-
Notifications
You must be signed in to change notification settings - Fork 0
/
coherePromptsV4.txt
90 lines (81 loc) · 3.24 KB
/
coherePromptsV4.txt
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
Prompt:
"
Please organize the following ideas into a coherent notes document IN HTML. Add words to make complete sentences, and generate some headings where necessary. Use the outline style of note taking:
Data Skewing
Data skewed left: more data on right, large left tail.
Data skewed right: more data on left, large right tail.
Standard Deviation
Find mean
Find sum of squared deviations
Find variance: divide squared deviations / (n-1)
Take square root
Empirical Rule
Middle 68% is 1 standard deviation.
Middle 95% is 2 standard deviation.
Middle 99.7% is 3 standard deviation.
Unusual: +- 2 standard deviations.
"
Response:
"
Data Skewing
Data is skewed to the right if more data is on the left and the distribution has a large right tail.
Data is skewed to the left if more data is on the right and the distribution has a large left tail.
The standard deviation is used to find the variance of a distribution.
The empirical rule states that 68% of the data is within 1 standard deviation of the mean, 95% of the data is within 2 standard deviations of the mean, and 99.7% of the data is within 3 standard deviations of the mean.
The mean, the standard deviation, and the empirical rule can be used to calculate the variance of a distribution.
"
--SEPARATOR--
Prompt:
"
Please organize the following ideas into a coherent notes document IN HTML. Add words to make complete sentences, and generate some headings where necessary. Use the outline style of note taking:
1 prop Test Statistic:
z = (p̂ - p) / sqrt(p*(1-p)/n)
z = (0.16 - 0.20) / sqrt(0.2*0.8/400)
z = -2
In this example, 0.16 is sample prop, 0.2 is pop prop, n=400.
Plot z=-2 on normal distribution curve, find area more extreme (1 or 2 tailed). In this case, area=0.025.
Significance level is 0.05, so strong evidence, reject null hypothesis.
"
Response:
"
2. Normal distribution
- Mean = average
- Standard deviation = spread
- Standard error = sqrt( Standard Deviation / N)
- N is number of data points
3. Samples and population
- Samples: a group of observations
- Population: the whole group
4. Hypothesis testing
- Null hypothesis: H0
- Alternate hypothesis: H1
- Significance level: alpha
- Type 1 error: rejecting H0 when it is true
- Type 2 error: not rejecting H0 when it is false
- Power: the probability that you'll correctly reject the null hypothesis
5. Confidence intervals
- Interval width: se
- Interval width: 1- se
6. Chi-square distribution
- Chi-square distribution is used to compare two groups
- Chi-square distribution is used to compare more than two groups
- Chi-square distribution is used to compare more than two groups and test for independence
- Chi-square distribution is used to compare more than two groups and test for correlation
- Chi-square distribution is used to compare more than two groups and test for regression
7. Confidence intervals for Chi-square distribution
- Interval width: se
- Interval width: 1- se
8. One-way ANOVA
- Independent variables: X1, X2
- Dependent variable: Y
- Null hypothesis: Ha
- Alternate hypothesis: Hb
- Significance level: alpha
- Power: beta
- Type 1 error: rejecting Ha when it is true
- Type 2 error: not rejecting Ha when it is false
- Type 3 error: rejecting Hb when it is true
9. Confidence intervals for one-way ANOVA
- Interval width: se
- Interval width: 1
"