CHAPTER 1-3 Mid Year Review Flashcards
What is a parameter?
A numerical summary of a population. Like a mean, median, range, of a population
<p>will residual plots always show outliers? (will outliers always have large residuals?)</p>
<p>Not necessarily, but usually. Some points have so much leverage, they pull the line up to it?</p>
What is undercoverage?
Undercoverage is when either one part of the population is not included in a survey or is underrepresented in the survey
what happens if you ADD a constant to each value in a data set?
it is SHIFTED only. Spread doesn?t change, but This effects all of the data values and measures of center (mean, med) and quartiles, deciles, etc, IT DOES NOT CHANGE THE SPREAD! (IQR, St Dev, Range all stay the SAME).
How can you think about the mean and median to remember the difference when looking at a histogram?
mean is balancing point of histogram, median splits the area of the histogram in half.
if you switch x and y does r change?
NO. The strength stays the same.
How do you find relative frequency?
just divide frequency by TOTAL,.
What percentile is Q3?
75th
What is Statistics?
The study of variability
What is a quantitative variable?
Quantitative variables are numeric like: Height, age, number of cars sold, SAT score, weight.
What is a big difference between subjects in experiments and members of a representative sample?
In experiments you don’t need a representative sample, you can have volunteers, convenient subjects and that is OK. You are looking at impact of treatment, not at getting a representative sample.
When drawing a graph or chart, what do you have to remember to do?
LABEL AXES, make a KEY(if needed ) AND GIVE IT A NAME!!! “Figure 1: Age and Food Preference”
Is matching blocking?
YES, little tiny blocks of one.
What’s the difference between lurking and confounding?
Lurking varibles, on one hand, infer the assoiation between the two varibles; confounding variables, on the other hand, make it unclear which variable has had an impact on which in an experiment.
If something is correlated is it associated?
Yes
For information purposes, which gives most, stem-leaf, histogram or box-whisker?
Stem leaf gives the actual values and the shape, histogram just the shape, and box-whisker the least amt, but are great for comparing multiple distributions.
what is the LSRL
the “least squares regression line”? that line, That equation
What is the difference between quantitative and categorical variables?
Quantitative variables are numerical measures, like height and IQ. Categorical are categories, like eye color and music preference
Sample size compared with the fraction of a population: For instance, do you need like 10% or 20% to have a good sample?
percent of popluation is irrelevent (as long as you have less than 10% for our procedures), The sample size determines how well the sample represents the population, not a fraction of the population sampled. The fraction of the population that you’ve sampled doesnt matter. Its the sample size its self thats most important. A sample of 100 people can tell you as much about a population of 10,000 as it can about a population of 2 Billion.
If the distribution is bimodal or multimodal, what would you use for center and spread statistics?
Talk about each mode (center) and maybe use the range or IQR. You could also say “one group is from __ to __ and the other from about __ to __”
What is homoscedasticity?
equal scatter along the regression line
What if a scatterplot goes straight across horizontally?
NO ASSOC. That would be like height and IQ. they are independent so each height has about the same IQ.
What is the total area under the normal curve?
one , or 1.000
Does a census make sense?
A census is ok for small populations (like Mr. Nystrom’s students) but impossible if you want to survey “all US teens”
What’s the difference between a prospective and a retrospective study?
A retrospective study takes a group and looks back at its history while a prospective study watches a group for a period of time and records the data. RETRO-REVERSE, PROspective- PResent and On,
What is statistically significant?
When an observed difference is too large for us to believe that it is likely to have occurred naturally (or just randomly). Basically it is Statistically Significant when we don’t think it happened randomly, When something is less than 5% likely to have happened by chance alone.
What is a census?
Like a sample of the entire population, you get information from every member of the population
What is meant by relative frequency?
The PERCENT of time something comes up (frequency/total)
What is a sample?
A subset of a population, often taken to make inferences about the population. We calculate statistics from samples.
If you want to find % below a value, what do put into normcdf (? ?)
find z score for value, and then normcdf (-999, Zright)
interpret r squared
r squared % of variability in y can be explained by the model WITH X. The rest is in residuals?
