Biostatistics and its Application to Health Science Research Flashcards
Statistics is the field concern with four things, and what information is drawn from a subgroup ?
Statistics definition
•Field of study concerned with:
1) The collection, organization, summarization, and analysis of data.
2) The drawing of inferences about a body of data when only a part of the data is observed
What is a population Vs sample? What is a unit of analysis ? What are variables ?
Basic Concepts
Population: set of individuals on which a given characteristic is studied
–Sample: a subset of a population that is used to represent the entire group.
•Unit of analysis: is the “who” or the “what” that you are analyzing for your study. –Variables: properties, attributes or characteristics
What are parameters ? Statistics ? What is an estimator ?
Basic Concepts •Parameters: numbers that summarize data for an entire population. •Statistics: numbers that summarize data from a sample –If a statistic is used to approximate a parameter it is also often called estimator
What’s the difference between population and sample ?(diagram)
What are dependent vs independent variable.
Type of variables
•Dependent (outcome)
–is the variable being tested in a scientific experiment
–those that depend on the value that is assigned to other phenomena or variables
•Independent (exposures, predictors)
–a factor or phenomenon that causes or influences another associated factor or phenomenon
What is Nominal ? Ordinal ?.
Type of variables
•Categorical Variables (qualitatives)
–Nominal: Two or more mutually exclusive categories without having any kind of natural order. They are variables with no numeric value.
nominal sounds like name
..Names.basically refers to categorically discrete data such as name of your school, type of car you drive or name of a book. This one is easy to remember because nominal sounds like name (they have the same Latin root).
–Ordinal: The order matters but not the difference between values.
Ordinal refers to quantities that have a natural ordering. like people in the line
ordinal sounds like order.
What is the difference between discrete vs Continuous ?
Type of variables
•Numeric Variables (quantitative)
–Discrete: can only takes on a finite number of values
•Ex: # of beds at the hospital, # persons in a room
–Continuous: can take on any value in a certain range.
•Ex: Age, Weight, Height
What are four type of measurable scales ?
Why are they assigned this way ? (NO Irvin) measure this
Measurement Scales
•There are 4 types of measurement scales
–Nominal
–Ordinal
–Interval
–Ratio
•The 4 types of scale are arranged so that all the above scales have properties from the previous scale plus an additional property
.What is is nominal used for ? what is an example with smokers and non smokers.
Do binary data count ?
Nominal
- Use names to establish categories
- You can use numbers, but these are of a symbolic nature
Example:
Dichotomous / binary data
•Gender –> Male = 1 / Female = 0
Categorical data
•Civil Status–> Single = 0 /Married = 1 / Widow = 2
What is an example of a psychiatric evaluation of ordinal scale ?
What is ordinal ? does it number matter ?
Is the following example of nominal scale?
yes, it is just setting catagerous,
Symptoms of depression in psychiatric evaluation
- None = 0
- Mild = 1
- Moderate = 2
- Severe = 3
Ordinal
•When the order of the categories is important
–Numbers are used to place the categories in an order
•You can not set distance between two points
What is an interval ? What does zero mean ?
Intervals
- Meets the above characteristics
- Numerically records the distance between two points
- The zero does not indicate the absence of the characteristic and it is arbitrary
Example: temperature (0° C does not express an absence of temperature instead it is a state of the variable)
What is ratio ? What does zero mean ? Where is this method used in medicine ?
Ratio
- It corresponds to the more complete level of measurement.
- Zero indicates the absence of the characteristic and is absolute
- The difference between two values is of known magnitude
- Most of the measures used in medicine (anthropometrics and quantitative from the labs) use this type of scale.
Example: Weight – 0 pounds state an absence of weight Distance – 0 Km state an absence of distance
.What is descriptive statistics ? What kind of conclusion do you reach ?
Descriptive Statistics
- Numeric or graphical summary of data
- You reach statistical inferences using descriptive statistics
Like a scatterd plot
–Process to generalize the collected data by the researcher (sample) to all possible observations of interest (population)
.What is Frequency ? frequency distribution?
•Frequency: the number of times that something happens during a particular period
Frequency Distribution
•An arrangement of statistical data that exhibits the frequency of the occurrence of the values of a variable
.What are the three frequency in frequency distribution?
Frequency Distribution
- Absolute Frequency
- Relative Frequency
- Cumulative Frequency
–Absolute
–Relative
What is an absolute freqency ?
