Table 1: Examples of ρ and ψ functions used with M-estimators.
P( t ) |
___________ψ ( t )___________ | |
Least squares |
t2 |
21 |
Least absolute deviation |
∖t∖ |
sign(t) |
Quantile estimation |
{τ — I(x < 0) }x |
τ — I(x < 0) |
Huber: for ∖t∖ ≤ c |
t2 |
2t |
for c < ∖t∖ |
c∖t∖ |
c sign(t) |
Hampel: for ∖t∖ ≤ a |
t2 |
2t |
for a < ∖t∖ ≤ b |
a∖t∖ |
a sign(t) |
for b < ∖t∖ ≤ c |
ɪt — -∖t2 sign(t) |
a ( c — ∖t∖ ) /( c — b ) |
for c < ∖t∖ |
a∖t∖ |
0 |
Biweight (Tukey) |
— (c2 — t2)31(∖t∖ ≤ c)/6 |
t(c2 — t2)21(∖t∖ ≤ c) |
Sine (Andrews) |
—ccos(x/c)I(∖t∖ ≤ πc) |
sin(x/c)I(∖t∖ ≤ πc) |
10
More intriguing information
1. Gianluigi Zenti, President, Academia Barilla SpA - The Changing Consumer: Demanding but Predictable2. Motivations, Values and Emotions: Three Sides of the same Coin
3. The bank lending channel of monetary policy: identification and estimation using Portuguese micro bank data
4. Synchronisation and Differentiation: Two Stages of Coordinative Structure
5. NEW DEVELOPMENTS IN FARM PRICE AND INCOME POLICY PROGRAMS: PART I. SITUATION AND PROBLEM
6. The name is absent
7. The Global Dimension to Fiscal Sustainability
8. The Triangular Relationship between the Commission, NRAs and National Courts Revisited
9. The name is absent
10. Altruism with Social Roots: An Emerging Literature