Machine Learning Unit-2 Quiz

Percentiles

Quartiles provide information about a distribution's center, spread, and shape.

Median, quartiles, and percentiles

<p>They are the same.</p> Signup and view all the answers

<p>The 75th percentile</p> Signup and view all the answers

<p>The spread of the middle half of the data</p> Signup and view all the answers

<p>IQR = Q3 - Q1</p> Signup and view all the answers

<p>18</p> Signup and view all the answers

<p>The median is 32 grams.</p> Signup and view all the answers

<p>The first quartile (Q1) is 29 grams.</p> Signup and view all the answers

<p>The maximum weight is 38 grams.</p> Signup and view all the answers

<p>The range is 13 grams.</p> Signup and view all the answers

<p>The lower hinge (minimum) is $19.</p> Signup and view all the answers

<p>The third quartile (Q3) is $34.</p> Signup and view all the answers

<p>The sum is $61.</p> Signup and view all the answers

<p>There are 6 data points above the median.</p> Signup and view all the answers

<p>Ordinal data can be arranged in a meaningful order based on assigned values, while nominal data cannot.</p> Signup and view all the answers

<p>Mathematical operations cannot be performed on nominal data because it represents categories without inherent numerical value.</p> Signup and view all the answers

<p>Interval data does not have a true zero point, whereas ratio data does.</p> Signup and view all the answers

<p>An example of ordinal data is customer satisfaction levels like ‘Very Happy’, ‘Happy’, and ‘Unhappy’, which can be ranked from best to worst.</p> Signup and view all the answers

<p>Mode and median can be used with ordinal data, but the mean cannot be calculated.</p> Signup and view all the answers

<p>Ratio data can be added, subtracted, multiplied, or divided, and can calculate measures of central tendency like mean and standard deviation.</p> Signup and view all the answers

<p>An example of quantitative data is height, which can be measured in units like centimeters.</p> Signup and view all the answers

<p>In interval data, such as temperature in degrees Celsius, there is no true zero, so you cannot say one temperature is 'twice' another; in ratio data, such as weight, there is an absolute zero allowing such comparisons.</p> Signup and view all the answers

<p>Outliers can drastically shift the mean, causing it to misrepresent the data.</p> Signup and view all the answers

<p>The weighted mean is an average where different outcomes have different probabilities, it is useful when outcomes do not contribute equally.</p> Signup and view all the answers

<p>The final weighted average is 83.</p> Signup and view all the answers

<p>It suggests that the dataset is less likely to have significant outliers.</p> Signup and view all the answers

<p>The mode is the most common value in a dataset; for example, in 1, 1, 2, 2, 2, the mode is 2.</p> Signup and view all the answers

<p>Missing values can lead to an incomplete analysis and affect overall statistical conclusions.</p> Signup and view all the answers

<p>Examining data spread provides insights into variability and the distribution of data points.</p> Signup and view all the answers

<p>Significant deviations often indicate the presence of outliers or skewed data distributions.</p> Signup and view all the answers

<p>Ignoring tuples leads to the loss of potentially useful information from other attributes in those tuples.</p> Signup and view all the answers

<p>It is time-consuming and may not be feasible for large datasets with many missing values.</p> Signup and view all the answers

<p>It may create a misleading concept in the data, as all missing values would share the same constant value.</p> Signup and view all the answers

<p>The mean should be used for normal data distributions, while the median is better for skewed distributions.</p> Signup and view all the answers

<p>Missing values can be replaced with the mean or median of that class, such as mean income for a specific credit risk category.</p> Signup and view all the answers

<p>Regression, inference-based tools using Bayesian methods, or decision tree induction can be employed.</p> Signup and view all the answers

<p>Min-max normalization scales data to a specified range, typically [0.0, 1.0], by transforming values from an original range.</p> Signup and view all the answers

<p>It may oversimplify the data relationships and fail to account for variations within the dataset.</p> Signup and view all the answers

<p>The interquartile range is 13.</p> Signup and view all the answers

<p>The first quartile is the mean of the two middle values, calculated as (64+64)/2 = 64.</p> Signup and view all the answers

<p>A box plot visually shows the distribution of numerical data, including quartiles and averages.</p> Signup and view all the answers

<p>The median marks the mid-point of the data and is represented by the line dividing the box.</p> Signup and view all the answers

<p>The lower whisker indicates scores outside the middle 50%, specifically the lowest scores excluding outliers.</p> Signup and view all the answers

<p>This value is called the upper quartile or the third quartile.</p> Signup and view all the answers

<p>The five number summary consists of the minimum, first quartile, median, third quartile, and maximum.</p> Signup and view all the answers

<p>Outliers are shown at the ends of the whiskers and are identified as points outside the whiskers.</p> Signup and view all the answers

Categorical data without a natural order or ranking.

Categorical data with a clear, ordered relationship among values.

Numeric data that can be measured and has numerical values.

Numeric data where the difference between values is meaningful, but no true zero exists.

Numeric data with a true zero point, allowing for all mathematical operations.

The value that appears most frequently in a dataset.

The middle value when data is ordered from least to greatest.

The average value calculated by summing all values and dividing by the number of values.

Values that are significantly higher or lower than the rest of the data.

An average where some values contribute more than others based on assigned weights.

The difference between a data point and the mean or another measure like median.

The extent to which data values spread out from the mean or median.

Data points that are not recorded or available in a dataset.

The median of the lower half of data, where 25% fall below this value.

The median of the upper half of data, where 75% fall below this value.

The difference between Q3 and Q1, showing the range of the middle 50% of data.

A graphical representation showing the distribution of data based on quartiles.

A summary of data consisting of minimum, Q1, median, Q3, and maximum values.

Represents scores outside the middle 50% and extends to the maximum value.

Represents scores outside the middle 50% and extends to the minimum value.

An ineffective method for handling missing values by omitting incomplete data.

Manually entering missing values, which is time-consuming and impractical for large datasets.

Replacing missing values with a uniform constant, like 'Unknown', risking misinterpretation.

Using mean or median values to replace missing data, depending on distribution shape.

Replacing missing values with the mean or median for that classification category.

Filling in missing data using common values, often determined by regression or decision trees.

A method used to predict missing values based on other dataset attributes.

Scaling data to a specified range, typically [0, 1], using original min and max values.

The smallest value in a dataset.

The largest value in a dataset.

Values that divide a dataset into four equal parts, specifically Q1, Median, and Q3.

Values that divide a dataset into 100 equal parts.

The 50th percentile; also known as the median.

Using quartiles to indicate distribution's spread and shape.

Using salary data to find quartiles and IQR.