Exam 3

Question 1

What makes time series data different from what we have studied so far in this course?

Answer 1

This data has time or dates

Question 2

What are the major components of a time-series Signal?

Answer 2

Level: Average value of the series
Trend: Increasing, decreasing, or static
Seasonality: Repetition in the data
Noise

Question 3

What are the two models we can use to understand the major components?

Answer 3

multiplicative
additive

Question 4

How do we choose between multiplicative and additive models?

Answer 4

When to use multiplicative model: when repetition changes over time
When to use additive model: when multiplicative model statement isn’t true

Question 5

If a signal does not have seasonality, what should we expect to see in the graphs for the two models?

Answer 5

Additive = seasonality would be close to 0
Multiplicative = seasonality would be close to 1

Question 6

Which components are present in all signals, and which are not guaranteed?

Answer 6

All series have level and noise, however trend and seasonality are not guaranteed

Question 7

Why is kmeans considered unsupervised learning?

Answer 7

We do not know which group the data belongs to before clustering

Question 8

The steps for Kmeans clustering

Answer 8

Step 1: Randomly select K observations as initial cluster centroids (center)
* Step 2: Use a distance (similarity) metric for assigning each observation to one of K clusters
* Step 3: Recalculate cluster centroid
(center)
* Step 4: If any data points changed clusters in Step 2 AND we have not reached our max iterations, go back to Step 2

Question 9

Know the difference between the K in KNN and Kmeans

Answer 9

K in k-means: number of clusters
K in KNN: number of neighbors to compare for class assignment

Question 10

What is convergence?

Answer 10

Convergence: no change in clusters

Question 11

How do we understand the similarity of a datapoint to each cluster center?

Answer 11

Most similar == smallest distance
* Euclidean distance: Because we are calculating a distance, the features must be numeric for K-means clustering

Question 12

What do we use for predictors when using linear regression on
time-series data?

Answer 12

trend and seasonality as predictors

Question 13

How do we use seasonality as a predictor?
* What do we need to know to create a sub-interval for one repetition

Answer 13

Size of the sub-repetitions is the period

Question 14

How are the training and validation sets different for time-series Datasets?

Answer 14

assumes the relationship between time steps is linear

Question 15

How does the time step affect the linear regression models for forecasting? (give example)

Answer 15

If we use quarters to represent seasonality, we end up with 4 linear models
* If we chose to use months,we end up with 12 linear models

Question 16

How does linear regression differ for time-series data from traditional linear regression?
* Hint: How many lines are used to estimate the target?

Answer 16

Depends on the time your data is in and how you want to display it (months, days, etc)

Question 17

If seasonality does not exist

Answer 17

straight line graph

Question 18

what is the significance between multiplicative and additive

Answer 18

level and trend are going to be the same, you are wanting to see the difference between seasonality and noise (y-axis difference)

Question 19

which signals are always guaranteed and not

Answer 19

guarenteed = noise and level
not = trend and seasonality

Question 20

how does time models differ from linear

Answer 20

time (seasonality) is accounted and we are fitting multiple lines of data vs 1 to estimate repetition. training and validation also must be in chronological order