation bias

Personal probability

●       Best guess or estimate

Expected Relative-Frequency Probability

likelihood of an event occurring based on the actual outcome of many, many trials

TRIAL

refers to each occasion that a given procedure is carried out

OUTCOME

●       refers to the result of a trial

 7 types of MISLEADING GRAPHS

1. FALSE FACE VALIDITY LIE 

2. BIASED SCALE LIE

3. SNEAKY SAMPLE LIE

4. INTERPOLATION LIE

5. EXTRAPOLATION LIE

6. INACCURATE VALUES LIE 

7. OUTRIGHT LIE 

   ·   

what is sampling bias ?

some members of the population are less likely to be included than others

What is survivorship bias?

people are more likely to be represented in the sample than unsuccessful ones

Attrition Bias?

articipants who drop out of a study systematically differ from the ones who remain

Non-response bias?

People who refuse to participate

Volunteer bias?

People with specific characteristics are more likely to participate than others

undercoverage bias?

correct participant but inadequate participants

●       Saktu but kuwang a respondents

Confirmation bias?

unintentional tendency to pay attention to evidence that confirms what we already believe

False face validity lie?

method looks correct but when we dig a little deeper, it does not

BIASED SCALE LIE?

• slants information in a particular way

SNEAKY SAMPLE LIE ?

preselecting participants in a study to make the data turn out in a particular way

interpolation lie?

• a misleading graph that some value between the data points necessarily lies on a straight line between those data points

• assumes the value between 2 data points follow the same pattern

EXTRAPOLATION LIE?

• goes beyond the data by assuming that a pattern will continue indefinitely. 

• assumes the knowledge outside the study

INACCURATE VALUES LIE ?

• involves telling the truth in one part of the data but visually distorting it in another place

• uses scaling to distort portions of data

Outright lie ?

People making up data

what are the common types of graphs

1. scatter plot

2. line graph

3. bar graph - histogram and frequency polygon

4. steam-and-leaf plot

5. pictorial graph

6. pie chart

7. pictorial graph

what is scatter plot?

• relation of two variables

  ● Range-frame - minimum to maximum scores

  ● Linear relations - straight line

  ● Non-linear relations - curves or breaks

what is line graph?

• Change in variable over time

Line of Best Fit - predictions 

Time plot or time series 

what is bar graph

• IV: Categorical

• DV: Numerical

Pareto Chart - a type of bar graph in which the categories along the x-axis are ordered from highest bar on the left to lowest bar on the right

what is Histogram?

graph used to represent the frequency distribution of a few data points of one variable

• its like bar grpah but naay decimals

why do we use histogram and frequency polygon ?

because two most common methods for graphing scale data for one variable

what is Frequency Polygon?

• dots are connected with a line

• Alternative of histogram, looks like line graphs but naay interval decimals

when do we use the STEM-AND-LEAF PLOT?

because Histogram and frequency polygons do not let us view two groups in a single graph very easily

Chart Junk 

any unnecessary information or feature in a graph that detracts from a viewer’s ability to understand the data

what are the features of chart junk?

• moire vibrations

• grids

• ducks

what is moire vibrations?

patterns that computers provide as options to fill in bars 

what is grids in chart junk ?

type of chart junk that has a background pattern, almost like graph paper, on which the data representations, such as bars

what is ducks in chart junk?

features of the data that have been dressed up to be something other than merely data, unnecessary designs