The absolute frequency is simply the total number of observations or trials within a given range. For example, assume there is a collection of grouped data for the percentage returns for a particular stock, which is ranged from lowest to highest.
What is relative frequency ?
how many times on thing happen/ total times all other thigns happen.
5 red apples were picked / 20 total apples were picked
What is relative frequency ?
Cumulative Relative Frequency
Relative Frequency. How often something happens divided by all outcomes. Example: Your team has won 9 games from a total of 12 games played: theFrequency of winning is 9. the Relative Frequency of winning is 9/12 = 75%
The Cumulative Relative Frequency is the sum of the relative frequencies for all values that are less than or equal to the given value.Aug 24, 2010
.
Measures of Central Tendency
- Numbers representing a central value in which the data appear to be clustered around
- Mean
- Median
- Mode
What is a mean? what is the formula ?
What is a medium ?
Median
- It is less affected by extreme values than the average
- It is the number that is exactly in the middle of a list of values that has been ordered
.
.What is a mode ? unimodel ? Bimodel ?
What is an example of a dot plot ?
What is skewness and kurtosis ?
Skewness and Kurtosis
- The measures of central tendencies obtain a representative value of the data.
- From the measures of variability (dispersion), we can know that whether most of the items of the data are close to or away from these central tendencies.
- Statistical means and measures are not enough to draw sufficient inferences about the data.
–This symmetry is well knowledge of the skewness
–Still one more aspect that we need to know is its flatness or otherwise its top. This is understood what is known as Kurtosis.
Review mean , median, mode grapth.
What is leptokurtic, mesokurtic, and platykurtic ?
lep·to·kur·tic
ˌleptəˈkərdik/
adjective
STATISTICS
(of a frequency distribution or its graphical representation) having greater kurtosis than the normal distribution; more concentrated about the mean.
mes·o·kur·tic
ˌmezəˈkərtik,ˌmē-/
adjective
STATISTICS
(of a frequency distribution or its graphical representation) having the same kurtosis as the normal distribution.
Platykurtic is a type of statistical distribution where the points along the X-axis are highly dispersed, resulting in a lower peak (lower kurtosis) than the curvature found in a normal distribution.
Lep-high
meso-middle-normal
platy-platued,down.
.What is a histogram, and what is another name for it ?
.What is interquartile range ? (IQR)
What is the formula for interquartile range ? what do each mean ?.
Turn it around and the the problem of interquartile range ?.
Examples of interquartile range . Turn in around
What is variance ? The formula ? What is the same too ?
Turn around the variance example ?
Turn around example of variance ?.
What is standard deviation, and what is the formula ?.
What is standard deviation for ?
What is coefficient of variations used for ? What is the ratio of ?
Which is the most and less homogenious ?.
what is a hypothesis ? What is a null hypothesis ? Alternative hypothesis ?
.
What is HO, and HA in two sided , and the one-sided ?
.Where is rejection region or critical value approach ?
What is a P value ? What happens if your P value is less or equel to significance value ?
What happens when you have signicance level of alpha of 5% ? Would you reject the Ho ? What is signfiance level also mean ?
.Turn over and explain true and false negative or positive
.Label what is statistical power, reject null, and fail to reject null
Chi-sqaured test and fishers’s exact , which one is parametric, and one which is not ?
do all people like chinese food ? how about fish ?
practice the example of Ho and Ha between males who will be obese compared to females
Independent vs dependent variables. How would you draw this ?
.what is used for unpaired T test ? Is it parametric or non-parametric ?
What is indepdence ? Normal distribution ?
Homogeneity of variance ?
Is Mann-Whitney test parametric ?
Examples of how to use Ho and Ha
.examples of indep and dependent variable ?
What do you use for unmatched data ? is it parametic ? and what other usesis there ?
Is keuskal-Wallis Test parametric ?
.Examples of indep- and depedent
Examples of independent and dependent variable .
What is Pearson correlation ? It must be normally distrubuted, therefore it cannot have any…
The values are between ? What do the ranges mean ?
Is it possible to predict? and what are accepted scale of measurements ??
What happens to pearson correlation when p=0 or p=/ 0
What happens if a null hypothesis is rejected ?
Is Spearman correlation sensitive to outliers ? Are avariables normally distributed ?
Is it non linear ?
What are the ranges ? from # to # ?
What happens if Rs is =1 , -1, or 0
What are accepted variable scale ?
What is logistic regression used for ? It is a measure between ? It represents the odd that ? It can be used to determine ?
it can be used to compare the magnitude of ?.