Use the following words in one sentence: population, parameter, census, sample, data, statistics, inference, population of interest.
I was curious about a population parameter, but a census was too costly so I decided to choose a sample, collect some data, calculate a statistic and use that statistic to make an inference about the population parameter (aka the parameter of interest).
Who chases the tail?
The mean chases the tail, the mean chases the tail, high-ho the derry-oh the mean chases the tail, and outliers,,.
data or datum?
datum is singular, Like “hey dude, come see this datum I got from this rat!” data is the plural, “hey look at all that data Edgar got from those chipmunks over there!!”
Can you predict an X by using a Y?
NOT WITH THE SAME EQUATION! BE CAREFUL!! You have to change the entire equation and start from scratch? Switch and run linreg with L2 v L1
Why blind the subject?
When people know they are getting a treatment, they may feel better even if the treatment doesn’t work. Their previous experience with the brand might bias their reporting or something,
Is it always better to do a census or a sample?
It depends, generally, it is better to do a sample since a census is expensive to execute, and because popultaions are always changing it is hardly more accurate then a sample. BUT,. For small populations, a census is fine.
What is a quality of SRS that is not a quality of Systematic, Stratified or Clustering?
In an SRS, all groups (samples) are possible, and ALL POSSIBLE GROUPS have the same chance of being picked. The other methods have lots of “impossible groups” SRS has no impossible groups.-Stratified- an impossible group would be all girls (you’re taking some boys and girls)-Clustered- an impossible group would be all girls (each cluster has boys and girls)-systematic- an impossible group would be 4 people that are right next to eachothe (you are taking every nth person)
To make a survey to tell of a restaurant is good, would you ask the people coming out of the restaurant?
People at the restaurant are probably there because they already like it. If you asked the question “Is this your first time dining here?” and if they say “yes” you survey them, that would be a better method. But then again, the people wouldn’t go into an Italian restaurant if they didn’t like that type of food.
Give some examples of response variables in an experiment
To test a medication, blood pressure might be response variable. To test and SAT course effect, SAT score might be response variable. To test a diet, “weight lost” might be a response variable.
what is marginal distribution? How does it differ from a conditional distribution?
overall distributions of a single variable in contingency table (out in margins) For instance, in a gender vs music preference, the overall distribution of gender would be a marginal distribution, like “22 males and 18 females”. A conditional distribution is within the table, a distribution along the given condition, for instance:” of the country music lovers, 8 were male and 3 were female”
Why don’t we always use the mean, we’ve been calculating it all of our life ?
It is not RESILIENT, it is impacted by skewness and outliers
Who can be blinded?
Subjects. Those delivering treatments. Those assessing effectiveness of treatments. and three mice.
the output for normcdf(Zleft, Zright) is_______
A PERCENT, or a probability, it is the area under the normal curve between the given z scores. The total area is 1 (or 100%)
What is an example of blocking that people often miss?
Matching, Like when someone does a pretest, treatment and then post test, they are blocked with themselves, aka matched to themselves
what are the percentiles from left to R on normal model?
2.5-16-50-84-97.5
What is Placebo used for?
Placebo is used for control in an experiment. the purpose of placebo is to determine the change between the controlled treatment and the other treatments
When do we often use mode?
With categorical variables. For instance, to describe the average teenagers preference, we often speak of what ?most? students chose, which is the mode. It is also tells the number of bumps in a histogram for quantitative data (unimodal, bimodal, etc,).
Look for lurking variables?
think hot chocolate sales in caf at wachusett mountain and ski accidents at wachusett mountain. Did the chocolate cause the accident??????
How can you tell if variables in a contingency table are independent?
If you look at the percents across the table or up and down. Like if 30% of males and 30% of females would both consider getting a pet pig, then you say gender and pet pig consideration are independent.
What is the difference between discrete and continuous variables?
Discrete can be counted, like “number of cars sold” or shoe size, school grade they are generally integers (you wouldn’t sell 9.3 cars), while continuous would be something like weight of a mouse, 4.344 oz.
What is wrong with using voluteers in an experiment?
