KonFound-it!.xlsx

	A	B	C	D	E	F	G	H	I	J	K
1	KonFound-it! ©: BASICS
2	unstandardized	User enters values in yellow					Optional: Only for Multivariate Impact Threshold (unconditional correlations)
3	estimated effect	standard error	sample size	# of covariates	α (significance level)	null hypothesis	std(y)	std(x)	R2	threshold	Max R2
4	-9.01	0.68	7639	231	0.05	0	13.53	0.24	0.22	0	0.286
5					For a 1-tailed test, double the size of α in cell E4
6	Calculated Values				name of predictor of interest:
7	df	default t critical (2-tailed)	t critical
8	7407	-1.960	-1.960	To override cell C8, type in your own value
9		The default sign of t critical is the same as the sign of the estimated effect.
10
11	Publishable statements
12	Replacement of Cases			Correlation Based (linear models only)
13	To invalidate the inference 85%			The minimum impact to invalidate an inference for a null hypothesis of 0 effect is -.132 and is based on correlations
14	of the estimated effect would have to be due to bias			of -.364 with and of .364 with the outcome, conditional on covariates.			(signs are interchangeable)
15
16	To invalidate the inference 85% (6509) of the cases would have			To invalidate the inference an omitted variable would have to be correlated
17	to be replaced with cases for which there is an effect of zero.			at -.305 with and at .325 with the outcome, before conditioning on covariates.			(signs are interchangeable)
18	Enhanced	% to replace	sdy unobserved	coefficient of proportionality	oster's delta* (using baseline of no covariates)
19	preserving standard error	0.8446062516	14.14273813	0.3264084256	-0.2831745639
20	conditional on covariates	0.850		requires special inputs: see Coeff of proportionality page
21				citation
22	Frank, K.A., Maroulis, S., Duong, M., and Kelcey, B. 2013.			Frank, K. 2000. "Impact of a Confounding Variable on the Inference of a Regression Coefficient." Sociological Methods and Research, 29(2), 147-194
23	What would it take to Change an Inference?:
24	Using Rubin’s Causal Model to Interpret the Robustness of Causal Inferences.
25	Education, Evaluation and Policy Analysis. Vol 35: 437-460.
26	See details of your sensitivity analysis on other tabs
27	↓ ↓ ↓ ↓ ↓ ↓				spreadsheet for calculating indices [KonFound-it!]
28					powerpoint with examples and calculations
29					cite this spreadsheet: Frank, K.A. (2014). KonFound-it!. Available at https://www.msu.edu/~kenfrank/research.htm#causal
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
91
92
93
94
95
96
97
98
99
100