Terms : Hide Images
| 9739292173 | Categorical vs Quantitative Data | Data are categorical if they fall into groups or categories and data are quantitative if they take on numeircal values where it makes sense to find an average. -Use bar graphs, pie graphs, or segmented bar charts for categorical variables -Use dotplots, stemplots, histograms or boxplots for quantitative variables such as age or weight. | 0 | |
| 9739318373 | Marginal vs. Conditional Distributions | In a two-way table, marginal distributions consider only one variable and use the total row/column of the table only. Conditional distributions describe the distribution of one variable for a specific value of the other (one row/column inside the table). | 1 | |
| 9768900763 | SOCS | Shape - Skewed Left, Skewed Right, Symmetric, Uniform, Unimodal (one peak), Bimodal (two peaks) Outliers - Discuss them if they are obvious Center - Mean or median Spread - Range, IQR, or Standard Deviation | 2 | |
| 9768932036 | Comparing Distributions | Address SOCS in context! You must use comparison phrases like "is greater than", etc. | 3 | |
| 9768943930 | Outlier Rule | Upper Cutoff = Q3 + 1.5xIQR Lower Cutoff = Q1 - 1.5xIQR IQR = Q3-Q1 | 4 | |
| 9768965302 | Interpret Standard Deviation | Standard deviation measures spread by giving "typical" distance that the observations (context) are away from the mean (context) | 5 | |
| 9768984020 | How does the shape affect measures of center? | In general,
Skewed Left (mean | 6 | |
| 9769047552 | Interpret a z-score | Z = (value - mean)/(standard deviation) A z-score describes how many standard deviations a value falls above/below the mean. Positive z-scores are above the mean, negative z-scores are below the mean. | 7 | |
| 9769080965 | Linear Transformations | a+bx adding/subtracting "a" to every member of a data set adds "a" to the measures of center, but does not affect shape or spread. Multiplying every member of a data set by "b" multiplies measures of center by "b", measures of spread by absolute value of "b" and does not affect shape. | 8 | |
| 9769129653 | Percentiles | The kth percentile of a distribution is the point that has k% of the values less than that point. For example, a student who has a test score in the 90th percentile has a score higher than 90% of all test takers. | 9 | |
| 9769153310 | The Standard Normal Distribution | The standard normal distribution with mean=0 and standard deviation = 1. Table displays areas to the left of z-scores. | 10 | |
| 9769179022 | Normalcdf and Invnorm calculator tips | Using boundaries to find area (probability) normlacdf(lower,upper,mean,SD) Using area (probability/percentile) to find boundary: invnorm(area to the left, mean, SD) | 11 | |
| 9769203852 | Describe an association in a scatterplot | S - strength of relationship (strong, moderate, weak) O-Obvious Outliers? F - Form (linear or non-linear) A - Association (positive/negative) | 12 | |
| 9769238178 | Interpret "r", the correlation coefficient | r is always between -1 and 1 Close to zero = very weak Close to 1 or -1 = very strong Exactly 1 or -1 = perfectly straight line Positive r = positive correclation Negative r = negative correlation | 13 | |
| 9769807531 | Interpret LSRL slope | For every one unit change in the x variable (context) the y variable (context) is predicted to increase/decrease by "b" units (context) | 14 | |
| 9769836926 | Interpret LSRL y-intercept "a" | When the x-variable (context) is zero, the predicted y-value (context) is "a" | 15 | |
| 9769854415 | What is a residual? | residual = actual y (or observed) - predicted y the residual measures the difference between the actual y-value and the predicted y-value. | 16 | |
| 9769881518 | Interpreting a residual plot | If there is a leftover pattern in the residual plot, then the model is not appropriate If there is no leftover pattern in the residual pot, then the model is appropriate. | 17 | |
| 9769922575 | Interpret LSRL "y-hat" | y-hat is the estimated or predicted value by the LSRL | 18 | |
| 9769927316 | Extrapolation | Using a LSRL to predict outside the domain of the explanatory variable. (can lead to ridiculous conclusions if the observed association does not continue) | 19 | |
| 9769947749 | Interprete LSRL "s" | s=______, the standard deviation of the residuals or a typical prediction error (context) | 20 | |
| 9769961215 | Interpret r-squared | _____% of variation in the y-variable (context) that is explained by the x-variable (context) using the LSRL model | 21 | |