Not much. In an experiment, we are not looking for a sample that is like the population, We just want to see the effectiveness of a treatment. It is fine if the subjects are all similar. In fact it is best sometimes when they are!
You want to simulate the likelihood of more than 4 psychology majors being on a full bus that seats 30.
Suppose that 1 in 9 students are psych majors. Use a random nunmber table.
use single digits on a random number table. Each digit represents a student on the bus. Ignore the zeros. Let 1 be a psych major, and 2 through 9 be other students. Trials end when you have reached 30 students. Count the number of psych majors (ones) in the trial. Record this. Do this 20 times. Find the percent of times there were 4 or more psych majors on the “bus.” If this occured in 5 trials, then the likelihood is 5 in 20, or 25%
are there any normal samples?
no, nothing is normal, just normalish. The only normal thing is the model we use.
mean/SD/median/IQR, How do I know which ones to use?
when unimodal and symmetric, mean and sd. When skewed or outliers use Median and IQR, when bimodal talk about the MODES and maybe range or iqr
what is leverage?
leverage just means it is far away from x-bar? far right or left from the middle, Some leverage points are not influential if they go along with the flow of the scatter.
which is explanatory variable?
x. horizontal axis. it “explains” what happens to y
If I take a random sample of 20 hamburgers from FIVE GUYS and count the number of pickles on a bunch of them, and one of them had 9 pickles, then the number 9 from that burger would be called ____?
a datum, or a data value.
Gender and Video Game playing are___________ because_______
associated (or not independent) because a higher percentage of males play video games. (think, It depends on gender)
How can you estimate the probability of an event occurring?
run a simulation. Find the percent of trials that you observed the event occur.
If I take a random sample 20 hamburgers from FIVE GUYS and count the number of pickles on a bunch of them, and the average number of pickles was 9.5, then 9.5 is considered a _______?
statistic. (t is a summary of a sample.)
What is a contingency table?
A two way table. shows distributions across 2 variables like gender and music pref.
when does a trial of a simulation end?
Generally there are two cases:1. You want to know the probability of having x successes in n attempts (getting 3 smokers in a group of 5 students). Trials end when you get to n (get to 5 students). You record the number of smokers for each trial.2. You want to know how many attempts it takes to get f successes. Trials end when you get f successes. Record the number of attempts.
How to describe association on a Scatterplot?
DIRECTION, FORM, STRENGTH
if you switch x and y will slope change?
YES- slope is rsy/sx? to get new slope you do: (r sqared)/old slope
What is the difference between a sample and a census?
With a sample, you get information from a small part of the population. In a census, you get info from the entire population. You can get a parameter from a census, but only a statistic from a sample.
How can you simulate rolling 1 die with a random number table
use only the digits 1-6, ignore 0, 7, 8, 9
what should we look for in resid plot?
curve or pattern, Also, it should have equalish scatter from left to right
What is a mutlistage sample?
A sample that combines several sampling methods
What’s a useful alternative when you can’t run an experiment? What are they useful forms of this, and how do you preform them respectively?
An alternative of an experiments could be an observational study. There’s two forms: prospective and retrospective. A prospective observational study is when you identify subjects in advance and record data as you go along. A retrospective observational study is when you analyze observations from the past.
How can you simulate on your calculator
RANDINT( lowest, highest, how many you want to grab)
What does normcdf do?
It gives you the area under the normal curve between any two z scores
What percent of the data is above Q3?
25%
What is the difference between a population mean and a sample mean?
population mean is the mean of a population, it is a parameter, sample mean is a mean of a sample, so it is a statistic. We use sample statistics to make inferences about population parameters.
Why blind the treatment givers?
The treatment givers may behave differently as they administer the actual stuff vs when they administer the placebo. They could cue the subjects unknowingly.
Samplin Method Types?
SRS, stratified, clustered, systematic, multistage, convenience, voluntary
When would you use two digits instead of a single on a random number table?
When the percent is not a multiple of ten, Like “18% ofdogs eat underwear”, You’ll have to assign 01-18, or 00-17 as undie eating dogs.
What is a conditional distribution?
