# CHAPTER 1: Investment Management Certificate

?
Convenience Sampling
Choosing the sample that is easiest to collect information from.
1 of 27
Judgement Sampling
Making a judgement of the sample that would best represent the population
2 of 27
Snowball sampling
Used where the data subjects are rare. Relies on referrals from initial subjects.
3 of 27
Discrete/Continuous
Discrete - Units of measurement cannot be split up. Continuous - infinite data
4 of 27
Quota Sampling
Often used in market research as a form of non-random selection. Breaks the members into categories with 'sub-quotas' for each type.
5 of 27
Stratified Sampling
Reduces sampling error by selecting amount that represents population. The individuals though are randomly.
6 of 27
Systematic Sampling
Non-random sampling. Select the nth record of a population. i.e. every 5th person on an alphabetical list of employees.
7 of 27
Relative Frequency and Cumulative frequency
Relative frequency it is a % of the whole. Cumulative frequency is the sum of the relative frequencies up until that category.
8 of 27
What are the visual representations of discrete data
bar chart, pie chart
9 of 27
What are the visual representations of Continuous data
Histograms, time series graphs, log (semi-log) graphs
10 of 27
Draw the Standard Deviation for sample and for population
/
11 of 27
Inter-Quartile Range
The 'median' is the 2nd quartile. You can then find the 1st and 3rd quartile. The IQR is the value at the 3rd quartile minus the value at the 1st quartile. It is not distorted by extreme values.
(n+1)x1/4= 1st quartile
(n+1)x3/4 = 3rd quartile
12 of 27
Where distributions are normal, what % of observations will fall on either side of the mean?
50%
13 of 27
Where distributions are normal, what % of observations will fall within 1 standard deviation of the mean?
68.26%
14 of 27
Where distributions are normal, what % of observations will fall within 2 standard deviation of the mean?
95.5%
15 of 27
Where distributions are normal, what % of observations will fall within 3 standard deviation of the mean?
99.75%
16 of 27
Positively Skewed distribution
if the peak of the curve lies to the left of the center, it is said to be positively skewed. MODE>MEDIAN>MEAN
17 of 27
Negatively Skewed distribution
If the peak of the curve lies to the right of center, it is said to be negatively skewed.
MEAN>MEDIAN>MODE. Hint: in negatively skewed distributions the mean, median and mode are in alphabetical order.
18 of 27
Geometric mean
multiply the differences together. Square root by the Nth number. -1. *100.
19 of 27
Perfect correlation
Relationship where changes in one variable are reflected by a proportional change in another. Like mass and weight
20 of 27
Auto correlation
Measure the relationship between an assets past performance and current performance. Correlation used to predict future performance.
21 of 27
How do you achieve diversification
Combining securities which are not perfectly positively correlated. Risk reduction achieved through combining assets with a low/negative correlation in returns. The lower the correlation in returns the greater the diversification and the lower the risk.
22 of 27
Correlation Coefficient
Correlation will always be between +1 and -1. COV(x,y)/SDxSDy
23 of 27
Bivariate Linear Regression
The 'least squares' method used to plot a line across the middle of all the points. 'Best Linear Unbiased Estimator (BLUE)/line of best fit. Can use bivariate linear regression to predict y axis with y=a+bx
Y=dependent variable
X= independent variable
a =
24 of 27
R squared
Coefficient of determination and gives us an impression of accuracy in forecasts. Ranges between 0-100, the higher the number the more accurate the predictive power. The % of a funds movement that is explained by a benchmarks movement.
25 of 27
Extrapolation
Bivariate linear regression used to predict an outcome outside of the range of values
26 of 27
Interpolation
Viewed as more reliable. Bivariate linear regression used to predict an outcome within the range of values.
27 of 27

## Other cards in this set

### Card 2

#### Front

Making a judgement of the sample that would best represent the population

#### Back

Judgement Sampling

### Card 3

#### Front

Used where the data subjects are rare. Relies on referrals from initial subjects.

### Card 4

#### Front

Discrete - Units of measurement cannot be split up. Continuous - infinite data

### Card 5

#### Front

Often used in market research as a form of non-random selection. Breaks the members into categories with 'sub-quotas' for each type.

## Comments

No comments have yet been made

## Similar Business Studies & Economics resources:

See all Business Studies & Economics resources »See all IMC Unit 2: Statistics CH1 resources »