| 9769981213 | Outliers and influetial points in regression | Any point that falls outsied the pattern of association should be considered an outlier. An influential point has a big effect on calculations like correlation and slope. It's usually an outlier in the x-direction. | 22 | |
| 9770011631 | LSRL computer printout | Use foot length to predict height: Predictor Coeff Constant 103.41 Foot Length 2.7469 S=7.95126 LSRL: Predicted Height = 103.41 + 2.7469xFoot length Typical predicted height will differ from the actual height by about 7.951 units | 23 | |
| 9770125113 | SRS | An SRS (simple random sample) is a sample taken in such a way that every set of n individuals has an equal chance of being the sample selected. | 24 | |
| 9770141603 | Using a random digits table to select a sample | Label - give every member of the population a numerical label wit hteh same number of digits. Use as few digits as possible. Randomize - read consecutive groups of digits of the appropriate length from left to right across a line in the table. Ignore reapeats and groups not used as labels. Stop when you have n different labels. The individuals who correspond to the labels selected are your sample. | 25 | |
| 9770180811 | Sampling Techniques | SRS - names in a hat Stratified - split the population into homogeneous groups, select SRSs from each group Cluster - Split the population into gropus(usually by location) called clusters, and randomly select whole clusters for the sample Census - An attempt to reach the entire population Convenience - Selects individuals in easiest to reach way Voluntary Response - People choose themselves by responding to a general appeal | 26 | |
| 9786155280 | Advantage of using a stratified random sample over SRS | Stratified sampling guarantees that each of the strata will be represented. When strata are chosen properly, a stratified random sample will produce better (less variable/more precise) information than an SRS of the same size. | 27 | |
| 9786170017 | Bias | A sampling method is biased if it consistently produces estimates that are too small or too large | 28 | |
| 9786182399 | Experiment vs. Observational Study | A study is an experiment ONLY if researchers impose a treatment upon the experimental units. In an observational study, researchers make no attempt to influence the results and cannot conclude cause-and-effect. | 29 | |
| 9786214455 | Confounding | Two variables are confounded if it cannot be determined which variable is causing the change in the response variable. For example, if people who take vitamins on their own have less cancer, we cannot say for sure that the vitamins are causing the reduction in cancer. It could be other characteristics of vitamin takers, such as diet or exercise. | 30 | |
| 9786238638 | Why use a control group? | A control group gives the researchers a comparison group to be used to evaluate the effectiveness of the treatments. (context) It allows the researchers to measure the effect of the treatment (context) compared to no treatment at all. | 31 | |
| 9786262154 | Blinding | When the subjects in an experiment don't know which treatment they are receiving, they are blind. If the people interacting with the subjects and measuring the response variable don't know which subjects received treatments, they are blind. If both groups are blind, the study is double-blind. | 32 | |
| 9786294825 | Experimental Designs | Completely Randomized Design - Units are allocated at random among all treatments. Randomized Block Design - Units are put into homogenous blocks and randomly assigned to treatments within each block. Matched Pairs - A form of blocking in which each subject receives both treatments in a random order or subjects are matched in pairs with one subject in each pair receiving each treatment, assigned at random. | 33 | |
| 9787372833 | Benefit of Blocking | Blocking helps account for variability in the response variable (context) that is caused by the blocking variable (context). If there really is a difference in the effectiveness of the treatments, using an appropriate blocking variable will increase power (probability of finding convincing evidence that the treatments are not equally effective) | 34 | |
| 9787405084 | Scope of Inference: generalizing to a larger population | We can generalize the results of a study to a larger population if we used a random sample from that population. | 35 | |
| 9787499877 | Scope of Inference: Cause-and-Effect | We can make a cause-and-effect conclusion if we randomly assign treatments to a experimental units in an experiment. Otherwise Association is NOT Causation! | 36 | |
| 9787514940 | Interpreting Probability | The probability of an event is the proportion of times the event would occur in a very large number of repetitions. Probability is a long-term relative frequency. | 37 | |