A distribution within the table, along only one row or one column, NOT OUT IN THE MARGINS. So, on a table about food preference and grade in school, a conditional distribution would be “of the freshmen, 20% liked pizza, 50% tacos and 30% pasta”, a marginal distribution would be “overall, 25% liked pizza, 45% liked tacos and 30% liked pasta”
What is bias?What are some common errors?
It’s any systematic failure of a sampling method. COMMON ERRORS: Voluntary response, undercoverage of the population, nonresponse bias and response bias. We use randomness and methods like stratifying to reduce these.
Give a quick example of associated variables
A higher percentage of boys play video games than girls so we say “gender and video game playing are associated” or “gender and video game playing are not independent”
how do you interpret slope?
for an increas of 1 [unit of x] there is an (increase/decrease) of [SLOPE] [units of y]
Why do we plug 999 into normcdf?
normcdf needs two z scores, but we can’t plug in infinity. So we go down or up 999 standard deviations and that pretty much gets everything,.
How do students often mix up IQR and St. Dev
They INCORRECTLY think that Q1 is 1sd below the mean and Q3 is 1sd above the mean. THIS IS NOT TRUE!!!
are any populations actually normal?
no, nothing is normal, just normalish. The only normal thing is the model we use.
When comparing boxplots, what do you compare?
Medians and IQRS, ALSO, you might want to compare medians to quartiles if you can. For instance, if one has a median above the others Q3, you might say, Half of the first group scored over 80 while less than 25% of the second did.
What is a random sample?
When you choose a sample by rolling dice, choosing names from a hat, or other REAL RANDOMLY generated sample. Humans can’t really do this well without the help of a calculator, cards, dice, or slips of paper.
If someone does a pre and post test, what type of experimental design is it?
BLOCK design. Matching with themselves is blocking. Little blocks of two (well, actually one, you and yourself)
How do you find percentiles and make a boxplot from OGIVE?
Go across from .25, .5, and .75 till you hit the curve and then STRAIGHT DOWN!
What is the five number summary?
min- Q1 - Q2(median)- Q3 and max
When we say “the average teenager” are we talking about mean, median or mode?
It depends, if we are talking height, it might be the mean, if we are talking about parental income, we’d probably use the median, if we were talking about music preference, we’d probably use the mode to talk about the average teenager.
what happens if you multiply all of a data set by a constant?
it is scaled, Everything is effected. Mean/ median/ stand dev/ iqr/ quartiles all multiplied by that constant. Center, spread and all individual values are changed.
What does GSOCS stand for?
Gaps Shape Outliers Center Spread.
Why does it make sense to double-blind an experiment?
It reduces bias in an experiment. If subjects don’t know what treatment they’re receiving, they won’t change their habits based on that knowledge. If evaluators don’t know which treatment each subject is receiving, they won’t bias the true results based on the results they expect to see
What are random variables?
If you randomly choose people from a list, then their hair color, height, weight and any other data collected from them can be considered random variables.
Give example of incorrectly using the word “correlation”
“there is a correlation between gender and video game playing” This person should say “association.” You can’t say correlation because gender is categorical.
Why is it calle d “least squares regression line?”
Because, after you find the mean-mean point, you fix the line so that it minimizes the squared vertical distance to that line (minimizes the squared residuals)
What is the difference between a study and an experiment?
In a study you are basically just watching and in an experiment you are manipulating factors and (hopefully randomly) assigning treatments. Sometimes people call an experiment a study.
How do you match OGIVES to histograms?
RECTANGLE DROP!!
How are mean, median and mode positioned in a skewed right histogram? goes in the opposite order, Mode-median-mean
mode- median- mean (mean chases the tail)
What is the mode?
the most common, or the peaks of a histogram. We often use mode with categorical data
What is retrospective study?
A retrospective study is a study that looks backwards in time. They focus on estimating differences between groups or some association between.
What are INFERENTIAL STATS?
Look at your data, and use that to say stuff about the BIG PICTURE, like tasting soup, a little sample can tell you a lot about the big pot of soup (the population)
What are DESCRIPTIVE STATS?
Tell me what you got! Describe to me the data that you collected, use pictures or summaries like mean, median, range, etc,