| 9787530169 | Law of large numbers | The law of large numbers says that if we observe many repetitions of a chance process, the observed proportion of times that an event occurs approaches a single value, called the probability of that event. | 38 | |
| 9787575213 | Complementary Events | Two mutually exclusive events whose union is the sample space. For Example: -Rain/No Rain -Draw at least one heart/Draw NO hearts |  | 39 |
| 9787630720 | Conditional Probability | Probability that one event occurs given that another event is already known to have occurred. On Formula Sheet |  | 40 |
| 9787652535 | Two events are independent if |  | 41 | |
| 9787661162 | Two events are mutually exclusive if |  | 42 | |
| 9787683423 | Interpreting Expected Value/Mean | If we were to repeat the chance process many times, the average value of __________ (context) would be about __________ (context) | 43 | |
| 9787701233 | Mean and Standard deviation of a discrete random variable |  | 44 | |
| 9789257028 | Mean and standard deviation of a transformation of a random variable |  | 45 | |
| 9789267128 | Mean and standard deviation of a difference of two random variables |  | 46 | |
| 9789277664 | Mean and standard deviation of a sum of two random variables |  | 47 | |
| 9789284235 | Binomial Setting and random variable |  | 48 | |
| 9789323208 | Binomial Distribution (Calculator usage) |  | 49 | |
| 9789330244 | Mean and standard deviation of a binomial random variable |  | 50 | |
| 9789349225 | What is a sampling Distribution? | A sampling distribution is the distribution of a sample statistic in all possible samples of the same sample size. It describes the possible values of the statistic and how likely these values are to occur. Contrast with the distribution of the population, and the distribution of a sample. | 51 | |
| 9789408582 | What is the sampling distribution of p-hat (sample proportions)? |  | 52 | |
| 9789421180 | What is the sampling distribution of x-bar (sample means)? |  | 53 | |
| 9789429294 | What is the central limit theorem (CLT)? | If the population distribution of a variable is not normal, the sampling distribution of the sample mean will become more and more normal as the sample size (n) increases. | 54 | |
| 9789455166 | 4-Step Process Confidence Intervals |  | 55 | |
| 9789468769 | Unbiased estimator | A statistic is an unbiased estimator of a parameter if the mean of its sampling distribution equals the true value of the parameter being estimated. | 56 | |
| 9789490876 | Interpreting a confidence interval | I am ______% confident that the interval from ______ to _______ captures the true ___________ (parameter in context) | 57 | |
| 9789501495 | Interpreting a confidence level | If many, many samples are selected and many, many confidence intervals are calculated, about _____% of them will capture the true ________(parameter in context) | 58 | |
| 9789602391 | Standard error vs margin of error | The standard error of a statistic measures how far the value of the statistic typically differs from the true value of the parameter. The margin of error estimates how far we expect the parameter to differ from the statistic, at most. | 59 | |
| 9789634878 | What factors affect the margin of error? | The margin of error decreases when: -the sample size increases -the confidence level decreases | 60 | |
| 9789651619 | Inference for means (conditions) |  | 61 | |
| 9789661446 | Inference for proportions (conditions) |  | 62 | |
| 9789670053 | 4-Step process Significance tests |  | 63 | |
| 9789679273 | Explain a p-value | Assuming that the null hypothesis is true (context) there is a ______ probability of observing a statistic (context) as large or larger than the one actually observed by chance alone. | 64 | |
| 9789704119 | Type I and Type II Error and Power |  | 65 | |
| 9789728958 | Factors that affect Power |  | 66 | |
| 9789739534 | Paired t-test, Identification hints |  | 67 | |
| 9789748914 | Two sample t-test, Identification hints |  | 68 | |
| 9789760216 | Chi-squared tests (conditions) |  | 69 | |
| 9789768449 | Types of Chi-squared tests | Goodness of Fit: Use to compare the distribution of a categorical variable in one population to a hypothesized distribution. Homogeneity: Use to compare distribution of a categorical variable for 2+ populations or treatments. Independence: Use to test the association between two categorical variables in one population. | 70 | |
| 9789807469 | Chi-squared tests, df and expected counts |  | 71 | |
| 9789816316 | Inference for regression with computer output |  | 72 |
